Identify Subgroups Of Patients Research Articles

Comorbidity neural network model for personalised recommendations in cardiometabolic risk factor management: towards early precision medicine in routine clinical practice

Abstract Background and Aims Hypertension and hypercholesterolaemia often develop in tandem to confer a risk of cardiovascular disease that may be more than additive. The present study explored early comorbid therapeutic intervention, i.e., beyond individual disease silos, while minimising data bias to provide clinical decision support tools that are portable across clinics. Methods A neural network was created to reproduce UK national clinical guidelines with an accuracy higher than 95%. Relying on real-world evidence from the UK primary care Clinical Practice Research Datalink electronic health record resource, a transfer learning methodology was then applied to achieve recommended risk factor goal attainment after two years. Shapley values derived from game theory were used to define similar digital twin cohorts, and to evaluate individualised recommendations that deviated from national clinical guidelines by rejecting a no-benefit hypothesis retrospectively in a classical proportion test. The methodology was ported to an independent hold-out dataset with anonymized records from six primary care clinics in the South of England. Results The adult patient population (n=469,496, mean+SD age 61+11yr; M 56% vs F 44%; primary 84% vs secondary prevention 16%) included 101,255 diagnosed for hypertension and 112,180 for cholesterol management. While a majority of the 52,504 therapeutic decisions in a test set agree with single morbidity guidelines, for 4639 deviations from the guidance, a significant minority was identified for whom alternative therapy was recommended. Rejecting a no-clinical benefit hypothesis at the 95% confidence level in a retrospective analysis, 1367 decisions showed statistically significant better outcomes over guidelines, for example by escalating anti-hypertensive therapies for patients receiving statin therapy (1085) or by complementing anti-hypertensive therapy with a statin (158). Similar findings were obtained when tested in a hold-out dataset with 13,725 decisions for 6531 patients. Conclusions The results support the contention that machine learning can identify patient subgroups for whom comorbid intervention deviating from clinical guidelines may be appropriate. A novel aspect of the study is the demonstration of clinically portable and actionable application of machine learning in the context of comorbid cardiometabolic diseases. The results represent practical steps towards personalised precision medicine for cardiovascular comorbidity in routine clinical practice.

Endomyocardial biopsy in patients with myocarditis - still justified in the CMR era? A single-centre experience

Abstract Background Endomyocardial biopsy (EMB) is still considered the diagnostic gold standard for myocarditis. However, in the past decades, cardiac magnetic resonance (CMR) was established as a non-invasive tool supporting the diagnosis of myocarditis. Furthermore, there is often reluctance in performing EMB due to rare but potentially severe complications. We therefore sought to identify patient subgroups that could potentially derive benefits from EMB. This involved a comprehensive analysis of the diagnostic and therapeutic outcomes resulting from the procedure at our centre. Methods In this retrospective single-centre study, data of all patients presenting with (peri-) myocarditis between 01/2016 and 06/2023 at our tertiary care centre were included. Frequency of histological confirmation of acute myocarditis and histology leading to immunosuppressive therapy were analysed according to patient risks. Prespecified risk factors were (i) LV-EF ≤30%, (ii) presence of severe arrhythmias (VF, VT, high grade AV-block) or (iii) pre-existing autoimmune disease. Furthermore, the subgroup of recurrent myocarditis cases was analysed separately. Results A total of 150 consecutive patients (36.7 ± 15.5 years, 77.3% male) were included in this study. 26/150 patients had a documented EF ≤30%, 13/150 an EF >30% with another risk factor and 111/150 an EF>30% without another risk factor. EMB was performed in 21/26 patients with EF ≤30% (80.7%), in 7/13 patients with EF >30% and another risk factors (53.8%) and in 16/111 (14%) patients without risk factors. EMB led to the initiation of immunosuppressive therapy in 11/28 patients with risk factors (39.3%) and in none of the patients without risk factors (0/16, 0%, p=0.003)(figure 1). With respect to the subgroup of patients presenting with recurrent myocarditis (n=10), no specific therapy was performed. Conclusion Due to a high therapeutic yield for initiation of immunosuppressive therapy in non-infectious myocarditis, performing EMB should be considered in all high-risk patients. In patients without clinical risk factors including cases of recurrent or relapsing myocarditis no specific therapy was initiated.

Identification of Severe Acute Exacerbations of Chronic Obstructive Pulmonary Disease Subgroups by Machine Learning Implementation in Electronic Health Records.

Acute exacerbations of COPD (AECOPD) are heterogeneous. Machine learning (ML) has previously been used to dissect some of the heterogeneity in COPD. The widespread adoption of electronic health records (EHRs) has led to the rapid accumulation of large amounts of patient data as part of routine clinical care. However, it is unclear whether the implementation of ML in EHR-derived data has the potential to identify subgroups of AECOPD. Determine whether ML implementation using EHR data from severe AECOPD requiring hospitalization identifies relevant subgroups. This study used two retrospective cohorts of patients with AECOPD (non-COVID-19 and COVID-19) treated at Yale-New Haven Hospital (YNHHS). K-means clustering was used to identify patient subgroups. We identified three subgroups in the non-COVID cohort (n=1,736). Each subgroup had distinct clinical characteristics. The reference subgroup was the largest (n=904), followed by cardio-renal (n = 548) and eosinophilic (n=284). The eosinophilic subgroup had milder severity of AECOPD, including a shorter hospital stay (p<0.01). The cardio-renal subgroup had the highest mortality during (5%) and in the year after hospitalization (30%). Validation of the severe AECOPD classifier in the COVID-19 cohort recapitulated the characteristics seen in the non-COVID cohort. AECOPD subgroups in the COVID-19 cohort had different IL-1 beta, IL-2R, and IL-8 levels (FDR ≤ 0.05. These specific leukocyte and cytokine profiles resulted in inflammatory differences between the AECOPD subgroups based on C-reactive protein levels. Incorporating ML with EHR-data allows the identification of specific clinical and biological subgroups for severe AECOPD.

Predictors of treatment response trajectories to cognitive behavioral therapy for chronic fatigue syndrome: A cohort study

BackgroundThe response to cognitive behavioral therapy (CBT) for chronic fatigue syndrome (CFS) varies greatly between patients, but predictors of treatment success remain to be elucidated. We aimed to identify patient subgroups based on fatigue trajectory during CBT, identify pre-treatment predictors of subgroup membership, and disentangle the direction of predictor – outcome relationships over time. Methods297 individuals with CFS were enrolled in a standardized CBT program consisting of 17 sessions, with session timing variable between participants. Self-reported levels of fatigue, depressive, anxiety, and somatic symptoms, perceived stress, and positive affect were collected pre-treatment, and after 3, 10, and 15 sessions. Latent Class Growth Analysis (LCGA) was used to identify subgroups based on fatigue trajectories and baseline predictors of group membership. Cross-lagged structural equation models were used to disentangle predictor-outcome relationships. ResultsLCGA identified four fatigue trajectory subgroups, which were labelled as “no improvement” (23 %), “weak improvement” (45 %), “moderate improvement” (23 %), and “strong improvement” (9 %) classes. Higher pre-treatment levels of depressive, anxiety, and somatic symptoms, stress, and lower levels of positive affect predicted membership of the “no improvement” subgroup. Reductions in anxiety preceded reductions in fatigue, while the depressive symptoms – fatigue relationship was bidirectional. ConclusionsOn a group level, there were statistically significant reductions in fatigue after 15 sessions of CBT, with important individual differences in treatment response. Higher pre-treatment levels of anxious, depressive, and somatic symptoms and perceived stress are predictors of lack of response, with reductions in anxiety and stress preceding improvements in fatigue.

Identifying patient subgroups in MASLD and MASH-associated fibrosis: molecular profiles and implications for drug development

The incidence of MASLD and MASH-associated fibrosis is rapidly increasing worldwide. Drug therapy is hampered by large patient variability and partial representation of human MASH fibrosis in preclinical models. Here, we investigated the mechanisms underlying patient heterogeneity using a discovery dataset and validated in distinct human transcriptomic datasets, to improve patient stratification and translation into subgroup specific patterns. Patient stratification was performed using weighted gene co-expression network analysis (WGCNA) in a large public transcriptomic discovery dataset (n = 216). Differential expression analysis was performed using DESeq2 to obtain differentially expressed genes (DEGs). Ingenuity Pathway analysis was used for functional annotation. The discovery dataset showed relevant fibrosis-related mechanisms representative of disease heterogeneity. Biological complexity embedded in genes signature was used to stratify discovery dataset into six subgroups of various sizes. Of note, subgroup-specific DEGs show differences in directionality in canonical pathways (e.g. Collagen biosynthesis, cytokine signaling) across subgroups. Finally, a multiclass classification model was trained and validated in two datasets. In summary, our work shows a potential alternative for patient population stratification based on heterogeneity in MASLD-MASH mechanisms. Future research is warranted to further characterize patient subgroups and identify protein targets for virtual screening and/or in vitro validation in preclinical models.

Bi-level Graph Learning Unveils Prognosis-Relevant Tumor Microenvironment Patterns in Breast Multiplexed Digital Pathology.

The tumor microenvironment is widely recognized for its central role in driving cancer progression and influencing prognostic outcomes. There have been increasing efforts dedicated to characterizing this complex and heterogeneous environment, including developing potential prognostic tools by leveraging modern deep learning methods. However, the identification of generalizable data-driven biomarkers has been limited, in part due to the inability to interpret the complex, black-box predictions made by these models. In this study, we introduce a data-driven yet interpretable approach for identifying patterns of cell organizations in the tumor microenvironment that are associated with patient prognoses. Our methodology relies on the construction of a bi-level graph model: (i) a cellular graph, which models the intricate tumor microenvironment, and (ii) a population graph that captures inter-patient similarities, given their respective cellular graphs, by means of a soft Weisfeiler-Lehman subtree kernel. This systematic integration of information across different scales enables us to identify patient subgroups exhibiting unique prognoses while unveiling tumor microenvironment patterns that characterize them. We demonstrate our approach in a cohort of breast cancer patients and show that the identified tumor microenvironment patterns result in a risk stratification system that provides new complementary information with respect to standard stratification systems. Our results, which are validated in two independent cohorts, allow for new insights into the prognostic implications of the breast tumor microenvironment. This methodology could be applied to other cancer types more generally, providing insights into the cellular patterns of organization associated with different outcomes.

CIRCULATING HEPARAN SULFATE PROFILES IN PEDIATRIC ACUTE RESPIRATORY DISTRESS SYNDROME.

Introduction: Sepsis-induced degradation of endothelial glycocalyx heparan sulfate (HS) contributes to the pulmonary microvascular endothelial injury characteristic of acute respiratory distress syndrome (ARDS) pathogenesis. Our objectives were to (1) examine relationships between plasma indices of HS degradation and protein biomarkers of endothelial injury and (2) identify patient subgroups characterized by distinct profiles of HS degradation in children with ARDS. Methods: We analyzed prospectively collected plasma (2018-2020) from a cohort of invasively mechanically ventilated children (aged >1 month to <18 years) with ARDS. Mass spectrometry characterized and quantified patterns of HS disaccharide sulfation. Protein biomarkers reflective of endothelial injury (e.g., angiopoietin-2, vascular cell adhesion molecule-1, soluble thrombomodulin) were measured with a multiplex immunoassay. Pearson correlation coefficients were used to construct a biomarker correlation network. Centrality metrics detected influential biomarkers (i.e., network hubs). K-means clustering identified unique patient subgroups based on HS disaccharide profiles. Results: We evaluated 36 patients with pediatric ARDS. HS disaccharide sulfation patterns, 6S, NS, and NS2S, positively correlated with all biomarkers of endothelial injury (all P < 0.05) and were classified as network hubs. We identified three patient subgroups, with cluster 3 (n = 5) demonstrating elevated levels of 6S and N-sulfated HS disaccharides. In cluster 3, 60% of children were female and nonpulmonary sepsis accounted for 60% of cases. Relative to cluster 1 (n = 12), cluster 3 was associated with higher oxygen saturation index (P = 0.029) and fewer 28-day ventilator-free days (P = 0.016). Conclusions: Circulating highly sulfated HS fragments may represent emerging mechanistic biomarkers of endothelial injury and disease severity in pediatric ARDS.

Mechanical Thrombectomy Versus Intravenous Thrombolysis in Distal Medium Vessel Acute Ischemic Stroke: A Multinational Multicenter Propensity Score-Matched Study.

The management of acute ischemic stroke (AIS) due to distal medium vessel occlusion (DMVO) remains uncertain, particularly in comparing the effectiveness of intravenous thrombolysis (IVT) plus mechanical thrombectomy (MT) versus IVT alone. This study aimed to evaluate the safety and efficacy in DMVO patients treated with either MT-IVT or IVT alone. This multinational study analyzed data from 37 centers across North America, Asia, and Europe. Patients with AIS due to DMVO were included, with data collected from September 2017 to July 2023. The primary outcome was functional independence, with secondary outcomes including mortality and safety measures such as types of intracerebral hemorrhage. The study involved 1,057 patients before matching, and 640 patients post-matching. Functional outcomes at 90 days showed no significant difference between groups in achieving good functional recovery (modified Rankin Scale 0-1 and 0-2), with adjusted odds ratios (OR) of 1.21 (95% confidence interval [CI] 0.81 to 1.79; P=0.35) and 1.00 (95% CI 0.66 to 1.51; P>0.99), respectively. Mortality rates at 90 days were similar between the two groups (OR 0.75, 95% CI 0.44 to 1.29; P=0.30). The incidence of symptomatic intracerebral hemorrhage was comparable, but any type of intracranial hemorrhage was significantly higher in the MT-IVT group (OR 0.43, 95% CI 0.29 to 0.63; P<0.001). The results of this study indicate that while MT-IVT and IVT alone show similar functional and mortality outcomes in DMVO patients, MT-IVT presents a higher risk of hemorrhagic complications, thus MT-IVT may not routinely offer additional benefits over IVT alone for all DMVO stroke patients. Further prospective randomized trials are needed to identify patient subgroups most likely to benefit from MT-IVT treatment in DMVO.

Therapeutic Potential of Glucagon-like Peptide-1 Receptor Agonists in Obstructive Sleep Apnea Syndrome Management: A Narrative Review.

Background: Obstructive Sleep Apnea (OSA) is a prevalent disorder characterized by repetitive upper airway obstructions during sleep, leading to intermittent hypoxia and sleep fragmentation. Current treatments, particularly Continuous Positive Airway Pressure (CPAP), face adherence challenges, necessitating novel therapeutic approaches. Methods: This review explores the potential of Glucagon-like Peptide-1 receptor agonists (GLP-1RA), commonly used for type 2 diabetes and obesity, in managing OSA. GLP-1RA promotes weight loss, enhances insulin sensitivity, and exhibits anti-inflammatory and neuroprotective properties, potentially addressing key pathophysiological aspects of OSA. Results: Emerging evidence suggests that these agents may reduce OSA severity by decreasing upper airway fat deposition and improving respiratory control. Clinical trials have demonstrated significant reductions in the Apnea-Hypopnea Index (AHI) and improvements in sleep quality with GLP-1 therapy. Conclusions: Future research should focus on elucidating the mechanisms underlying GLP-1 effects on OSAS, optimizing combination therapies, and identifying patient subgroups that may benefit the most. Integrating GLP-1RA into OSAS management could revolutionize treatment by addressing both the metabolic and respiratory components of the disorder, ultimately enhancing patient outcomes.

Measurement of Patients' Acceptable Symptom Levels and Priorities for Symptom Improvement in Advanced Prostate Cancer.

Limited research has evaluated the success criteria and priorities for symptom improvement of patients with cancer to inform patient-centered care. In this study, we adapted and tested a measure of these constructs, the Patient-Centered Outcomes Questionnaire (PCOQ), for patients with advanced prostate cancer. We compared acceptable symptom severity levels following symptom treatment across 10 symptoms and identified patient subgroups based on symptom importance. Patients with advanced prostate cancer (N = 99) participated in a one-time survey, which included a modified version of the PCOQ, standard symptom measures, and additional clinical characteristics. The modified PCOQ demonstrated construct validity through its correlations with related theoretical constructs. There was a moderate correlation between symptom severity and importance. Acceptable symptom severity levels were generally low, with sexual dysfunction having a higher acceptable severity than most other symptoms. Three patient subgroups were identified: (1) those who rated all symptoms as low in importance (n = 43); (2) those who rated all symptoms as moderately important (n = 33); and (3) those who rated all symptoms as highly important (n= 18). Subgroups were associated with functional status, fatigue, sleep problems, pain, and emotional distress. The modified PCOQ demonstrated preliminary evidence of construct validity. Patients generally considered low symptom severity to be acceptable, with variations across symptoms. Results suggest that symptom severity and importance are related but distinct aspects of the symptom experience in advanced prostate cancer. Patients' diverse priorities for symptom improvement point to the need for individualized treatment plans.

Identifying patients who benefit more from perioperative immunotherapy combinations for resectable non-small cell lung cancer based on clinical and molecular characteristics: a meta-analysis of randomized clinical trials.

This study aims to identify patient subgroups who benefit more from perioperative immunotherapy combined with chemotherapy (IO-CT) based on clinical and molecular characteristics in resectable non-small cell lung cancer (NSCLC). Randomized controlled trials (RCTs) on perioperative IO-CT were searched. Beneficial differences of IO-CT regimens across different patient subgroups were assessed by pooling trial-specific ratios in event-free survival (EFS), overall survival (OS), pathological complete response (pCR), and major pathological response (MPR). Six studies (n = 3003) involving five IO-CT regimens were included. Compared to CT alone, all IO-CT regimens significantly improved EFS, OS, MPR, and pCR, but increased toxicity. Toripa-chemo showed the best EFS and nivo-chemo showed the best OS. Patients with PD-L1 ≥ 1% had more EFS benefits compared to those with PD-L1 < 1% (HR [hazard ratio]: 1.55, 95% CI 1.17-2.04). Squamous NSCLC patients had significantly more pCR and MPR benefits than non-squamous NSCLC patients (pCR: OR [odds ratio] 0.68, 95% CI 0.49-0.95; MPR: OR 0.61, 95% CI 0.45-0.82). Former smokers had significantly higher pCR benefits than non-smokers (OR: 2.18; 95% CI 1.21-3.92). Additionally, OS benefit was significantly higher in patients < 65years compared to those ≥ 65years (HR ratio: 0.59, 95% CI 0.36-0.95). For MPR, males benefited significantly more from IO-CT compared to females (OR: 1.69, 95% CI 1.18-2.42). Perioperative IO-CT is more effective but more toxic than CT alone in resectable NSCLC. Patients with PD-L1 ≥ 1%, squamous NSCLC, a history of smoking, age < 65years and male gender may experience greater benefits from perioperative IO-CT.

Complexity in palliative care inpatients: Prevalence and relationship with the provision of care—a retrospective study

Context End-of-life palliative care aims to provide comprehensive care and can be marked by somatic, psychosocial, and spiritual distresses, requiring interdisciplinary care. However, interdisciplinary care is costly, and palliative care services, similar to all other medical services, are pressurized to be as cost-effective as possible. Objectives To describe the case complexity of palliative care inpatients, we evaluated possible correlations between complexity and the provision of care and identified complexity subgroups. Methods Patients (N = 222) hospitalized in a specialist palliative care unit in Switzerland were assessed for biopsychosocial complexity using INTERMED. Based on a chart review, INTERMED scores were determined at admission and at the end of hospitalization or at death. Descriptive statistics and Pearson’s correlation coefficients were used to estimate the association between biopsychosocial complexity and the amount and type of care provided. Principal component analysis (PCA) was conducted to explain variance and identify patient subgroups. Results Almost all patients (98.7%) qualified as complex, as indicated by INTERMED. Provision of care was positively correlated (r = 0.23, p = 0.0008) with INTERMED scores upon admission. The change in the INTERMED score during the stay correlated negatively with the provision of care (r = −0.27, p = 0.0001). PCA performed with two factors explained 49% of the total variance and identified two subgroups that differed in the INTERMED psychosocial-item scores. Conclusion Inpatients receiving specialist palliative care showed the highest complexity score of all populations assessed to date using INTERMED. Correlations between biopsychosocial complexity and care provided, and between care and decrease in complexity scores can be considered indicators of care efficiency. Patient subgroups with specific requirements (psychosocial burden) suggested that palliative care teams require specialist palliative care collaborators. Key message Palliative care provision correlates with case complexity and is effective.

Discrete Mathematics in Dynamic Network Analysis: Long-Term Efficacy Evaluation of Fotona Laser Therapy for Overactive Bladder Syndrome Using Clustering-Based Patient Subgroup Identification.

Dynamic network analysis, a state-of-the-art application of discrete mathematics, offers unprecedented insight into complex, time-evolving clinical data. This technical report demonstrates the value of evaluating the long-term efficacy of Fotona laser therapy (Fotona d.o.o., Ljubljana, Slovenia) in overactive bladder (OAB) syndrome. We analyzed data from 101 female patients aged ≥60 years who underwent Fotona laser treatment, including Vaginal Erbium Laser (VEL) and Urethral Erbium Laser (UEL), between 2020 and 2022. OAB symptom scores (OABSS) were collected at baseline (T0) and at six, 12, 18, and 24 months post treatment. Network graphs were constructed, representing patients as nodes, and symptom similarities as edges. Clustering techniques identify patient subgroups, whereas principal component analysis reduces dimensionality. The dynamic evolution of patient clusters was visualized through changes in average degree centrality over time. This approach revealed three distinct patient clusters with unique treatment response patterns. The results showed a progressive reduction in OABSS, with the total score decreasing by 2.82 ± 3.03 at 24 months. Our method provides novel visualization and analysis of complex longitudinal clinical data, offering insights into personalized treatment strategies for OAB. This report presents one of the first applications of discrete mathematics and dynamic network analysis to evaluate the long-term outcomes of Fotona laser therapy for OAB and introduces an innovative perspective for clinical decision-making in urogynecology.

Effect of adequacy of empirical antibiotic therapy for hospital-acquired bloodstream infections on intensive care unit patient prognosis: a causal inference approach using data from the Eurobact2 study

ObjectivesHospital-acquired bloodstream infections (HA-BSI) in the intensive care unit (ICU) are common life-threatening events. We aimed to investigate the association between early adequate antibiotic therapy and 28-day mortality in ICU patients who survived at least 1 day after the onset of HA-BSI. MethodsWe used individual data from a prospective, observational, multicentre, and intercontinental cohort study (Eurobact2). We included patients who were followed for ≥1 day and for whom time-to-appropriate treatment was available. We used an adjusted frailty Cox proportional-hazard model to assess the effect of time-to-treatment-adequacy on 28-day mortality. Infection- and patient-related variables identified as confounders by the Directed Acyclic Graph were used for adjustment. Adequate therapy within 24 hours was used for the primary analysis. Secondary analyses were performed for adequate therapy within 48 and 72 hours and for identified patient subgroups. ResultsAmong the 2418 patients included in 330 centres worldwide, 28-day mortality was 32.8% (n = 402/1226) in patients who were adequately treated within 24 hours after HA-BSI onset and 40% (n = 477/1192) in inadequately treated patients (p < 0.01). Adequacy within 24 hours was more common in young, immunosuppressed patients, and with HA-BSI due to Gram-negative pathogens. Antimicrobial adequacy was significantly associated with 28-day survival (aHR, 0.83; 95% CI, 0.72–0.96; p 0.01). The estimated population attributable fraction of 28-day mortality of inadequate therapy was 9.15% (95% CI, 1.9–16.2%). DiscussionIn patients with HA-BSI admitted to the ICU, the population attributable fraction of 28-day mortality of inadequate therapy within 24 hours was 9.15%. This estimate should be used when hypothesizing the possible benefit of any intervention aiming at reducing the time-to-appropriate antimicrobial therapy in HA-BSI.

Exploring the diverse therapeutic benefits of metformin: from anti-cancer to anti-inflammation and PCOS management

Background: Metformin is widely prescribed for type 2 diabetes mellitus and is recognized for its therapeutic benefits beyond glycemic control. This review summarizes current data on metformin's diverse roles in various therapeutic contexts, including treating polycystic ovarian syndrome (PCOS), anti-inflammatory effects, and cancer prevention. Method: This comprehensive examination highlights the multifaceted applications of metformin in modern medicine and its potential to enhance the treatment of inflammatory diseases, cancer, and reproductive disorders. Results and Discussion: Metformin's anti-inflammatory properties may benefit autoimmune disorders, neurological diseases, and cardiovascular illnesses. In women with PCOS, metformin aids in restoring menstrual regularity, inducing ovulation, and improving reproductive outcomes by enhancing insulin sensitivity, modulating ovarian function, and reducing hyperandrogenism. Additionally, emerging evidence suggests that metformin may reduce cancer incidence and mortality in diabetic individuals by modulating cellular metabolism, inducing apoptosis, and inhibiting tumor cell proliferation. Conclusion: Our review suggests promising evidence for metformin's role in cancer prevention, reducing inflammation, and managing PCOS. However, further research is required to identify patient subgroups that will benefit most from metformin therapy, elucidate its mechanisms of action, and optimize dosing regimens.

High expression of L-GILZ transcript variant 1 (GILZ TV 1) is associated with increased 30-day sepsis mortality, and a high expression ratio possibly contraindicates hydrocortisone administration

BackgroundSepsis presents a challenge due to its complex immune responses, where balance between inflammation and anti-inflammation is critical for survival. Glucocorticoid-induced leucine zipper (GILZ) is key protein in achieving this balance, suppressing inflammation and mediating glucocorticoid response. This study aims to investigate GILZ transcript variants in sepsis patients and explore their potential for patient stratification and optimizing glucocorticoid therapy.MethodsSepsis patients meeting the criteria outlined in Sepsis-3 were enrolled, and RNA was isolated from whole blood samples. Quantitative mRNA expression of GILZ transcript variants in both sepsis patient samples (n = 121) and the monocytic U937 cell line (n = 3), treated with hydrocortisone and lipopolysaccharides, was assessed using quantitative PCR (qPCR).ResultsElevated expression of GILZ transcript variant 1 (GILZ TV 1) serves as a marker for heightened 30-day mortality in septic patients. Increased levels of GILZ TV 1 within the initial day of sepsis onset are associated with a 2.2-[95% CI 1.2–4.3] fold rise in mortality, escalating to an 8.5-[95% CI 2.0–36.4] fold increase by day eight. GILZ TV1 expression is enhanced by glucocorticoids in cell culture but remains unaffected by inflammatory stimuli such as LPS. In septic patients, GILZ TV 1 expression increases over the course of sepsis and in response to hydrocortisone treatment. Furthermore, a high expression ratio of transcript variant 1 relative to all GILZ mRNA TVs correlates with a 2.3-fold higher mortality rate in patients receiving hydrocortisone treatment.ConclusionHigh expression of GILZ TV 1 is associated with a higher 30-day sepsis mortality rate. Moreover, a high expression ratio of GILZ TV 1 relative to all GILZ transcript variants is a parameter for identifying patient subgroups in which hydrocortisone may be contraindicated.

Frailty Explains Variation in Emergency Department Use for Older Veterans During the COVID-19 Pandemic.

Older adults were critically vulnerable to disruptions in health care during the COVID-19 pandemic, but it is not known if changes in ED utilization varied based on patient characteristics. Using a cohort of older Veterans, we examined changes in ED visit rates based on four characteristics of interest: age, race, area deprivation index, and frailty. Participants were aged ≥65, with ≥2 visits in primary or geriatric clinics between 02/02/2018-05/07/2019. An adjusted negative binomial regression model was constructed for each characteristic. We report mean counts of all ED visits by quarter for subgroups separately, and report rate ratios to compare ED visits in the first year of the COVID-19 pandemic to the year before. Patients with complete case data numbered 38,871. During the first two quarters, all subgroups had decreased ED visits, with more variation in the third and fourth quarters. The very highly frail, who had the highest mean estimated count of ED visits per person through both pre-COVID and COVID periods, also had a significant decrease in their ED visits during multiple quarters of the pandemic to a greater degree than other frailty subgroups. Stratifying older adults by frailty identified patient subgroups with the greatest variation in ED visits during COVID. Very highly frail patients warrant special attention to understand how variation in ED utilization affects patient outcomes.

Interpretable artificial intelligence to optimise use of imatinib after resection in patients with localised gastrointestinal stromal tumours: an observational cohort study

Current guidelines recommend use of adjuvant imatinib therapy for many patients with gastrointestinal stromal tumours (GISTs); however, its optimal treatment duration is unknown and some patient groups do not benefit from the therapy. We aimed to apply state-of-the-art, interpretable artificial intelligence (ie, predictions or prescription logic that can be easily understood) methods on real-world data to establish which groups of patients with GISTs should receive adjuvant imatinib, its optimal treatment duration, and the benefits conferred by this therapy. In this observational cohort study, we considered for inclusion all patients who underwent resection of primary, non-metastatic GISTs at the Memorial Sloan Kettering Cancer Center (MSKCC; New York, NY, USA) between Oct 1, 1982, and Dec 31, 2017, and who were classified as intermediate or high risk according to the Armed Forces Institute of Pathology Miettinen criteria and had complete follow-up data with no missing entries. A counterfactual random forest model, which used predictors of recurrence (mitotic count, tumour size, and tumour site) and imatinib duration to infer the probability of recurrence at 7 years for a given patient under each duration of imatinib treatment, was trained in the MSKCC cohort. Optimal policy trees (OPTs), a state-of-the-art interpretable AI-based method, were used to read the counterfactual random forest model by training a decision tree with the counterfactual predictions. The OPT recommendations were externally validated in two cohorts of patients from Poland (the Polish Clinical GIST Registry), who underwent GIST resection between Dec 1, 1981, and Dec 31, 2011, and from Spain (the Spanish Group for Research in Sarcomas), who underwent resection between Oct 1, 1987, and Jan 30, 2011. Among 1007 patients who underwent GIST surgery in MSKCC, 117 were included in the internal cohort; for the external cohorts, the Polish cohort comprised 363 patients and the Spanish cohort comprised 239 patients. The OPT did not recommend imatinib for patients with GISTs of gastric origin measuring less than 15·9 cm with a mitotic count of less than 11·5 mitoses per 5 mm2 or for those with small GISTs (<5·4 cm) of any site with a count of less than 11·5 mitoses per 5 mm2. In this cohort, the OPT cutoffs had a sensitivity of 92·7% (95% CI 82·4-98·0) and a specificity of 33·9% (22·3-47·0). The application of these cutoffs in the two external cohorts would have spared 38 (29%) of 131 patients in the Spanish cohort and 44 (35%) of 126 patients in the Polish cohort from unnecessary treatment with imatinib. Meanwhile, the risk of undertreating patients in these cohorts was minimal (sensitivity 95·4% [95% CI 89·5-98·5] in the Spanish cohort and 92·4% [88·3-95·4] in the Polish cohort). The OPT tested 33 different durations of imatinib treatment (<5 years) and found that 5 years of treatment conferred the most benefit. If the identified patient subgroups were applied in clinical practice, as many as a third of the current cohort of candidates who do not benefit from adjuvant imatinib would be encouraged to not receive imatinib, subsequently avoiding unnecessary toxicity on patients and financial strain on health-care systems. Our finding that 5 years is the optimal duration of imatinib treatment could be the best source of evidence to inform clinical practice until 2028, when a randomised controlled trial with the same aims is expected to report its findings. National Cancer Institute.

Identifying Subgroups with Differential Responses to Amiodarone among Cardiac Arrest Patients with a Shockable Rhythm at Hospital Arrival using the Machine Learning Approach.

There are few reports of studies on the differential effects of amiodarone among out-of-hospital cardiac arrest (OHCA) patients with a shockable rhythm at hospital arrival. The present study aimed to investigate the clinical heterogeneity of OHCA patients with a shockable rhythm upon hospital arrival and to identify subgroups with differential responses to amiodarone, using a machine learning approach. We used the Japanese nationwide OHCA registry of the Japanese Association for Acute Medicine for this study; data from OHCA patients with a shockable rhythm at hospital arrival were included in the analyses. The primary outcome was a favorable neurological outcome at 30 days. We developed a scoring system by the weighting method with logistic likelihood loss to identify patient subgroups showing differential effects of amiodarone from the point of view of the neurological outcome and survival at 30 days. Among the 68,111 cases of OHCA in the registry, the data of 2333 OHCA patients with an initial shockable rhythm at hospital arrival were analyzed. The developed score identified higher age, longer interval between the call to the emergency medical service and hospital arrival, absence of a "witness", no defibrillation prior to hospital arrival, hypothermia at hospital arrival, and pre-hospital epinephrine administration as variables that were significantly associated with a beneficial effect of amiodarone. Based on the results of the developed scoring system, 47% (1107/2333) of the patients were considered to greatly benefit from amiodarone administration, whereas 53% (1226/2333) of patients were considered to not benefit from amiodarone administration. The effect of amiodarone on the neurological outcome at 30 days varied significantly among the subgroups identified by the developed score ( : 1.07 [95% confidence interval (CI): 0.99-1.13], p = 0.005). We successfully developed a model that could discriminate between OHCA patients with an initial shockable rhythm at hospital arrival who would benefit or not benefit from the administration of amiodarone in terms of the neurological outcome at 30 days. There was clinical heterogeneity among OHCA patients with a shockable rhythm in terms of their response to amiodarone.

Exploring the workplace factors and their influence on the employment outcomes for people with multiple sclerosis

BackgroundHigh unemployment rate of people with multiple sclerosis (PwMS) is associated with substantial economic costs. Whilst the impact of MS symptoms and other disease-related factors on employment outcomes of PwMS has been assessed, limited evidence exists on the impacts of workplace factors. ObjectiveTo investigate the most common individual and group workplace factors associated with unemployment or a perceived risk of unemployment in PwMS, and to identify patient subgroups that are more susceptible to changes in employment status due to such factors. MethodsData from the Australian MS Longitudinal Study (AMSLS) on employment status and workplace factors were used. Fifteen workplace factors were classified under four groups: organisational, commuting, moving around at work, and equipment usage factors. Participants answered ‘Yes’ to each factor if it related to their unemployment and/or perceived risk of becoming unemployed and a group factor was considered “Yes” if at least one individual factor within it was answered as “Yes”. The proportions of “Yes” responses were calculated for both individual and group factors. Total number of individual factors was calculated and descriptive analyses and ordered logistic regression were used to summarize the total number of factors affecting each participant, and their association with participants’ occupations, sex, disability severity and disease duration. ResultsCommon workplace factors influencing employment were organisational (39.8 % perceived risk, 44.0 % lost employment), commuting (28.9 % perceived risk) and equipment usage difficulty (30.9 % lost employment). Common individual factors included inflexible working conditions, lack of suitable work, commuting difficulties, architectural barriers, and requirement to stand for long periods to use equipment. Professionals, blue-collar workers, and those with moderate/severe disability were more likely to report a higher number of workplace factors risking their employment. ConclusionsWorkplace factors undermine PwMS employment, with variations among subgroups based on occupation and disability severity. Understanding these barriers is crucial for supporting PwMS in the workforce.