Search Results (81)

Previous studies have noted associations between age and healthcare costs in non-small-cell lung cancer (NSCLC). However, the drivers of cost disparities have not yet been fully examined. This retrospective cohort study included deceased patients diagnosed with stage IV NSCLC in Ontario from 1 April 2008 to 30 March 2014. Variables of interest were extracted from the Institute for Clinical Evaluative Sciences. Average monthly cancer-attributable costs (CACs), defined as the net additional costs due to cancer, determined by subtracting pre-diagnosis costs from post-diagnosis costs, were calculated by phases of care (staging, initial, continuing, and end-of-life). Regression analyses assessed predictors of cost variability. The median age of the 14,655 patients was 65 to 69 years; 54% were male and 29% had received chemotherapy. On both univariate and multivariate analysis, CACs decreased with age after cancer diagnosis across all phases of care (p < 0.001). Receiving chemotherapy contributed to higher costs in staging, initial, and continuing phases (OR 2.11, 95% C.I. 1.90–2.33, p < 0.01), and lower costs in the end-of-life phase (OR 0.77, 95% C.I. 0.72–0.81, p < 0.01). Our study showed that older patients had higher baseline healthcare costs and lower cancer-attributable costs following diagnosis of advanced NSCLC. Cost drivers, including treatment and gender, varied by phase of care. Full article

This research develops large language models (LLMs) to alleviate the workload of healthcare professionals by classifying medical records into their departments. The models utilize medical records as a dataset for fine-tuning and use clinical knowledge bases to enhance accuracy and efficiency in identifying appropriate departments. This study explores the integration of advanced large language models (LLMs) with quantized low-rank adaptation (QLoRA) for efficient training. The medical department classifier demonstrated impressive performance in diagnosing medical conditions, with an accuracy of 96.26. The findings suggest that LLM-based solutions could significantly improve the efficiency of clinical consultations. What is more, the trained models are hosted on GitHub and are publicly available for use, empowering the wider community to benefit from this research. Full article

Background/Objectives: Parkinson’s disease (PD) is a neurodegenerative disorder with a prolonged prodromal phase and progressive symptom burden. Traditional monitoring relies on clinical visits post-diagnosis, limiting the ability to capture early symptoms and real-world disease progression outside structured assessments. Social media provides an alternative source of longitudinal, patient-driven data, offering an opportunity to analyze both pre-diagnostic experiences and later disease manifestations. This study evaluates the feasibility of using Facebook to analyze PD-related discourse and disease timelines. Methods: Participants (N = 60) diagnosed with PD, essential tremor, or atypical parkinsonism, along with caregivers, were recruited. Demographic and clinical data were collected during structured interviews. Participants with Facebook accounts shared their account data. PD-related posts were identified using a Naïve Bayes classifier (recall: 0.86, 95% CI: 0.84–0.88, AUC = 0.94) trained on a ground-truth dataset of 6750 manually labeled posts. Results: Among participants with PD (PwPD), Facebook users were significantly younger but had similar Movement Disorder Society-United Parkinson’s Disease Rating Scale scores and disease duration compared to non-users. Among Facebook users with PD, 90% had accounts before diagnosis, enabling retrospective analysis of pre-diagnostic content. PwPD maintained 14 ± 3 years of Facebook history, including 5 ± 6 years pre-diagnosis. On average, 3.6% of all posts shared by PwPD were PD-related, and 1.7% of all posts shared before diagnosis were PD-related. Overall, 69% explicitly referenced PD, and 93% posted about PD-related themes. Conclusions: Facebook is a viable platform for studying PD progression, capturing both early content from the premorbid period and later-stage symptoms. These findings support its potential for disease monitoring at scale. Full article

Proton exchange membrane fuel cell (PEMFC) fault diagnosis faces two critical limitations: conventional offline methods lack real-time predictive capability, while existing prediction approaches are confined to single fault types. To address these gaps, this study proposes an online multi-fault prediction framework integrating three novel contributions: (1) a sensor fusion strategy leveraging existing thermal/electrochemical measurements (voltage, current, temperature, humidity, and pressure) without requiring embedded stack sensors; (2) a real-time sliding window mechanism enabling dynamic prediction updates every 1 s under variable load conditions; and (3) a modified CNN-based Bi-LSTM parallel model with attention mechanism (ConvBLSTM-PMwA) architecture featuring multi-input multi-output (MIMO) capability for simultaneous flooding/air-starvation detection. Through comparative analysis of different neural architectures using experimental datasets, the optimized ConvBLSTM-PMwA achieved 96.49% accuracy in predicting dual faults 64.63 s pre-occurrence, outperforming conventional LSTM models in both temporal resolution and long-term forecast reliability. Full article

Background: Ambient air pollution is a modifiable determinant of lung cancer survival, affecting early-stage Non-Small Cell Lung Cancer (NSCLC) incidence and mortality. Methods: This retrospective cohort study examined the association between all-cause mortality and exposure to air pollution among stage 1A NSCLC-treated patients from the U.S. National Cancer Registry from 1988 to 2015. The Cox hazard model and Kaplan–Meier survival plots were provided. Air pollutants were included separately and together in the models, accounting for spatiotemporal weather variability affecting air pollution exposure levels pre and post lung cancer diagnosis. Results: NO₂ (above the median sample mean = 25.66 ppb; 12.97 ppb below median), SO₂ (above median sample mean = 3.98 ppb; 1.81 ppb below median), and CO (above median sample mean = 1010.84 ppb; 447.91 ppb below median) air pollutant levels and weather conditions were calculated for county-day units. The median months of survival for those exposed to above-median NO₂ were 27 months (SD = 17.61 months), while the median was 30 months (SD = 15.93 months) for those exposed to below-median levels. Multipollutant analyses indicated that an average monthly NO₂ increase of 1 part per billion (ppb) in the county of NSCLC diagnosis was associated with increases of 4%, 6%, and 9% in the all-cause mortality rate one, three, and five years after diagnosis, respectively; an equivalent increase in SO₂ was associated with increases of 16%, 17%, and 17%; and an increase in CO was associated with increases of 53%, 51%, and 42% Conclusion: It is vital to implement environmental policies that control emissions to reduce preventable deaths in stage 1A NSCLC patients with adenocarcinoma or squamous cell carcinoma histology types who reside in metropolitan areas. Full article

Background/Objectives: Delayed diagnosis in psoriatic arthritis (PsA) is associated with significant health consequences. We hypothesize that musculoskeletal (MSK) surgery rates may be higher during the diagnostic delay period. This study aimed to compare the frequency of MSK surgeries in PsA patients during the period of diagnostic delay with the frequency of MSK surgeries post-diagnosis. Methods: This retrospective cohort study included PsA patients who fulfilled CASPAR criteria and were followed up on in our outpatient clinic. The pre-diagnosis symptomatic period was considered as the period of diagnostic delay. Data on MSK surgeries were obtained from patient records. The annual number of surgeries was calculated separately for the diagnostic delay and post-diagnosis periods. Results: The study included 84 PsA patients. The mean diagnostic delay in PsA patients was 7.49 years. During this period, 27.4% of patients underwent at least one MSK surgery. The mean annual number of MSK surgeries was significantly higher during the diagnostic delay period compared to the post-diagnosis period (Z = −3.18, p = 0.001, r = 0.35). Conclusions: Following PsA diagnosis, a reduction in MSK surgery rates was observed compared to during the diagnostic delay period. This suggests that inflammatory symptoms in PsA patients, which could have been managed with medical therapy, may have led to avoidable MSK surgeries. These findings highlight the potential for early diagnosis to reduce the rate of musculoskeletal surgery and associated healthcare costs. Full article

Objectives: There is strong evidence that not enough physical activity is among the most critical risk factors for cancer disease and premature mortality. The literature on the benefits of regular physical activity regarding cancer disease has grown in the last decades. This review aimed to present the current findings on the effect of prediagnosis physical activity on cancer incidence and mortality published between January 2019 and October 2024; this study summarizes the previous evidence, as well as the literature underlying biological mechanisms operating in the exercise–cancer relationship. The review also highlights gaps in the existing research and identifies future research directions. Methods: Medline/PubMed, ScienceDirect, and Google Scholar were searched with the search terms “physical activity” and “physical exercise” in conjunction with the MeSH terms for “cancer” and “carcinoma”. Primary, review, and meta-analysis studies published in English were included if they reported a measure of the effect size of prediagnosis physical activity on cancer incidence and/or cancer mortality. Results: Evidence from 37 observational studies and 10 reviews were included in this systematic review; 22 studies reported the effect of physical activity on cancer incidence, and 15 studies on cancer mortality. Of the 37 included observational studies, 19 confirmed the previous evidence that physical activity significantly decreased all-cancer-combined and cancer-specific site incidences, and 10 studies focused on cancer mortality. However, the molecular mechanisms involved in this process require future studies. The most convincing evidence maintains the effects of physical activity on body weight and fat, insulin resistance, sex hormones, regulation of redox homeostasis, enhancing the antioxidant defense system, and reducing oxidative stress. Conclusions: These data demonstrate substantial prevention against several cancer incidences and mortality among patients who performed regular physical activity, of which dose meets at least the WHO’s guidelines. Further prospective cohort studies and long-term RCT studies are warranted to address a safe and personalized activity dose for cancer-site prevention, identify more precisely the biological mechanisms operating in the physical activity–cancer relationship, and promote the benefits of being physically active. Full article

Background/Objectives: Gastrointestinal stromal tumors (GISTs) are rare mesenchymal tumors of the gastrointestinal (GI) tract, predominantly driven by KIT or PDGFRα oncogene mutations. Nonspecific symptoms contribute to diagnostic delays, with general practitioners (GPs) playing a pivotal role in early detection. However, studies on GIST-specific primary care pathways are limited. This study examines GP contacts, diagnoses, and prescribed drugs in primary care during the 12 months preceding GIST diagnosis. Methods: This case-control study utilized data from the Netherlands Cancer Registry and Nivel Primary Care Database. It included 294 GIST patients diagnosed between 2010 and 2020 and 576 matched cancer-free controls. GP contacts, diagnoses, and newly prescribed drugs were analyzed across two time intervals: 0–4 and 5–12 months prediagnosis. Statistical comparisons were conducted using the Wilcoxon rank-sum test and descriptive analyses. Results: GIST cases had a median of six GP contacts (IQR 4–11) in the 12 months prediagnosis versus three (IQR 2–6) for controls (p < 0.05). Contacts increased 4 months before diagnosis, peaking 1 month prior. Common diagnoses in the 4-month interval included malignant neoplasms of the stomach (27.9%) and other digestive sites (27.6% and 11.2%), abdominal pain (9.5%), and iron deficiency anemia (9.5%). Newly prescribed drugs included proton pump inhibitors (13.9%) and osmotically acting laxatives (15.0%). Conclusions: This study highlights increased GP visits and specific reasons for these visits before GIST diagnosis. Future research should further examine GP records, not only through coded data but also unstructured data, and incorporate patient and GP perspectives to explore potential improvements in the diagnostic process. Full article

Background/Objectives: The increasing incidence of cancer during pregnancy is a growing public health concern, driven by delayed parenthood and rising maternal age. Pregnancy-associated cancer (PAC) presents complex clinical challenges, necessitating a balance between maternal cancer treatment and fetal safety. Historically considered incompatible with favorable pregnancy outcomes, evidence now suggests that pregnancy can often proceed without affecting cancer prognosis. A 2022 study in Italy provided the first population-based PAC estimates by linking cancer registries (CRs) and hospital discharge records (HDRs). This study aimed to update PAC estimates to 2019, covering 30% of the Italian population and addressing prior data limitations. Methods: A retrospective longitudinal analysis was conducted on women aged 15–49 diagnosed with malignant cancers between 2003 and 2019. Data from 21 Italian CRs were linked with HDRs to identify PAC cases, defined as obstetric hospitalizations occurring for women diagnosed with cancer in our study cohort in the period spanning from one year before to two years after a cancer diagnosis. All malignant cancers, excluding non-melanoma skin cancers, were analyzed. PAC rates were calculated per 1000 pregnancies, and trends were assessed using log-linear and JoinPoint regression models. Results: Among 131,774 women diagnosed with cancer, 6329 PAC cases were identified, with a PAC rate of 1.43 per 1000 pregnancies, consistent with global estimates. Thyroid (24.4%) and breast cancer (23.2%) were the most common. Analyzing the PAC rate by pregnancy outcome, in the period 2015–2019, this increased for both childbirths and miscarriages but decreased for voluntary terminations. Most hospitalizations (54%) occurred pre-diagnosis, peaking at diagnosis, especially for breast cancer (69%). Conclusions: PAC incidence is rising, particularly for live births and miscarriages, underscoring the need for multidisciplinary care and robust epidemiological insights to guide clinical management. Full article

Background: Gaucher disease (GD) is a rare autosomal recessive lysosomal storage disorder caused by mutations in the GBA1 gene, leading to deficient β-glucocerebrosidase activity. This results in the accumulation of glucocerebroside in macrophages, primarily affecting the liver, spleen, bone marrow, and bones. Understanding the clinical outcomes and genetic mutation profiles in specific populations, such as Turkish patients, is essential for optimized disease management and personalized therapy and preventing morbidity and mortality. Method: This retrospective study analyzed data from 29 Turkish patients with previously diagnosed type 1 GD at a single center between September and December 2023. Genetic analyses were performed to identify GBA1 mutations using next-generation sequencing. Genetic mutations were the primary criterion for diagnosing GD. Clinical features, treatment responses, and outcomes were evaluated. Clinical parameters included hematological findings, organomegaly, and bone involvement. Data were analyzed to identify potential correlations between genetic mutations and clinical manifestations. Results: This study included 14 male and 15 female patients, with a mean diagnosis age of 22.1 years. A significant family history was observed in 93% of cases, and 52% had consanguineous parents. Epistaxis (72%) was the most common pre-diagnosis symptom. Most patients received enzyme replacement therapy with 60 units/kg. Treatment led to significant improvements, including increased hemoglobin (21.1%), higher platelet count (86.1%), and reduced organomegaly (liver (10.02%), spleen (25.22%)). Genetic analysis identified seven mutations, with c.1226A>G (p.N409S) being the most frequent. Conclusions: This study highlights the spectrum of clinical outcomes and genetic mutations in Turkish patients with GD, emphasizing the variability in disease severity based on genotype. GD should be considered for patients with unexplained nosebleeds, hepatosplenomegaly, bone pain, weakness, or siblings or other family members with similar symptoms. The genetic analysis revealed considerable heterogeneity among patients, which indicates the necessity of observing this in the development of personalized treatment strategies. Future studies with larger cohorts and long-term follow-up are needed to further elucidate genotype–phenotype correlations in this population. Full article

This study investigates the relationship between lameness, milk composition, and rumination behaviour in dairy cows by leveraging sensor-based data for automated monitoring. Lameness was found to significantly impact both rumination and milk production. Lameness was assessed in 24 multiparous Holstein dairy cows throughout early lactation (up to 100 days postpartum), utilising a 1-to-5 scale. Lameness was found to significantly impact both rumination and milk production. On the day of diagnosis, rumination time decreased by 26.64% compared to the pre-diagnosis period (p < 0.01) and by 26.06% compared to healthy cows, indicating the potential of rumination as an early health indicator. The milk yield on the day of diagnosis was 28.10% lower compared to pre-diagnosis levels (p < 0.01) and 40.46% lower than healthy cows (p < 0.05). These findings suggest that lameness manifests prior to clinical signs, affecting productivity and welfare. Milk composition was also influenced, with lame cows exhibiting altered fat (+0.68%, p < 0.05) and lactose (−2.15%, p < 0.05) content compared to healthy cows. Positive correlations were identified between rumination time and milk yield (r = 0.491, p < 0.001), while negative correlations were observed between milk yield and milk fat, protein, and the fat-to-protein ratio (p < 0.001). Additionally, lameness was associated with elevated somatic cell counts in the milk, although sample size limitations necessitate further validation. This study highlights the critical role of rumination and milk performance metrics in identifying subclinical lameness, emphasising the utility of automated systems in advancing dairy cow welfare and productivity. The findings underscore the importance of early detection and management strategies to mitigate the economic and welfare impacts of lameness in dairy farming. Full article

While the pet market is continuously rapidly increasing in Korea, pet dog owners feel uncomfortable in coping with pet dog’s health problems in time. In this paper, we propose a pre-diagnosis system based on neuro-fuzzy learning, enabling non-expert users to monitor their pets’ health by inputting observed symptoms. To develop such a system, we form a disease–symptom database based on several textbooks with veterinarians’ guidance and filtering. The system offers likely disease predictions and recommended coping strategies based on fuzzy inference. We evaluated three fuzzy inference algorithms—PFCM-R, FHAL, and MNFL. While PFCM-R achieved high accuracy with clean data, it struggled with noisy inputs. FHAL showed better noise tolerance but lower precision. PFCM-R is a variant of well-known fuzzy unsupervised learner FCM, and FHAL is the hybrid fuzzy inference engine based on Fuzzy Association Memory and a double-layered FCM we developed. To make the system more robust, we propose the multi-layered neuro-fuzzy learner (MNFL) in this paper, which effectively weakens the association strength between the disease and the observed symptoms, less related to the body part on which the abnormal symptoms are observed. In experiments that are designed to examine how the inference system reacts under increasing noisy input from the user, MNFL achieved 98% accuracy even with non-erroneous inputs, demonstrating superior robustness to other inference engines. This system empowers pet owners to detect health issues early, improving the quality of care and fostering more informed interactions with veterinarians, ultimately enhancing the well-being of companion animals. Full article

The increasing adoption of electronic medical records (EMRs) presents a unique opportunity to enhance trauma care through data-driven insights. However, extracting meaningful and actionable information from unstructured clinical text remains a significant challenge. Addressing this gap, this study focuses on the application of natural language processing (NLP) techniques to extract injury-related variables and classify trauma patients based on the presence of loss of consciousness (LOC). A dataset of 23,308 trauma patient EMRs, including pre-diagnosis and post-diagnosis free-text notes, was analyzed using a bilingual (English and Korean) pre-trained RoBERTa model. The patients were categorized into four groups based on the presence of LOC and head trauma. To address class imbalance in LOC labeling, deep learning models were trained with weighted loss functions, achieving a high area under the curve (AUC) of 0.91. Local Interpretable Model-agnostic Explanations analysis further demonstrated the model’s ability to identify critical terms related to head injuries and consciousness. NLP can effectively identify LOC in trauma patients’ EMRs, with weighted loss functions addressing data imbalances. These findings can inform the development of AI tools to improve trauma care and decision-making. Full article

Background: The integration of artificial intelligence (AI) in medicine has progressed from rule-based systems to advanced models and is showing potential in clinical decision-making. In this study, the psychological impact of AI collaboration in clinical practice is assessed, highlighting its role as a support tool for medical residents. This study aimed to compare clinical decision-making approaches of junior rheumatology residents with both trained and untrained AI models in clinical reasoning, pre-diagnosis, first-line, and second-line management stages. Methods: Ten junior rheumatology residents and two GPT-4 models (trained and untrained) responded to 10 clinical cases, encompassing diagnostic and treatment challenges in inflammatory arthritis. The cases were evaluated using the Revised-IDEA (R-IDEA) scoring system and additional case management metrics. In addition to scoring clinical case performance, residents’ attitudes toward AI integration in clinical practice were assessed through a structured questionnaire, focusing on perceptions of AI’s potential after reviewing the trained GPT-4’s answers. Results: Trained GPT-4 outperformed residents across all stages, achieving significantly higher median R-IDEA scores and superior performance in pre-diagnosis, first-line, and second-line management phases. Residents expressed a positive attitude toward AI integration, with 60% favoring AI as a supportive tool in clinical practice, anticipating benefits in competence, fatigue, and burnout. Conclusions: Trained GPT-4 models outperform junior residents in clinical reasoning and management of rheumatology cases. Residents’ positive attitudes toward AI suggest its potential as a supportive tool to enhance confidence and reduce uncertainty in clinical practice. Trained GPT-4 may be used as a supplementary tool during the early years of residency. Full article

Background: Physical activity has been associated with a lower risk of various types of cancer and reduced cancer-specific mortality. Less is known about its impact on pancreatic cancer. The aim of this systematic review and meta-analysis was to summarize evidence on the association between physical activity and pancreatic cancer risk and mortality. Methods: PubMed and Embase were searched until May 2024 for studies examining physical activity in relation to pancreatic cancer incidence and mortality. Summary risk estimates for highest vs. lowest physical activity levels were calculated using a random-effects model. The risk of publication bias was assessed with a funnel plot and Egger’s regression test. Results: A total of seven case–control and eighteen prospective cohort studies were included that investigated the association between physical activity and pancreatic cancer incidence. Our meta-analysis showed a summary estimate of 0.75 (95% CI 0.64–0.88) for case–control studies (I² = 23%, n = 7) and a summary estimate of 0.91 (95% CI 0.86–0.97) for prospective cohort studies (I² = 5%, n = 18). Among the six prospective cohort studies that assessed pancreatic cancer mortality, the summary estimate was 1.03 (95% CI 0.83–1.27), I² = 50%. Conclusions: Higher levels of physical activity were associated with reduced pancreatic cancer risk. Evidence from a limited number of studies suggests that pre-diagnosis physical activity does not affect pancreatic cancer mortality. Full article