Search Results (1,883)

Introduction: The combination of ceftazidime−avibactam (CAZ-AVI) with aztreonam (ATM) may be an option for the treatment of infections due to metallo-β-lactamases (MBLs) producing bacteria, as recommended by current guidelines. MBLs protect the pathogen from any available β-lactam/β-lactamase inhibitor (BL/BLI). Moreover, in vitro and clinical data suggest that double carbapenem therapy (DCT) may be an option for such infections. Materials and Methods: This retrospective study was conducted in two mixed intensive care units (ICUs) at the University Hospital of Larissa, Thessaly, Greece, and the General Hospital of Larissa, Thessaly, Greece, during a three-year period (2022−2024). Mechanically ventilated patients with bloodstream infection (BSI) caused by K. pneumoniae resistant to all BL/BLI combinations were studied. Patients were divided into three groups: in the first, patients were treated with CAZ-AVI + ATM; in the second, with DCT; and in the third, with antibiotics other than BL/BLIs that presented in vitro susceptibility. The primary outcome of the study was the change in Sequential Organ Failure Assessment (SOFA) score between the onset of infection and the fourth day of antibiotic treatment. Secondary outcomes were SOFA score evolution during the treatment period, total duration of mechanical ventilation (MV), ICU length of stay (LOS), and ICU mortality. Results: A total of 95 patients were recruited. Among them, 23 patients received CAZ-AVI + AZT, 22 received DCT, and 50 patients received another antibiotic regimen which was in vitro active against the pathogen. The baseline characteristics were similar. The mean (SE) overall age was 63.2 (1.3) years. Mean (SE) Acute Physiology and Chronic Health Evaluation II (APACHE II) and SOFA scores were 16.3 (0.6) and 7.6 (0.3), respectively. The Charlson Index was similar between groups. The control group presented a statistically lower SOFA score on day 4 compared to the other two groups [mean (SE) 8.9 (1) vs. 7.4 (0.9) vs. 6.4 (0.5) for CAZ-AVI + ATM, DCT and control group, respectively (p = 0.045)]. The duration of mechanical ventilation, ICU LOS, and mortality were similar between the groups (p > 0.05). Comparison between survivors and non-survivors revealed that survivors had a lower SOFA score on the day of BSI, higher PaO₂/FiO₂ ratio, higher platelet counts, and lower lactate levels (p < 0.05). Septic shock was more frequent among non-survivors (60.3%) in comparison to survivors (27%) (p = 0.0015). Independent factors for mortality were PaO₂/FiO₂ ratio and lactate levels (p < 0.05). None of the antibiotic regimens received by the patients was independently associated with survival. Conclusions: Treatment with CAZ-AVI + ATM or DCT may offer similar clinical outcomes for patients suffering from BSI caused by K. pneumoniae strains resistant to all available BL/BLIs. However, larger studies are required to confirm the findings. Full article

Background: Fear of falling (FOF) is a significant concern among older adults, especially after total knee arthroplasty (TKA). FOF can limit daily activities, reduce quality of life, and hinder recovery. This study aimed to investigate the prevalence, severity, and impacts of FOF in patients undergoing TKA and identify factors contributing to increased FOF. Methods: A prospective observational study was conducted at King Abdulaziz Medical City in Riyadh, Saudi Arabia, from April 2024 to December 2024. This study included 52 participants aged 20 to 75 years who had undergone primary TKA. Data were collected at two time points: after TKA and at three months post-surgery. The Short Falls Efficacy Scale-International (SFES-I) was used to assess the severity of FOF, and the Short Form 36 (SF-36) was used to measure the quality of life. Descriptive statistics, t-tests, and logistic regression were used for analysis. Results: This study included 52 participants (mean age: 63.77 ± 6.65 years; 82.7% female). Post-TKA, all participants exhibited high FOF (mean SFES-I score: 56.75 ± 8.30). After three months, the mean SFES-I score decreased significantly to 49.04 ± 12.45 (t = 4.408, p < 0.05). Post-TKA, SF-36 showed significant improvements in the physical function, role of physical limitations, bodily pain, vitality, social function, role of emotional limitations, and mental health subdomains. Bilateral total knee arthroplasty, body mass index, and some SF-36 subcomponents—such as general health, vitality, and role of emotional limitations—were identified as factors leading to increased FOF. Conclusions: FOF remains prevalent and severe in TKA patients, even at three months post-surgery, affecting rehabilitation outcomes. Early identification and tailored interventions for FOF should be considered essential components of comprehensive TKA recovery programs. Full article

Adverse drug events (ADEs) significantly impact patient safety and health outcomes. Manual ADE detection from clinical narratives is time-consuming, labor-intensive, and costly. Recent advancements in large language models (LLMs), including transformer-based architectures such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pretrained Transformer (GPT) series, offer promising methods for automating ADE extraction from clinical data. These models have been applied to various aspects of pharmacovigilance and clinical decision support, demonstrating potential in extracting ADE-related information from real-world clinical data. Additionally, chatbot-assisted systems have been explored as tools in clinical management, aiding in medication adherence, patient engagement, and symptom monitoring. This narrative review synthesizes the current state of LLMs in ADE detection from a clinical perspective, organizing studies into categories such as human-facing decision support tools, immune-related ADE detection, cancer-related and non-cancer-related ADE surveillance, and personalized decision support systems. In total, 39 articles were included in this review. Across domains, LLM-driven methods have demonstrated promising performances, often outperforming traditional approaches. However, critical limitations persist, such as domain-specific variability in model performance, interpretability challenges, data quality and privacy concerns, and infrastructure requirements. By addressing these challenges, LLM-based ADE detection could enhance pharmacovigilance practices, improve patient safety outcomes, and optimize clinical workflows. Full article

Large, high-quality patient datasets are essential for applications like economic modeling and patient simulation. However, real-world data is often inaccessible or incomplete. Synthetic patient data offers an alternative, and current methods often fail to preserve clinical plausibility, real-world correlations, and logical consistency. This study presents a patient cohort generator designed to produce realistic, statistically valid synthetic datasets. The generator uses predefined probability distributions and Cholesky decomposition to reflect real-world correlations. A dependency matrix handles variable relationships in the right order. Hard limits block unrealistic values, and binary variables are set using percentiles to match expected rates. Validation used two datasets, NHANES (2021–2023) and the Framingham Heart Study, evaluating cohort diversity (general, cardiac, low-dimensional), data sparsity (five correlation scenarios), and model performance (MSE, RMSE, R², SSE, correlation plots). Results demonstrated strong alignment with real-world data in central tendency, dispersion, and correlation structures. Scenario A (empirical correlations) performed best (R² = 86.8–99.6%, lowest SSE and MAE). Scenario B (physician-estimated correlations) also performed well, especially in a low-dimensions population (R² = 80.7%). Scenario E (no correlation) performed worst. Overall, the proposed model provides a scalable, customizable solution for generating synthetic patient cohorts, supporting reliable simulations and research when real-world data is limited. While deep learning approaches have been proposed for this task, they require access to large-scale real datasets and offer limited control over statistical dependencies or clinical logic. Our approach addresses this gap. Full article

The increasing complexity and scale of electronic health records (EHRs) demand advanced tools for efficient data retrieval, summarization, and comparative analysis in clinical practice. MERA (Medical Electronic Records Assistant) is a Retrieval-Augmented Generation (RAG)-based AI system that addresses these needs by integrating domain-specific retrieval with large language models (LLMs) to deliver robust question answering, similarity search, and report summarization functionalities. MERA is designed to overcome key limitations of conventional LLMs in healthcare, such as hallucinations, outdated knowledge, and limited explainability. To ensure both privacy compliance and model robustness, we constructed a large synthetic dataset using state-of-the-art LLMs, including Mistral v0.3, Qwen 2.5, and Llama 3, and further validated MERA on de-identified real-world EHRs from the MIMIC-IV-Note dataset. Comprehensive evaluation demonstrates MERA’s high accuracy in medical question answering (correctness: 0.91; relevance: 0.98; groundedness: 0.89; retrieval relevance: 0.92), strong summarization performance (ROUGE-1 F1-score: 0.70; Jaccard similarity: 0.73), and effective similarity search (METEOR: 0.7–1.0 across diagnoses), with consistent results on real EHRs. The similarity search module empowers clinicians to efficiently identify and compare analogous patient cases, supporting differential diagnosis and personalized treatment planning. By generating concise, contextually relevant, and explainable insights, MERA reduces clinician workload and enhances decision-making. To our knowledge, this is the first system to integrate clinical question answering, summarization, and similarity search within a unified RAG-based framework. Full article

Background: Hypertension is a serious global health issue affecting over one billion adults and leading to severe complications if left unmanaged. Despite medical advancements, only a fraction of patients effectively have their hypertension under control. Among the factors that hinder adherence to hypertensive drugs are the debilitating side effects of the drugs. The lack of adherence results in poorer patient outcomes as patients opt to live with their condition, instead of having to deal with the side effects. Hence, there is a need to discover new hypertension drug molecules with better side effects to increase patient treatment options. To this end, computational methods such as artificial intelligence (AI) have become an exciting option for modern drug discovery. AI-based computational drug discovery methods generate numerous new lead antihypertensive drug molecules. However, predicting their potential side effects remains a significant challenge because of the complexity of biological interactions and limited data on these molecules. Methods: This paper presents a machine learning approach to predict the potential side effects of computationally synthesised antihypertensive drug molecules based on their molecular properties, particularly functional groups. We curated a dataset combining information from the SIDER 4.1 and ChEMBL databases, enriched with molecular descriptors (logP, PSA, HBD, HBA) using RDKit. Results: Gradient Boosting gave the most stable generalisation, with a weighted F1 of 0.80, and AUC-ROC of 0.62 on the independent test set. SHAP analysis over the cross-validation folds showed polar surface area and logP contributing the largest global impact, followed by hydrogen bond counts. Conclusions: Functional group patterns, augmented with key ADMET descriptors, offer a first-pass screen for identifying side-effect risks in AI-designed antihypertensive leads. Full article

Background: Down syndrome (DS) is a genetic disorder characterized by an extra copy of chromosome 21, often leading to intellectual disabilities, developmental delays, and an increased risk of various comorbidities, including thyroid dysfunction and mental health disorders. The relationship between thyroid dysfunction and mood disorders, particularly depression in DS populations, requires further investigation. Objective: This study aims to investigate the presence of a correlative relationship between hypothyroidism and depression in 178,840 individuals with DS, utilizing data from the National Inpatient Sample (NIS) to determine if those with comorbid hypothyroidism exhibit higher rates of depression compared to their counterparts without hypothyroidism. Methods: A retrospective analysis of the 2016–2019 NIS dataset was conducted, focusing on patients with DS, hypothyroidism, and depression diagnoses. The diagnoses were determined and labeled based on ICD-10 codes associated with NIS datapoints. Survey-weighted linear regression analyses were employed to assess the association between hypothyroidism and depression within the DS cohort, adjusting for demographic factors such as age, gender, and race. Results: This study found that individuals with DS exhibit a significantly higher prevalence of hypothyroidism (29.88%) compared to the general population (10.28%). Additionally, individuals with DS and comorbid hypothyroidism demonstrated a higher prevalence of depression (8.67%) compared to those without hypothyroidism (3.00%). These findings suggest a significant association between hypothyroidism and increased depression risk among individuals with DS. However, the overall prevalence of depression in DS (4.69%) remains substantially lower than in the general population (12.27%). Conclusions: This study highlights the importance of considering hypothyroidism as a potential contributor to depression in individuals with DS. Further research is needed to explore the underlying mechanisms of this association and potential screening and management strategies to address thyroid dysfunction and its potential psychiatric implications in DS. Full article

Background/Objectives: The RTK-RAS signaling cascade is a central axis in colorectal cancer (CRC) pathogenesis, governing cellular proliferation, survival, and therapeutic resistance. Somatic alterations in key pathway genes—including KRAS, NRAS, BRAF, and EGFR—are pivotal to clinical decision-making in precision oncology. However, the integration of these genomic events with clinical and demographic data remains hindered by fragmented resources and a lack of accessible analytical frameworks. To address this challenge, we developed AI-HOPE-RTK-RAS, a domain-specialized conversational artificial intelligence (AI) system designed to enable natural language-based, integrative analysis of RTK-RAS pathway alterations in CRC. Methods: AI-HOPE-RTK-RAS employs a modular architecture combining large language models (LLMs), a natural language-to-code translation engine, and a backend analytics pipeline operating on harmonized multi-dimensional datasets from cBioPortal. Unlike general-purpose AI platforms, this system is purpose-built for real-time exploration of RTK-RAS biology within CRC cohorts. The platform supports mutation frequency profiling, odds ratio testing, survival modeling, and stratified analyses across clinical, genomic, and demographic parameters. Validation included reproduction of known mutation trends and exploratory evaluation of co-alterations, therapy response, and ancestry-specific mutation patterns. Results: AI-HOPE-RTK-RAS enabled rapid, dialogue-driven interrogation of CRC datasets, confirming established patterns and revealing novel associations with translational relevance. Among early-onset CRC (EOCRC) patients, the prevalence of RTK-RAS alterations was significantly lower compared to late-onset disease (67.97% vs. 79.9%; OR = 0.534, p = 0.014), suggesting the involvement of alternative oncogenic drivers. In KRAS-mutant patients receiving Bevacizumab, early-stage disease (Stages I–III) was associated with superior overall survival relative to Stage IV (p = 0.0004). In contrast, BRAF-mutant tumors with microsatellite-stable (MSS) status displayed poorer prognosis despite higher chemotherapy exposure (OR = 7.226, p < 0.001; p = 0.0000). Among EOCRC patients treated with FOLFOX, RTK-RAS alterations were linked to worse outcomes (p = 0.0262). The system also identified ancestry-enriched noncanonical mutations—including CBL, MAPK3, and NF1—with NF1 mutations significantly associated with improved prognosis (p = 1 × 10⁻⁵). Conclusions: AI-HOPE-RTK-RAS exemplifies a new class of conversational AI platforms tailored to precision oncology, enabling integrative, real-time analysis of clinically and biologically complex questions. Its ability to uncover both canonical and ancestry-specific patterns in RTK-RAS dysregulation—especially in EOCRC and populations with disproportionate health burdens—underscores its utility in advancing equitable, personalized cancer care. This work demonstrates the translational potential of domain-optimized AI tools to accelerate biomarker discovery, support therapeutic stratification, and democratize access to multi-omic analysis. Full article

Background: Gastrointestinal (GI) cancer patients face a four-fold higher suicide risk than the general US population. This study explores psychosocial aspects of GI cancer patient experiences, assessing suicidal ideation and behavior, mental distress during treatment phases, and psychosocial factors on mental health. Methods: A two-phase mixed-methods approach involved a web-based survey and follow-up interviews. Quantitative data analysis validated mental health and suicidal ideation constructs, and correlation analyses were performed. The patient journey was charted from diagnosis to treatment. Results: Two hundred and two individuals participated, with 76 from the rural Appalachian region and 78 undergoing treatments. Quantitative analysis showed a higher prevalence of passive suicidal ideation than active planning. The post-treatment recovery period was the most emotionally challenging. Qualitative data emphasized emotional support and vulnerability to isolation. Care quality concerns included individualized treatment plans and better communication. Patients also needed clear, comprehensive information about treatment and side effects. The in-depth interview with four GI cancer patients revealed a healthcare system prioritizing expedient treatment over comprehensive care, lacking formal psychological support. AI emerged as a promising avenue for enhancing patient understanding and treatment options. Conclusions: Our research advocates for a patient-centric model of care, enhanced by technology and empathetic communication. Full article

Total Knee Arthroplasty (TKA) is a well-established surgical intervention for the management of end-stage knee osteoarthritis. While the procedure is generally successful, postoperative rehabilitation remains a key determinant of long-term functional outcomes. Traditional rehabilitation protocols, particularly those requiring in-person clinical visits, often encounter limitations in accessibility, patient adherence, and personalization. In response, emerging sensor technologies have introduced innovative solutions to support and enhance recovery following TKA. This review provides a thematically organized synthesis of the current landscape and future directions of sensor-assisted rehabilitation in TKA. It examines four main categories of technologies: wearable sensors (e.g., IMUs, accelerometers, gyroscopes), smart implants, pressure-sensing systems, and mobile health (mHealth) platforms such as ReHub^® and BPMpathway. Evidence from recent randomized controlled trials and systematic reviews demonstrates their effectiveness in tracking mobility, monitoring range of motion (ROM), detecting gait anomalies, and delivering real-time feedback to both patients and clinicians. Despite these advances, several challenges persist, including measurement accuracy in unsupervised environments, the complexity of clinical data integration, and digital literacy gaps among older adults. Nevertheless, the integration of artificial intelligence (AI), predictive analytics, and remote rehabilitation tools is driving a shift toward more adaptive and individualized care models. This paper concludes that sensor-enhanced rehabilitation is no longer a future aspiration but an active transition toward a smarter, more accessible, and patient-centered paradigm in recovery after TKA. Full article

Objectives: Spinal diseases are commonly encountered health problems with a wide spectrum. In addition to degenerative changes, other common spinal pathologies include metastases and compression fractures. Benign tumors like hemangiomas and infections such as spondylodiscitis are also frequently observed. Although magnetic resonance imaging (MRI) is considered the gold standard in diagnostic imaging, the morphological similarities of lesions can pose significant challenges in differential diagnoses. In recent years, the use of artificial intelligence applications in medical imaging has become increasingly widespread. In this study, we aim to detect and classify vertebral body lesions using the YOLO-v8 (You Only Look Once, version 8) deep learning architecture. Materials and Methods: This study included MRI data from 235 patients with vertebral body lesions. The dataset comprised sagittal T1- and T2-weighted sequences. The diagnostic categories consisted of acute compression fractures, metastases, hemangiomas, atypical hemangiomas, and spondylodiscitis. For automated detection and classification of vertebral lesions, the YOLOv8 deep learning model was employed. Following image standardization and data augmentation, a total of 4179 images were generated. The dataset was randomly split into training (80%) and validation (20%) subsets. Additionally, an independent test set was constructed using MRI images from 54 patients who were not included in the training or validation phases to evaluate the model’s performance. Results: In the test, the YOLOv8 model achieved classification accuracies of 0.84 and 0.85 for T1- and T2-weighted MRI sequences, respectively. Among the diagnostic categories, spondylodiscitis had the highest accuracy in the T1 dataset (0.94), while acute compression fractures were most accurately detected in the T2 dataset (0.93). Hemangiomas exhibited the lowest classification accuracy in both modalities (0.73). The F1 scores were calculated as 0.83 for T1-weighted and 0.82 for T2-weighted sequences at optimal confidence thresholds. The model’s mean average precision (mAP) 0.5 values were 0.82 for T1 and 0.86 for T2 datasets, indicating high precision in lesion detection. Conclusions: The YOLO-v8 deep learning model we used demonstrates effective performance in distinguishing vertebral body metastases from different groups of benign pathologies. Full article

Tobacco use disorder remains a leading cause of preventable mortality, with nicotine playing a central role in the development and maintenance of dependence, mainly through its action on α4β2 nicotinic acetylcholine receptors (nAChRs). Smoking cessation treatments must address both physiological withdrawal and the affective disturbances (such as anxiety, irritability, and mood lability) which often facilitate relapses. This review compares two pharmacotherapies used in smoking cessation, varenicline and cytisinicline (cytisine), with particular focus on their impact on emotional regulation, psychological symptoms, and neuropsychiatric safety. Varenicline, a high-affinity partial agonist at α4β2 nAChRs, has demonstrated superior efficacy in maintaining abstinence and is well-supported by robust clinical data, including in psychiatric populations. However, its use may be limited by adverse effects such as nausea and sleep disorders. Cytisinicline, a structurally similar but less potent partial agonist, has recently gained renewed interest due to its lower cost, favorable tolerability profile, and comparable effectiveness in the general population. Although less extensively studied in patients with serious mental illness, preliminary data suggest cytisinicline may offer a better side effect profile, particularly regarding sleep disturbances and emotional reactivity. Both agents appear to ameliorate withdrawal-related affective symptoms without significantly increasing psychiatric risk. Ultimately, pharmacotherapy choice should be guided by individual clinical features, mental health status, treatment tolerability, and resource availability. Further research is needed to establish cytisinicline’s efficacy and safety across diverse clinical contexts, particularly among individuals with severe psychiatric comorbidities. Full article

Background: Osteogenesis imperfecta (OI) is a rare genetic connective tissue disorder characterized by bone fragility, most often caused by pathogenic variants in type I collagen genes. In this context, we aimed to describe the clinical and epidemiological characteristics of patients with OI who were hospitalized for coronavirus disease (COVID)-19 in Brazil between 2020 and 2024. Methods: We conducted a retrospective descriptive analysis using data from the Brazilian Unified Health System (SUS, which stands for the Portuguese Sistema Único de Saúde) through the Open-Data-SUS platform. Patients with a confirmed diagnosis of OI and hospitalization due to COVID-19 were included. Descriptive statistical analysis was performed to evaluate demographic, clinical, and outcome-related variables. We included all hospitalized COVID-19 cases with a confirmed diagnosis of OI between 2020 and 2024. Results: Thirteen hospitalized patients with OI and COVID-19 were identified. Most were adults (9; 69.2%), male (7; 53.8%), self-identified as White (9; 69.2%), and all were residents of urban areas (13; 100.0%). The most frequent symptoms were fever (10; 76.9%), cough (9; 69.2%), oxygen desaturation (9; 69.2%), dyspnea (8; 61.5%), and respiratory distress (7; 53.8%). Two patients had heart disease, one had chronic lung disease, and one was obese. As for vaccination status, five patients (38.5%) had been vaccinated against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Four patients (30.8%) required admission to an intensive care unit (ICU), and six (46.2%) required noninvasive ventilatory support. Among those admitted to the ICU, only two required invasive mechanical ventilation. The clinical outcome was death in two cases (15.4%). Both patients were male, White, and had not been vaccinated against SARS-CoV-2. One was 47 years old, was not admitted to the ICU, but required noninvasive ventilation. Despite the underlying condition most patients had favorable outcomes, consistent with an international report. Conclusions: This is the first report to describe the clinical and epidemiological profile of patients with OI hospitalized for COVID-19 in Brazil, providing initial insights into how a rare bone disorder intersects with an acute respiratory infection. The generally favorable outcomes observed—despite the underlying skeletal fragility—suggest that individuals with OI are not necessarily at disproportionate risk of severe COVID-19, particularly when appropriately monitored. The occurrence of deaths only among unvaccinated patients underscores the critical role of SARS-CoV-2 vaccination in this population. Although pharmacological treatment data were unavailable, the potential protective effects of bisphosphonates and vitamin D merit further exploration. These findings support the need for early preventive strategies, systematic vaccination efforts, and dedicated clinical protocols for rare disease populations during infectious disease outbreaks. Full article

Objectives: The relationship between oral health and general health of geriatric in-hospital patients (GIH) who are poly-morbid and edentulous is currently unclear. This study determined the relationship between oral health and general health, and further implications and recommendations were derived. Methods: This retrospective cohort study included 81 GIH patients with impairment of oral state and masticatory function and need for immediate prosthetic treatment. The number of medical diagnoses, particularly main diagnoses of being hospitalized, comorbid diagnoses and the dental/oral state, were evaluated. Laboratory data of vitamin D3 and albumin concentrations were measured. Intraoral risk factors (IRF) affecting the masticatory function were intraoral inflammation, mucogingival impairment (MGI) and severe bone crest atrophy (SBCA). Masticatory function was evaluated by DMF*-T Index (number of destroyed/diseased, missing teeth and artificial fabrication), Eichner Index and Scores. The clinical relevance was surveyed by significance and effect size calculations. Results: In GIH, the number of medical diagnoses correlated significantly with the occurrence of IRFs. SBCA was the most affecting IRF, as measured by Eichner Index at baseline (p = 0.001). Single main diagnoses CNS and gastro-intestinal disease (GID) correlated with both deficiency of vitamin D3 levels (p = 0.011; p = 0.028) and hypoalbuminemia (p = 0.013; p = 0.023). Single comorbid diagnoses significantly correlated with both vitamin D3 deficiency and hypoalbuminemia (CVD (p = 0.031); DM (p = 0.042). Hypoalbuminemia was further found to be correlated with the sum of comorbid diagnoses (p = 0.033). Conclusions: GIH patients suffered from general and dental poly-morbidity. The prevalence of diseases was higher due to SBCA and impaired masticatory function. Deficiency of vitamin D3 and hypoalbuminemia were possible malnutrition markers. Full article

Background/Objectives: Adherence to oral endocrine therapy (OET) is essential to reduce recurrence but is predominantly lower among underserved patients, leading to worse health outcomes. We aimed to depict longitudinal patterns of OET adherence using group-based trajectory modeling (GBTM) and identify predictors associated with each adherence trajectory. Methods: A single-center, retrospective study was conducted to analyze data from women 18 years or older with metastatic breast cancer who initiated with an OET and were treated from January to December 2022. Adherence was measured using a proportion of days covered (PDC > 80%) for 12 months. Binary monthly indicator of PDC was incorporated into GBTM. Four models were generated by changing the number of groups from 2 to 5, using a 2nd-order polynomial function of time. A multinomial logistic regression model was run to evaluate the predictors of non-adherence trajectories, and “adherence” was considered the reference group. Results: A total of 346 women had a (mean age of 60) years; 93% were Hispanic or of Mexican origin; 90% were taking aromatase inhibitors (AIs), with an endocrine therapy of 1.05 years. Three trajectories of adherence to GBTM were identified: a gradual decline in adherence (n = 88, 25.5%), improving suboptimal adherence (n = 106, 30.6%), and adherent (n = 152, 43.9%). Multinomial logistic regression analysis showed that significant predictors are diabetes (odds ratio (OR), 2.96; 95% confidence interval (CI), 1.57–5.57) and fewer years of therapy (OR, 2.96; 95% CI, 1.57–5.57). Suboptimal adherence among RGV patients receiving OET, with approximately 56% following a non-adherent trajectory. Conclusions: Suboptimal adherence among RGV patients receiving OET, with approximately 56% following a non-adherent trajectory. Significant predictors should be considered when designing targeted interventions. Full article