Journal Description
Journal of Personalized Medicine
Journal of Personalized Medicine
is an international, peer-reviewed, open access journal on personalized medicine, published monthly online by MDPI. The Inter-American Society for Minimally Invasive Spine Surgery (SICCMI), Korean Society of Brain Neuromodulation Therapy (KBNT) and American Board of Precision Medicine (ABOPM) are affiliated with JPM, and their members receive a discount on article processing charges.
- Open Access— free for readers, with article processing charges (APC) paid by authors or their institutions.
- High Visibility: indexed within Scopus, PubMed, PMC, Embase, and other databases.
- Journal Rank: CiteScore - Q2 (Medicine (miscellaneous))
- Rapid Publication: manuscripts are peer-reviewed and a first decision is provided to authors approximately 17.4 days after submission; acceptance to publication is undertaken in 2.6 days (median values for papers published in this journal in the second half of 2024).
- Recognition of Reviewers: reviewers who provide timely, thorough peer-review reports receive vouchers entitling them to a discount on the APC of their next publication in any MDPI journal, in appreciation of the work done.
Latest Articles
Interstitial Lung Diseases and Lung Cancer: A Review on Similarities, Common Pathogenesis and Therapeutic Approach
J. Pers. Med. 2025, 15(5), 213; https://doi.org/10.3390/jpm15050213 - 21 May 2025
Abstract
Interstitial lung disease (ILD) prevalence and survival are increasing due to improvement in scientific research together with clinical complications typical of advanced disease. Lung cancer (LC) is described as a possible event occurring in lung parenchyma in the context of fibrotic abnormalities that
[...] Read more.
Interstitial lung disease (ILD) prevalence and survival are increasing due to improvement in scientific research together with clinical complications typical of advanced disease. Lung cancer (LC) is described as a possible event occurring in lung parenchyma in the context of fibrotic abnormalities that worsen patients’ prognosis. This growth of malignant cells on a fibrotic background has also been called scar-cinoma. For this reason, not only an early diagnosis but also personalized decisions on the best treatment approach should be considered for each patient in a multidisciplinary discussion, since in some cases chemotherapy or surgery could be detrimental for patients with pulmonary fibrosis. LC and lung fibrosis may share common pathogenetic mechanisms like an altered healing process in response to repeated tissue damage from environmental exposure in genetically susceptible individuals. Smoking history and air pollution together with mutations in telomere and surfactant protein genes lead to the production of cytokines and nitro derivatives in the microenvironment that facilitate the carcinomatous transformation during fibrogenesis. The evolution of LC therapy and the implementation of immunotherapy acting on targetable immune checkpoints have raised interest in evaluating ILD-LC actionable mutations. The main pathogenetic mechanisms, clinical presentations and treatment implications are presented in this review.
Full article
(This article belongs to the Special Issue Pathology and Molecular Diagnostics in the Personalized Treatment of Lung Diseases)
►
Show Figures
Open AccessArticle
Associations of PPARG and PPARGC1A Polymorphisms with Ritodrine-Induced Adverse Events in Patients with Preterm Labor
by
Eun Jeong Jang, Da Hoon Lee, Yubin Song, Jung Sun Kim, Young Ju Kim, Jeong Yee and Hye Sun Gwak
J. Pers. Med. 2025, 15(5), 212; https://doi.org/10.3390/jpm15050212 - 21 May 2025
Abstract
Objectives: Ritodrine, a tocolytic agent used to delay preterm labor, can cause several cardiovascular-associated adverse events (AEs). This study aimed to examine the relationship between gene polymorphisms in peroxisome proliferator-activated receptor gamma (PPARG) and PPARG coactivator-1α (PPARGC1A) and the
[...] Read more.
Objectives: Ritodrine, a tocolytic agent used to delay preterm labor, can cause several cardiovascular-associated adverse events (AEs). This study aimed to examine the relationship between gene polymorphisms in peroxisome proliferator-activated receptor gamma (PPARG) and PPARG coactivator-1α (PPARGC1A) and the occurrence of ritodrine-induced AEs. Additionally, a risk-scoring system was developed to identify patients at high risk of AEs. Methods: Patients aged 18 years or older who were administered ritodrine to manage preterm labor with intact membranes and uterine contractions occurring at 20–36 weeks of gestation were enrolled in this study. A total of 70 common PPARG and PPARGC1A variants (minor allele frequency ≥ 0.2) with low linkage disequilibrium (r2 < 0.8) were selected from an Axiom™ Precision Medicine Research Array (AMPRA). Results: A total of 149 patients were included in the analysis. After adjusting for confounders (age, gestational age, and the maximum infusion rate), weight and rs2946385, rs35523565, and rs2240748 of PPARGC1A were identified as significant predictors associated with ritodrine-induced AEs. Based on the risk-scoring system, the predicted probabilities of AEs for patients with scores of 0, 1, 2, 3, 4, and 5 points were 4%, 9%, 18%, 35%, 55%, and 74%, respectively. The AUROC for the risk score predicting ritodrine-induced AEs was 0.729 (95% CI: 0.672–0.831, p < 0.001). Conclusions: This study indicates that ritodrine-induced AEs are related to PPARGC1A polymorphisms. A risk-scoring system based on genetic variants showed moderate predictive ability for ritodrine-induced AEs, suggesting potential utility in females with preterm labor.
Full article
(This article belongs to the Section Pharmacogenetics)
►▼
Show Figures

Figure 1
Open AccessReview
Lactate as a Preoperative Predictor of Mortality in Patients Undergoing Emergency Type A Aortic Dissection Repair
by
Sombuddha Bhadra, Rachel H. Drgastin, Howard K. Song, Frederick A. Tibayan, Gurion Lantz, Julie W. Doberne and Castigliano M. Bhamidipati
J. Pers. Med. 2025, 15(5), 211; https://doi.org/10.3390/jpm15050211 - 21 May 2025
Abstract
Background: Aortic dissection is a life-threatening condition where emergent surgical repair is the standard of care. However, despite operative intervention, mortality is 10–15% in all patients. Objective markers to distinguish when surgical repair is more beneficial versus being futile are warranted. Currently, no
[...] Read more.
Background: Aortic dissection is a life-threatening condition where emergent surgical repair is the standard of care. However, despite operative intervention, mortality is 10–15% in all patients. Objective markers to distinguish when surgical repair is more beneficial versus being futile are warranted. Currently, no such known measures are widely agreed upon. Since most complications from aortic dissection stem from malperfusion, serum lactate is thought to be a surrogate marker for malperfusion. This scoping review aims to examine the preoperative predictive value of lactate or lactate dehydrogenase (LDH) in assessing postoperative mortality in patients undergoing surgical repair for acute Stanford Type A aortic dissection (ATAAD). Methods: PubMed was searched for the following search terms: “Dissection, Ascending Aorta”, “Dissection, Thoracic Aorta”, or “Aortic Dissection”. Prospective and retrospective randomized controlled trials, case reports, and cohort studies were included in the initial search. Studies were first screened for inclusion of preoperative lactate or LDH level with a search of “lac” or “LDH”. Included studies consisted of patients aged 18 or older diagnosed with Stanford Type A/Debakey Type I and II aortic dissection with reported preoperative lactate or LDH levels and postoperative mortality treated within 14 days of symptom onset. Preoperative laboratory values were measured from samples collected prior to patient transfer to the operating room or before utilization of ECMO intraoperatively. Results: A comprehensive database search identified a total of 4722 articles. After a rigid screening process, 46 studies fit the inclusion criteria. These papers reported a combined 4696 participants with either preoperative lactate or LDH levels and postoperative mortality. The mean preoperative lactate level was 2.4 mmol/L, whereas the LDH level was 424.9 U/L. Postoperative mortality was 16.51%. Average creatinine, BUN, platelets, INR, PT, PTT, and hemoglobin were all within normal lab analysis limits. Conclusions: Neither lactate nor LDH should be used as a solo predictor of postoperative mortality after ATAAD due to lack of consensus on the cut-off values. Accompanying clinical signs, lab abnormalities, and radiographic findings taken together may be better predictors of prognosis.
Full article
(This article belongs to the Special Issue Advances in Cardiothoracic Surgery)
►▼
Show Figures

Figure 1
Open AccessArticle
A Comprehensive Dataset for Activity of Daily Living (ADL) Research Compiled by Unifying and Processing Multiple Data Sources
by
Jaime Pabón, Daniel Gómez, Jesús D. Cerón, Ricardo Salazar-Cabrera, Diego M. López and Bernd Blobel
J. Pers. Med. 2025, 15(5), 210; https://doi.org/10.3390/jpm15050210 (registering DOI) - 21 May 2025
Abstract
Background: Activities of Daily Living (ADLs) are essential tasks performed at home and used in healthcare to monitor sedentary behavior, track rehabilitation therapy, and monitor chronic obstructive pulmonary disease. The Barthel Index, used by healthcare professionals, has limitations due to its subjectivity.
[...] Read more.
Background: Activities of Daily Living (ADLs) are essential tasks performed at home and used in healthcare to monitor sedentary behavior, track rehabilitation therapy, and monitor chronic obstructive pulmonary disease. The Barthel Index, used by healthcare professionals, has limitations due to its subjectivity. Human activity recognition (HAR) is a more accurate method using Information and Communication Technologies (ICTs) to assess ADLs more accurately. This work aims to create a singular, adaptable, and heterogeneous ADL dataset that integrates information from various sources, ensuring a rich representation of different individuals and environments. Methods: A literature review was conducted in Scopus, the University of California Irvine (UCI) Machine Learning Repository, Google Dataset Search, and the University of Cauca Repository to obtain datasets related to ADLs. Inclusion criteria were defined, and a list of dataset characteristics was made to integrate multiple datasets. Twenty-nine datasets were identified, including data from various accelerometers, gyroscopes, inclinometers, and heart rate monitors. These datasets were classified and analyzed from the review. Tasks such as dataset selection, categorization, analysis, cleaning, normalization, and data integration were performed. Results: The resulting unified dataset contained 238,990 samples, 56 activities, and 52 columns. The integrated dataset features a wealth of information from diverse individuals and environments, improving its adaptability for various applications. Conclusions: In particular, it can be used in various data science projects related to ADL and HAR, and due to the integration of diverse data sources, it is potentially useful in addressing bias in and improving the generalizability of machine learning models.
Full article
(This article belongs to the Special Issue Selected Papers From the pHealth 2024 Conference, Rende, Italy, 27–29 May 2024)
►▼
Show Figures

Figure 1
Open AccessArticle
Corneal Endothelial Changes After Phacoemulsification Using the Eight-Chop Technique in Diabetic Eyes
by
Tsuyoshi Sato
J. Pers. Med. 2025, 15(5), 209; https://doi.org/10.3390/jpm15050209 - 20 May 2025
Abstract
Background/Objectives: To analyze corneal endothelial changes and intraocular pressure (IOP) after phacoemulsification combined with the eight-chop technique and intraoperative parameters in patients with diabetes mellitus. Methods: The eyes of patients with cataracts who underwent phacoemulsification were analyzed in this study. Based
[...] Read more.
Background/Objectives: To analyze corneal endothelial changes and intraocular pressure (IOP) after phacoemulsification combined with the eight-chop technique and intraoperative parameters in patients with diabetes mellitus. Methods: The eyes of patients with cataracts who underwent phacoemulsification were analyzed in this study. Based on their hemoglobin A1c levels, patients were divided into two groups. The eight-chop technique was used for cataract surgery. The operative time, the phaco time, the aspiration time, the cumulative energy dissipated, and the volume of fluid used were determined. Best corrected visual acuity, IOP, corneal endothelial cell density (CECD), central corneal thickness (CCT), coefficient of variation (CV), and percentage of hexagonal cells (PHC) were recorded before and after surgery. Results: Overall, 181 eyes of 138 patients with cataracts were evaluated. In the diabetes group, the CECD loss rates were 5.1%, 3.9%, and 2.1% at 7 weeks, 19 weeks, and 1 year postoperatively, respectively. In the control group, the CECD loss rates were 2.8%, 2.6%, and 1.2% at 7 weeks, 19 weeks, and 1 year postoperatively, respectively. Significant differences in the percentage decrease in CECD were observed between the two groups at 7 and 19 weeks postoperatively. Significant differences in the CV and PHC were observed preoperatively and postoperatively between the diabetes and control groups (p < 0.01 or p = 0.01, 0.02). Significant differences were also observed between CV and PHC preoperatively, at 19 weeks, and 1 year postoperatively in the diabetes and control groups (p < 0.01). At 1 year postoperatively, IOP reduction rates were 8.0% and 11.2% in the diabetes and control groups, respectively. Conclusions: CECD loss was minimal with the eight-chop technique; however, the diabetes group showed a higher percentage decrease than the control group up to 19 weeks postoperatively. In addition, although IOP decreased in both groups after surgery, the percentage decrease was significantly different at 1 year postoperatively. This study suggests that the corneal endothelial cells of diabetic eyes may be more fragile than those of normal eyes and that the long-term postoperative IOP-lowering effect may be attenuated. These findings will contribute to advances in personalized treatment strategies for patients with diabetes.
Full article
(This article belongs to the Special Issue Current Trends in Cataract Surgery)
Open AccessArticle
Comparative Evaluation of Automatic Detection and Classification of Daily Living Activities Using Batch Learning and Stream Learning Algorithms
by
Paula Sofía Muñoz, Ana Sofía Orozco, Jaime Pabón, Daniel Gómez, Ricardo Salazar-Cabrera, Jesús D. Cerón, Diego M. López and Bernd Blobel
J. Pers. Med. 2025, 15(5), 208; https://doi.org/10.3390/jpm15050208 - 20 May 2025
Abstract
Background/Objectives: Activities of Daily Living (ADLs) are crucial for assessing an individual’s autonomy, encompassing tasks such as eating, dressing, and moving around, among others. Predicting these activities is part of health monitoring, elderly care, and intelligent systems, improving quality of life, and facilitating
[...] Read more.
Background/Objectives: Activities of Daily Living (ADLs) are crucial for assessing an individual’s autonomy, encompassing tasks such as eating, dressing, and moving around, among others. Predicting these activities is part of health monitoring, elderly care, and intelligent systems, improving quality of life, and facilitating early dependency detection, all of which are relevant components of personalized health and social care. However, the automatic classification of ADLs from sensor data remains challenging due to high variability in human behavior, sensor noise, and discrepancies in data acquisition protocols. These challenges limit the accuracy and applicability of existing solutions. This study details the modeling and evaluation of real-time ADL classification models based on batch learning (BL) and stream learning (SL) algorithms. Methods: The methodology followed is the Cross-Industry Standard Process for Data Mining (CRISP-DM). The models were trained with a comprehensive dataset integrating 23 ADL-centric datasets using accelerometers and gyroscopes data. The data were preprocessed by applying normalization and sampling rate unification techniques, and finally, relevant sensor locations on the body were selected. Results: After cleaning and debugging, a final dataset was generated, containing 238,990 samples, 56 activities, and 52 columns. The study compared models trained with BL and SL algorithms, evaluating their performance under various classification scenarios using accuracy, area under the curve (AUC), and F1-score metrics. Finally, a mobile application was developed to classify ADLs in real time (feeding data from a dataset). Conclusions: The outcome of this study can be used in various data science projects related to ADL and Human activity recognition (HAR), and due to the integration of diverse data sources, it is potentially useful to address bias and improve generalizability in Machine Learning models. The principal advantage of online learning algorithms is dynamically adapting to data changes, representing a significant advance in personal autonomy and health care monitoring.
Full article
(This article belongs to the Special Issue Selected Papers From the pHealth 2024 Conference, Rende, Italy, 27–29 May 2024)
►▼
Show Figures

Figure 1
Open AccessReview
Point of View: A Holistic Four-Interface Conceptual Model for Personalizing Shock Resuscitation
by
Philippe Rola, Eduardo Kattan, Matthew T. Siuba, Korbin Haycock, Sara Crager, Rory Spiegel, Max Hockstein, Vimal Bhardwaj, Ashley Miller, Jon-Emile Kenny, Gustavo A. Ospina-Tascón and Glenn Hernandez
J. Pers. Med. 2025, 15(5), 207; https://doi.org/10.3390/jpm15050207 - 20 May 2025
Abstract
The resuscitation of a patient in shock is a highly complex endeavor that should go beyond normalizing mean arterial pressure and protocolized fluid loading. We propose a holistic, four-interface conceptual model of shock that we believe can benefit both clinicians at the bedside
[...] Read more.
The resuscitation of a patient in shock is a highly complex endeavor that should go beyond normalizing mean arterial pressure and protocolized fluid loading. We propose a holistic, four-interface conceptual model of shock that we believe can benefit both clinicians at the bedside and researchers. The four circulatory interfaces whose uncoupling results in shock are as follows: the left ventricle to arterial, the arterial to capillary, the capillary to venular, and finally the right ventricle to pulmonary artery. We review the pathophysiology and clinical consequences behind the uncoupling of these interfaces, as well as how to assess them, and propose a strategy for approaching a patient in shock. Bedside assessment of shock may include these critical interfaces in order to avoid hemodynamic incoherence and to focus on microcirculatory restoration rather than simply mean arterial pressure. The purpose of this model is to serve as a mental model for learners as well as a framework for further resuscitation research that incorporates these concepts.
Full article
(This article belongs to the Special Issue Precision Medicine in Critical Care Medicine: Novel Challenges and Advances)
►▼
Show Figures

Graphical abstract
Open AccessArticle
Features of Heart Failure with Preserved Ejection Fraction in Patients with Chronic Obstructive Pulmonary Disease and Systemic Sclerosis-Associated Interstitial Lung Diseases
by
Lyazat Ibrayeva, Meruyert Aubakirova, Irina Bacheva, Assel Alina, Nazira Bazarova, Aizhan Zhanabayeva, Olga Avdiyenko, Seda Borchashvili, Saltanat Tazhikhanova and Askhat Murzabaeyev
J. Pers. Med. 2025, 15(5), 206; https://doi.org/10.3390/jpm15050206 - 20 May 2025
Abstract
Background/Objectives: This study aims to investigate the potential etiopathogenesis of HFpEF development and identify possible different phenotypes of HFpEF in patients with chronic obstructive pulmonary disease (COPD) and systemic sclerosis-associated interstitial lung diseases (SS-ILDs). It could help clinicians improve early HFpEF personalized
[...] Read more.
Background/Objectives: This study aims to investigate the potential etiopathogenesis of HFpEF development and identify possible different phenotypes of HFpEF in patients with chronic obstructive pulmonary disease (COPD) and systemic sclerosis-associated interstitial lung diseases (SS-ILDs). It could help clinicians improve early HFpEF personalized detection and management. Methods: This study included 150 patients with chronic lung diseases (CLDs), such as COPD and SS-ILD, who were outside of exacerbation, had no history of chronic heart failure (CHF), and had a left ventricular ejection fraction (LV EF) of ≥50%. The functional status of the lungs, heart, endothelial dysfunction, and acid–base balance was assessed. The results obtained were compared in groups of patients with CLD depending on the presence or absence of HF with preserved ejection fraction (HFpEF). The diagnosis of HFpEF was established based on the HFA-PEFF Score classification. Nonparametric statistical methods were used. Results: In patients with CLD, indicators such as age, longitudinal size of the right atrium, mid-regional pro-atrial natriuretic peptide (MR-proANP), and highly sensitive cardiac troponin T (hsTnT) were higher than in the group of patients without HFpEF. In patients with COPD and HFpEF, statistically significant changes were found in the volume of the left atrium. In patients with SS-ILD and HFpEF, statistically significant differenceswere found in SBP before and after the 6 min walk test (6MWT), the Borg scale before 6MWT, MR-proANP, and the longitudinal dimension of the right atrium. Conclusions: The results of our study allow us to identify two different mechanisms of HFpEF development: In patients with COPD, the predominant factor in the development of HFpEF was hypoxia, while in patients with SS-ILD, myocardial dysfunction with remodeling developed against the background of secondary pulmonary hypertension, highlighting the importance of phenotype-specific evaluation. These findings suggest potential approaches for personalized risk stratification and the development of targeted management strategies for patients with HFpEF.
Full article
(This article belongs to the Section Mechanisms of Diseases)
Open AccessOpinion
A Talk with ChatGPT: The Role of Artificial Intelligence in Shaping the Future of Cardiology and Electrophysiology
by
Angelica Cersosimo, Elio Zito, Nicola Pierucci, Andrea Matteucci and Vincenzo Mirco La Fazia
J. Pers. Med. 2025, 15(5), 205; https://doi.org/10.3390/jpm15050205 - 20 May 2025
Abstract
Background: Artificial intelligence (AI) is poised to significantly impact the future of cardiology and electrophysiology, offering new tools to interpret complex datasets, improve diagnosis, optimize clinical workflows, and personalize therapy. ChatGPT-4o, a leading AI-based language model, exemplifies the transformative potential of AI
[...] Read more.
Background: Artificial intelligence (AI) is poised to significantly impact the future of cardiology and electrophysiology, offering new tools to interpret complex datasets, improve diagnosis, optimize clinical workflows, and personalize therapy. ChatGPT-4o, a leading AI-based language model, exemplifies the transformative potential of AI in clinical research, medical education, and patient care. Aim and Methods: In this paper, we present an exploratory dialogue with ChatGPT to assess the role of AI in shaping the future of cardiology, with a particular focus on arrhythmia management and cardiac electrophysiology. Topics discussed include AI applications in ECG interpretation, arrhythmia detection, procedural guidance during ablation, and risk stratification for sudden cardiac death. We also examine the risks associated with AI use, including overreliance, interpretability challenges, data bias, and generalizability. Conclusions: The integration of AI into cardiovascular care offers the potential to enhance diagnostic accuracy, tailor interventions, and support decision-making. However, the adoption of AI must be carefully balanced with clinical expertise and ethical considerations. By fostering collaboration between clinicians and AI developers, it is possible to guide the development of reliable, transparent, and effective tools that will shape the future of personalized cardiology and electrophysiology.
Full article
(This article belongs to the Section Methodology, Drug and Device Discovery)
►▼
Show Figures

Graphical abstract
Open AccessArticle
High Ocular Disease Burden and Increased Referral Needs in Patients with Chronic Kidney Disease: A Step Toward Personalized Care
by
Yulia Liem, Pavitra Thyagarajan, Miao Li Chee, Cynthia Ciwei Lim, Boon Wee Teo and Charumathi Sabanayagam
J. Pers. Med. 2025, 15(5), 204; https://doi.org/10.3390/jpm15050204 - 19 May 2025
Abstract
Background/Objectives: To evaluate the prevalence of eye diseases in patients with confirmed chronic kidney disease (CKD) and their referral patterns to ophthalmologists, with the aim of informing personalized screening and referral strategies. Methods: This study involved 528 CKD patients from a tertiary hospital’s
[...] Read more.
Background/Objectives: To evaluate the prevalence of eye diseases in patients with confirmed chronic kidney disease (CKD) and their referral patterns to ophthalmologists, with the aim of informing personalized screening and referral strategies. Methods: This study involved 528 CKD patients from a tertiary hospital’s outpatient renal clinics in Singapore, with CKD defined as an estimated glomerular filtration rate (eGFR) < 60 mL/min/1.73 m2. Retinal photographs from each dilated eye were graded for the presence of diabetic retinopathy (DR) and other eye diseases by professional graders. Patients with significant eye conditions were referred to ophthalmologists based on severity and urgency, categorized as urgent (same day or within 24 h), semi-urgent (within 1–2 weeks), fast-track (within 1–3 months), or annual referrals. Results: More than half of the CKD patients (53.7%) had some form of eye disease; 20% were diagnosed with DR, and 29% required fast-track referrals. Of the 251 patients with diabetes, 67% adhered to annual follow-ups; however, despite this regular monitoring, over half required fast-track referrals for severe eye conditions. Among the 167 non-diabetic CKD patients, nearly a third (31%) were on follow-up, with 7.8% requiring fast-track referrals. Notably, 11% of those not on follow-up also needed fast-track referrals. Seven non-diabetic and ten diabetic patients required urgent referral due to critical conditions such as pseudo-holes, impending occlusions, and disc swelling. Conclusions: These findings underscore the high prevalence and severe nature of eye diseases in CKD patients, even those who are under regular annual follow-up. Integrating systematic eye screening into CKD care supports personalized medicine by enabling early detection and tailored interventions, ultimately improving both visual and overall patient outcomes.
Full article
(This article belongs to the Special Issue Clinical Advances in Diagnosis and Personalized Treatments of Chronic Kidney Diseases)
►▼
Show Figures

Figure 1
Open AccessReview
Data-Driven Defragmentation: Achieving Value-Based Sarcoma and Rare Cancer Care Through Integrated Care Pathway Mapping
by
Bruno Fuchs and Philip Heesen
J. Pers. Med. 2025, 15(5), 203; https://doi.org/10.3390/jpm15050203 - 19 May 2025
Abstract
Sarcomas, a rare and complex group of cancers, require multidisciplinary care across multiple healthcare settings, often leading to delays, redundant testing, and fragmented data. This fragmented care landscape obstructs the implementation of Value-Based Healthcare (VBHC), where care efficiency is tied to measurable patient
[...] Read more.
Sarcomas, a rare and complex group of cancers, require multidisciplinary care across multiple healthcare settings, often leading to delays, redundant testing, and fragmented data. This fragmented care landscape obstructs the implementation of Value-Based Healthcare (VBHC), where care efficiency is tied to measurable patient outcomes.ShapeHub, an interoperable digital platform, aims to streamline sarcoma care by centralizing patient data across providers, akin to a logistics system tracking an item through each stage of delivery. ShapeHub integrates diagnostics, treatment records, and specialist consultations into a unified dataset accessible to all care providers, enabling timely decision-making and reducing diagnostic delays. In a case study within the Swiss Sarcoma Network, ShapeHub has shown substantial impact, improving diagnostic pathways, reducing unplanned surgeries, and optimizing radiotherapy protocols. Through AI-driven natural language processing, Fast Healthcare Interoperability Resources, and Health Information Exchanges, HIEs, the platform transforms unstructured records into real-time, actionable insights, enhancing multidisciplinary collaboration and clinical outcomes. By identifying redundancies, ShapeHub also contributes to cost efficiency, benchmarking treatment costs across institutions and optimizing care pathways. This data-driven approach creates a foundation for precision medicine applications, including digital twin technology, to predict treatment responses and personalize care plans. ShapeHub offers a scalable model for managing rare cancers and complex diseases, harmonizing care pathways, improving precision oncology, and transforming VBHC into a reality. This article outlines the potential of ShapeHub to overcome fragmented data barriers and improve patient-centered care.
Full article
(This article belongs to the Section Methodology, Drug and Device Discovery)
►▼
Show Figures

Figure 1
Open AccessArticle
Clinical Outcomes in the Treatment of Pertrochanteric Femur Fractures: A Retrospective Cohort Study
by
Cesare Donadono, Domenico Tigani, Andrea Assenza, Davide Censoni, Francesco Pesce and Giuseppe Melucci
J. Pers. Med. 2025, 15(5), 202; https://doi.org/10.3390/jpm15050202 - 19 May 2025
Abstract
Background: Pertrochanteric fractures of the proximal femur present a common challenge for traumatologists, with intramedullary nailing emerging as the preferred treatment. Complication rates are around 20%, including screw jamming, refractures, implant breakage, or medial migration, with cut-out being the most common. A tip–apex
[...] Read more.
Background: Pertrochanteric fractures of the proximal femur present a common challenge for traumatologists, with intramedullary nailing emerging as the preferred treatment. Complication rates are around 20%, including screw jamming, refractures, implant breakage, or medial migration, with cut-out being the most common. A tip–apex distance (TAD) of >25 mm and incorrect cephalic screw position are predictive factors for cut-out. This study assesses outcomes using the Elos intramedullary nail, based on the experience of the Department of Orthopedics and Traumatology at Ospedale Maggiore in Bologna. Methods: We conducted a retrospective cohort study of 344 patients treated with the Elos intramedullary nail for pertrochanteric femoral fractures from 1 January 2017 to 31 December 2022. The Elos®-Intrauma nail was implanted using the standard technique. Initial X-rays classified fractures according to the AO-OTA classification, and postoperative X-rays confirmed the cephalic screw’s placement per Cleveland’s regions. Patients were divided into two groups: optimal cephalic screw position (positions 5-8-9) and other positions. We evaluated TAD, calcar-referred TAD (CalTAD), and postoperative reduction quality using Chang’s criteria. The incidence of cut-out and other complications were assessed in connection with these measurements. Results: Among the 344 patients, 227 (65.9%) had the screw in positions 5-8-9, while 117 (34.1%) had it in other positions. The median TAD was 19.47 ± 6.26 mm (range 3.96–46.6), with TAD ≤ 25 mm in 265 patients (77%). The median CalTAD was 22.37 ± 5.65 mm (range 8.75–45.3), with CalTAD ≤ 25 mm in 231 patients (67.1%). According to Chang’s criteria, 8 cases (2.3%) had poor reduction, 139 cases (40.4%) had acceptable reduction, and 197 cases (57.3%) had excellent reduction. Cut-out occurred in four cases (1.19%). Multivariate analysis revealed only poor reduction and TAD > 25 mm as independent predictors of cut-out (p < 0.05), while cephalic screw position, CalTAD, and fracture type did not impact cut-out incidence. Conclusions: This study indicates that optimal TAD and quality of reduction are crucial for minimizing cut-out risks. The Elos intramedullary nail shows favorable outcomes with a low cut-out incidence when these parameters are met. Emphasis should be placed on achieving a TAD ≤ 25 mm and excellent reduction quality to reduce complications.
Full article
(This article belongs to the Special Issue Orthopedic Trauma: New Perspectives and Innovative Techniques)
►▼
Show Figures

Figure 1
Open AccessArticle
Trans-Oral Robotic Surgery (TORS) and Postoperative Hemorrhage: An Analysis of Risk Factors
by
Andrea Migliorelli, Elia Biancoli, Marianna Manuelli, Alberto Caranti, Andrea Ciorba, Chiara Bianchini, Giuseppe Meccariello and Claudio Vicini
J. Pers. Med. 2025, 15(5), 201; https://doi.org/10.3390/jpm15050201 - 16 May 2025
Abstract
Background/Objectives: Postoperative hemorrhage is the most common complication after Trans-Oral Robotic Surgery (TORS) described in the literature. The aim of this study is to assess the presence of any risk factors that may impact postoperative bleeding. Methods: This was a retrospective study
[...] Read more.
Background/Objectives: Postoperative hemorrhage is the most common complication after Trans-Oral Robotic Surgery (TORS) described in the literature. The aim of this study is to assess the presence of any risk factors that may impact postoperative bleeding. Methods: This was a retrospective study based on the analysis of patient data. Patients undergoing TORS procedures at the ENT Unit of Forlì Hospital from 2008 to 2022 for OSA (obstructive sleep apnea) or oncological disease and with a minimum follow-up of 30 days were included. The comorbidities analyzed were perioperative anticoagulant/antiplatelet therapy and clinicopathological features concerning the pathology. Total bleeding and severe bleeding (which required management in the operating room) were included. Results: A total of 414 patients (106 oncological TORS and 308 OSA TORS patients) were included. Post-TORS bleeding occurred in 47 cases (11.3%) and severe bleeding in 18 cases (4.3%). The pathology (oncology vs. OSA) treated with TORS did not represent a risk factor (p = 0.466). Antiplatelet intake represented an important risk factor (p = 0.002). Postoperative hemorrhage for oncological TORS occurred in 11.3% patients; of these, 6.6% had severe bleeding. Artery ligation during neck dissection prevented the risk of severe bleeding (p < 0.001). In TORS for OSA, postoperative hemorrhage was found in 11.4% cases, of which 3.6% were major bleeding. Neither the degree of OSA nor the association with other concurrent procedures were risk factors for postoperative bleeding in this study. Conclusions: Patients taking perioperative antiplatelet therapy have an almost 5-fold increased risk of developing postoperative bleeding. The pathology (oncology vs. OSA) does not influence the risk of bleeding. Prophylactic arterial ligation during neck dissection significantly decreases the risk of severe bleeding.
Full article
(This article belongs to the Section Clinical Medicine, Cell, and Organism Physiology)
Open AccessArticle
From Preliminary Urinalysis to Decision Support: Machine Learning for UTI Prediction in Real-World Laboratory Data
by
Athanasia Sergounioti, Dimitrios Rigas, Vassilios Zoitopoulos and Dimitrios Kalles
J. Pers. Med. 2025, 15(5), 200; https://doi.org/10.3390/jpm15050200 - 16 May 2025
Abstract
Background/Objectives: Urinary tract infections (UTIs) are frequently diagnosed empirically, often leading to overtreatment and rising antimicrobial resistance. This study aimed to develop and evaluate machine learning (ML) models that predict urine culture outcomes using routine urinalysis and demographic data, supporting more targeted
[...] Read more.
Background/Objectives: Urinary tract infections (UTIs) are frequently diagnosed empirically, often leading to overtreatment and rising antimicrobial resistance. This study aimed to develop and evaluate machine learning (ML) models that predict urine culture outcomes using routine urinalysis and demographic data, supporting more targeted empirical antibiotic use. Methods: A real-world dataset comprising 8065 urinalysis records from a hospital laboratory was used to train five ensemble ML models, including random forest, XGBoost (eXtreme gradient boosting), extra trees, voting classifier, and stacking classifier. Models were developed using 10-fold stratified cross-validation and assessed via clinically relevant metrics including specificity, sensitivity, likelihood ratios, and diagnostic odds ratios (DORs). To enhance screening utility, threshold optimization was applied to the best-performing model (XGBoost) using the Youden index. Results: XGBoost and random forest demonstrated the most balanced diagnostic profiles (AUROC: 0.819 and 0.791, respectively), with DORs exceeding 21. The voting and stacking classifiers achieved the highest specificity (>95%) and positive likelihood ratios (>10) but exhibited lower sensitivity. Feature importance analysis identified positive nitrites, white blood cell count, and specific gravity as key predictors. Threshold tuning of XGBoost improved sensitivity from 70.2% to 87.9% and reduced false negatives by 82%, with an associated NPV of 96.4%. The adjusted model reduced overtreatment by 56% compared to empirical prescribing. Conclusions: ML models based on structured urinalysis and demographic data can support clinical decision-making for UTIs. While high-specificity models may reduce unnecessary antibiotic use, sensitivity trade-offs must be considered. Threshold-optimized XGBoost offers a clinically adaptable tool for empirical treatment decisions by improving sensitivity and reducing overtreatment, thus supporting the more personalized and judicious use of antibiotics.
Full article
(This article belongs to the Special Issue Advances in the Use of Machine Learning for Personalized Medicine)
►▼
Show Figures

Figure 1
Open AccessArticle
Clinicopathological Features of Non-Small Cell Lung Carcinoma with NRAS Mutation
by
Andrea Ambrosini-Spaltro, Claudia Rengucci, Laura Capelli, Elisa Chiadini, Chiara Bennati, Angelo Delmonte, Silvia Vecchiarelli, Francesco Limarzi, Sofia Nosseir, Graziana Gallo, Mirca Valli, Paola Ulivi and Daniele Calistri
J. Pers. Med. 2025, 15(5), 199; https://doi.org/10.3390/jpm15050199 - 16 May 2025
Abstract
(1) Background: NRAS mutations affect fewer than 1% of lung adenocarcinomas. The aim of this study was to describe the clinicopathological features of lung carcinomas with NRAS mutations. (2) Methods: A series of NRAS-mutated lung carcinomas was collected from a molecular
[...] Read more.
(1) Background: NRAS mutations affect fewer than 1% of lung adenocarcinomas. The aim of this study was to describe the clinicopathological features of lung carcinomas with NRAS mutations. (2) Methods: A series of NRAS-mutated lung carcinomas was collected from a molecular diagnostic unit (from four hospitals). The cases were analyzed with next-generation sequencing. A log-rank test for overall survival (OS) was calculated. (3) Results: NRAS mutations were detected in 14/1948 samples (0.72%) of non-small-cell lung carcinomas from 13 patients (8 males, 5 females). NRAS mutations involved codon 61 in the majority (9/13, 69.2%) of cases. The other NRAS mutations affected codon 12 (2/13, 15.4%), codon 13 (1/13, 7.7%), and codon 142 (1/13, 7.7%). In 7/13 cases, co-alterations in additional genes were also present. Pleomorphic/sarcomatoid features were identified in 3/13 (23.1%) cases, in 2/8 (25.0%) histological specimens, and in 2/5 (40.0%) surgical specimens, respectively. Follow-up data were available in 11/13 cases, with 6 patients deceased. By a log-rank test, patients with NRAS mutations in codon 61 had a better outcome (estimated mean of 32.6 ± 7.1 months) compared to those with other NRAS mutations (estimated mean of 8.7 ± 4.4 months), with a significant difference (p = 0.048 for OS). (4) Conclusions: Lung carcinomas with NRAS mutation may display pleomorphic or sarcomatoid features. Mutations in codon 61 showed a more favorable prognosis than those in other codons.
Full article
(This article belongs to the Special Issue Pathology and Molecular Diagnostics in the Personalized Treatment of Lung Diseases)
►▼
Show Figures

Graphical abstract
Open AccessArticle
Shoulder Tendinopathy Induced by Statins: A Case Report and Systematic Review
by
Nicola Manocchio, Carmelo Pirri, Andrea Sorbino, Laura Giordani, Giulia Vita, Concetta Ljoka and Calogero Foti
J. Pers. Med. 2025, 15(5), 198; https://doi.org/10.3390/jpm15050198 - 15 May 2025
Abstract
Background: Statins are essential for managing cholesterol levels but can induce musculoskeletal side effects, including tendinopathy of the shoulder. Rotator Cuff Disease (RCD) is one of the most common shoulder tendinopathy. The aim of the present study is to report a clinical case
[...] Read more.
Background: Statins are essential for managing cholesterol levels but can induce musculoskeletal side effects, including tendinopathy of the shoulder. Rotator Cuff Disease (RCD) is one of the most common shoulder tendinopathy. The aim of the present study is to report a clinical case of statin-induce RCD after performing a systematic review on the subject. Materials and Methods: We performed a systematic review of the literature and report the case of a 49-year-old man with statin-induced RCD treated with a personalized individual rehabilitation project (IRP) (steroid and HA injections, mesotherapy, and therapeutic exercise) to investigate the relationship between statins and shoulder tendinopathy. The review followed PRISMA guidelines (2020 version), searching PubMed, Web of Science, and SCOPUS. Results: Out of a total of 217 articles, three cohort studies were suitable for our review. Conflicting evidence emerged regarding the association between statins and shoulder tendinopathy from the included papers. The case report describes a patient who experienced RCD after increasing atorvastatin dosage, with symptoms improving after dose reduction and a multimodal personalized IRP. Conclusions: Statins may contribute to tendon injury by altering the extracellular matrix and cell membrane integrity. While tendinopathy and statin relation is still under discussion, clinicians should monitor patients for tendinopathy and consider switching to alternative treatments in case symptoms arise. The case report demonstrated the successful management of statin-induced RCD with a multimodal personalized IRP. Further research is needed to clarify the relationship between statins and shoulder tendinopathy. Early diagnosis and appropriate personalized management are crucial for optimizing patient outcomes.
Full article
(This article belongs to the Section Personalized Therapy and Drug Delivery)
►▼
Show Figures

Figure 1
Open AccessSystematic Review
One-Stop Mitral Valve Transcatheter Edge-to-Edge Repair and Left Atrial Appendage Occlusion in Patients with Atrial Fibrillation and Mitral Regurgitation: A Systematic Review and Meta-Analysis
by
Konstantinos Pamporis, Dimitrios Tsiachris, Konstantinos Grigoriou, Paschalis Karakasis, Ioannis Doundoulakis, Panagiotis Theofilis, Panagiotis Kouvatsos, Athanasios Saplaouras, Athanasios Kordalis, Aikaterini-Eleftheria Karanikola, Panagiotis Antonios Goutis and Konstantinos Tsioufis
J. Pers. Med. 2025, 15(5), 197; https://doi.org/10.3390/jpm15050197 - 14 May 2025
Abstract
Background/Objectives: Patients with atrial fibrillation and mitral regurgitation (MR) undergoing transcatheter edge-to-edge mitral valve repair (M-TEER) often have concomitant indications for left atrial appendage occlusion (LAAO), mandating a more personalized treatment approach. This study aimed to examine the effectiveness and safety of
[...] Read more.
Background/Objectives: Patients with atrial fibrillation and mitral regurgitation (MR) undergoing transcatheter edge-to-edge mitral valve repair (M-TEER) often have concomitant indications for left atrial appendage occlusion (LAAO), mandating a more personalized treatment approach. This study aimed to examine the effectiveness and safety of combining M-TEER/LAAO in one procedure. Methods: MEDLINE (PubMed), Scopus, and Cochrane were searched through 21 March 2025 for studies examining M-TEER/LAAO with or without control (M-TEER only). Double-independent study selection, extraction, and quality assessments were performed. Frequentist random-effects models were used to calculate mean differences (MDs) and risk ratios (RRs) with 95% confidence intervals (CIs). Results: Seven studies (223 participants) were included. For M-TEER/LAAO, the mean procedural time was 101.6 min (95% CI = [85.06, 118.13]), the mean radiation time was 29.97 min (95% CI = [23.85, 36.09]), the mean length of stay was 5.21 days (95% CI = [3.31, 7.12]), procedural success was achieved in 89.5% of cases (95% CI = [73.4, 96.3], and post-procedure MR > 2+ occurred in 14.8% of cases (95% CI = [3.6, 44.5]). Compared to M-TEER only, patients with M-TEER/LAAO had similar procedural (RR = 0.91, 95% CI = [0.71, 1.17]) and technical success (RR = 1, 95% CI = [0.94, 1.06]) with a similar risk of acute kidney injury (RR = 1, 95% CI = [0.07, 15.12]), bleeding (RR = 0.40, 95% CI = [0.01, 18.06]), and all-cause death (RR = 0.59, 95% CI = [0.22, 1.54]). M-TEER/LAAO was non-significantly associated with in-hospital death (RR = 3, 95% CI = [0.13, 70.23]), stroke (RR = 3, 95% CI = [0.13, 70.23]), and vascular complications (RR = 1.55, 95% CI = [0.43, 5.59]) compared to M-TEER only. Most patients (34.2%, 95% CI = [2.8, 90.4]) received dual antiplatelet therapy at discharge, followed by anticoagulation only (20.2%, 95% CI = [7.5, 44.3]). Conclusions: M-TEER/LAAO can be combined into a single procedure with good peri-procedural outcomes. Safety was also satisfactory; however, some concerns may arise regarding in-hospital death, stroke, and vascular complications. Further research is needed to explore the effectiveness and safety of this combined strategy and elucidate the risk–benefit profile of this personalized treatment approach.
Full article
(This article belongs to the Special Issue Cardiology and Vascular Health: Pathophysiology, Therapeutics and Epidemiology)
►▼
Show Figures

Figure 1
Open AccessArticle
Yeast-Produced Human Recombinant Lysosomal β-Hexosaminidase Efficiently Rescues GM2 Ganglioside Accumulation in Tay–Sachs Disease
by
Orhan Kerim Inci, Andrés Felipe Leal, Nurselin Ates, Diego A. Súarez, Angela Johana Espejo-Mojica, Carlos Javier Alméciga-Diaz and Volkan Seyrantepe
J. Pers. Med. 2025, 15(5), 196; https://doi.org/10.3390/jpm15050196 - 10 May 2025
Abstract
Background: Tay–Sachs disease (TSD) is an autosomal recessive lysosomal storage disorder characterized by the accumulation of GM2 ganglioside due to mutations in the HEXA gene, which encodes the α-subunit of β-Hexosaminidase A. This accumulation leads to significant neuropathological effects and premature death in
[...] Read more.
Background: Tay–Sachs disease (TSD) is an autosomal recessive lysosomal storage disorder characterized by the accumulation of GM2 ganglioside due to mutations in the HEXA gene, which encodes the α-subunit of β-Hexosaminidase A. This accumulation leads to significant neuropathological effects and premature death in affected individuals. No effective treatments exist, but enzyme replacement therapies are under investigation. In our previous work, we demonstrated the internalization and efficacy of human recombinant lysosomal β-hexosaminidase A (rhHex-A), produced in the methylotrophic yeast Pichia pastoris, in reducing lipids and lysosomal mass levels in fibroblasts and neural stem cells derived from patient-induced pluripotent stem cells (iPSCs). In this study, we further evaluated the potential of rhHex-A to prevent GM2 accumulation using fibroblast and neuroglia cells from a TSD patient alongside a relevant mouse model. Methods: Fibroblasts and neuroglial cell lines derived from a murine model and TSD patients were treated with 100 nM rhHexA for 72 h. After treatment, cells were stained by anti-GM2 (targeting GM2 ganglioside; KM966) and anti-LAMP1 (lysosomal-associated membrane protein 1) colocalization staining and incubated with 50 nM LysoTracker Red DND-99 to label lysosomes. In addition, GM2AP and HEXB expression were analyzed to assess whether rhHex-A treatment affected the levels of enzymes involved in GM2 ganglioside degradation. Results: Immunofluorescence staining for LysoTracker and colocalization studies of GM2 and Lamp1 indicated reduced lysosomal mass and GM2 levels. Notably, rhHex-A treatment also affected the expression of the HEXB gene, which is involved in GM2 ganglioside metabolism, highlighting a potential regulatory interaction within the metabolic pathway. Conclusions: Here, we report that rhHex-A produced in yeast can efficiently degrade GM2 ganglioside and rescue lysosomal accumulation in TSD cells.
Full article
(This article belongs to the Special Issue Inborn Errors of Metabolism: From Pathomechanisms to Treatment)
►▼
Show Figures

Figure 1
Open AccessSystematic Review
Methodologies for the Emulation of Biomarker-Guided Trials Using Observational Data: A Systematic Review
by
Faye D. Baldwin, Rukun K. S. Khalaf, Ruwanthi Kolamunnage-Dona and Andrea L. Jorgensen
J. Pers. Med. 2025, 15(5), 195; https://doi.org/10.3390/jpm15050195 - 10 May 2025
Abstract
Background: Target trial emulation involves the application of design principles from randomised controlled trials (RCTs) to observational data, and is particularly useful in situations where an RCT would be unfeasible. Biomarker-guided trials, which incorporate biomarkers within their design to either guide treatment
[...] Read more.
Background: Target trial emulation involves the application of design principles from randomised controlled trials (RCTs) to observational data, and is particularly useful in situations where an RCT would be unfeasible. Biomarker-guided trials, which incorporate biomarkers within their design to either guide treatment and/or determine eligibility, are often unfeasible in practice due to sample size requirements or ethical concerns. Here, we undertake a systematic review of methodologies used in target trial emulations, comparing treatment effectiveness, critically appraising them, and considering their applicability to the emulation of biomarker-guided trials. Methods: A comprehensive search strategy was developed to identify studies reporting on methods for target trial emulation comparing the effectiveness of treatments using observational data, and applied to the following bibliographic databases: PubMed, Scopus, Web of Science, and Ovid MEDLINE. A narrative description of methods identified in the review was undertaken alongside a critique of their relative strengths and limitations. Results: We identified a total of 59 papers: 47 emulating a target trial (‘application’ studies), and 12 detailing methods to emulate a target trial (‘methods’ studies). A total of 25 papers were identified as emulating a biomarker-guided trial (42%). While all papers reported methods to adjust for baseline confounding, 40% of application papers did not specify methods to adjust for time-varying confounding. Conclusions: This systematic review has identified a range of methods used to control for baseline, time-varying, and residual/unmeasured confounding within target trial emulation and provides a guide for researchers interested in emulation of biomarker-guided trials.
Full article
(This article belongs to the Section Disease Biomarker)
►▼
Show Figures

Figure 1
Open AccessArticle
The Accuracy of ChatGPT-4o in Interpreting Chest and Abdominal X-Ray Images
by
Pietro G. Lacaita, Malik Galijasevic, Michael Swoboda, Leonhard Gruber, Yannick Scharll, Fabian Barbieri, Gerlig Widmann and Gudrun M. Feuchtner
J. Pers. Med. 2025, 15(5), 194; https://doi.org/10.3390/jpm15050194 - 10 May 2025
Abstract
Background/Objectives: Large language models (LLMs), such as ChatGPT, have emerged as potential clinical support tools to enhance precision in personalized patient care, but their reliability in radiological image interpretation remains uncertain. The primary aim of our study was to evaluate the diagnostic accuracy
[...] Read more.
Background/Objectives: Large language models (LLMs), such as ChatGPT, have emerged as potential clinical support tools to enhance precision in personalized patient care, but their reliability in radiological image interpretation remains uncertain. The primary aim of our study was to evaluate the diagnostic accuracy of ChatGPT-4o in interpreting chest X-rays (CXRs) and abdominal X-rays (AXRs) by comparing its performance to expert radiology findings, whilst secondary aims were diagnostic confidence and patient safety. Methods: A total of 500 X-rays, including 257 CXR (51.4%) and 243 AXR (48.5%), were analyzed. Diagnoses made by ChatGPT-4o were compared to expert interpretations. Confidence scores (1–4) were assigned and responses were evaluated for patient safety. Results: ChatGPT-4o correctly identified 345 of 500 (69%) pathologies (95% CI: 64.81–72.9). For AXRs 175 of 243 (72.02%) pathologies were correctly diagnosed (95% CI: 66.06–77.28), while for CXRs 170 of 257 (66.15%) were accurate (95% CI: 60.16–71.66). The highest detection rates among CXRs were observed for pulmonary edema, tumor, pneumonia, pleural effusion, cardiomegaly, and emphysema, and lower rates were observed for pneumothorax, rib fractures, and enlarged mediastinum. AXR performance was highest for intestinal obstruction and foreign bodies, and weaker for pneumoperitoneum, renal calculi, and diverticulitis. Confidence scores were higher for AXRs (mean 3.45 ± 1.1) than CXRs (mean 2.48 ± 1.45). All responses (100%) were considered to be safe for the patient. Interobserver agreement was high (kappa = 0.920), and reliability (second prompt) was moderate (kappa = 0.750). Conclusions: ChatGPT-4o demonstrated moderate accuracy for the interpretation of X-rays, being higher for AXRs compared to CXRs. Improvements are required for its use as efficient clinical support tool.
Full article
(This article belongs to the Section Methodology, Drug and Device Discovery)
►▼
Show Figures

Figure 1

Journal Menu
► ▼ Journal Menu-
- JPM Home
- Aims & Scope
- Editorial Board
- Reviewer Board
- Topical Advisory Panel
- Instructions for Authors
- Special Issues
- Topics
- Sections & Collections
- Article Processing Charge
- Indexing & Archiving
- Editor’s Choice Articles
- Most Cited & Viewed
- Journal Statistics
- Journal History
- Journal Awards
- Society Collaborations
- Conferences
- Editorial Office
Journal Browser
► ▼ Journal BrowserHighly Accessed Articles
Latest Books
E-Mail Alert
News
Topics
Topic in
Diagnostics, JCTO, JCM, JPM, Tomography
Optical Coherence Tomography (OCT) and OCT Angiography – Recent Advances
Topic Editors: Sumit Randhir Singh, Jay ChhablaniDeadline: 26 May 2025
Topic in
JCM, JPM, JVD, Diagnostics, Cancers
Diagnosis, Management, and Prognostic Assessment of Chronic Disease
Topic Editors: Xiude Fan, Enfa Zhao, Yang Xia, Shanshan Shao, Tatsunori Miyata, Dongxing XieDeadline: 5 July 2025
Topic in
JCM, Diagnostics, JPM, Brain Sciences, JVD
Diagnosis and Management of Acute Ischemic Stroke
Topic Editors: Hyo Suk Nam, Byung Moon Kim, Tae-jin Song, Minho HanDeadline: 20 September 2025
Topic in
Antibiotics, JPM, Pharmaceuticals, Pharmaceutics, Medicines
Pharmacokinetic and Pharmacodynamic Modelling in Drug Discovery and Development
Topic Editors: Inaki F. Troconiz, Victor Mangas Sanjuán, Maria Garcia-Cremades MiraDeadline: 31 October 2025

Conferences
Special Issues
Special Issue in
JPM
Sex and Gender-Related Issues in the Era of Personalized Medicine
Guest Editors: Davide Bizzoca, Anna Maria Moretti, Biagio MorettiDeadline: 22 May 2025
Special Issue in
JPM
Innovations in Personalized Diagnosis and Treatment for Cystic Fibrosis
Guest Editor: Martina GentzschDeadline: 22 May 2025
Special Issue in
JPM
Emergency Medicine: Clinical Advances and Challenges in Diagnosis and Treatment, 2nd Edition
Guest Editor: Ovidiu Alexandru MederleDeadline: 25 May 2025
Special Issue in
JPM
Clinical Advances in Dermatology: Pathophysiology, Diagnosis and Treatment
Guest Editors: Ricardo Ruíz-Villaverde, Manuel Galán-GutiérrezDeadline: 25 May 2025