Explore the vast range of titles available.

Visceral Leishmaniasis (VL), also known as Kala-Azar, poses a significant global public health challenge and is a neglected disease, with relapses and treatment failures leading to increased morbidity and mortality. This study introduces an explainable machine learning approach to predict VL relapse and identify critical risk factors, thereby aiding patient monitoring and treatment strategies. Leveraging data from a follow-up study of 571 patients, the survival machine learning models are applied, including Random Survival Forest (RSF), Survival Support Vector Machine (SSVM), and eXtreme Gradient Boosting (XGBoost), for relapse prediction. The results demonstrated that RSF, with a C-index of 0.85, outperformed the conventional Cox Proportional Hazard (CPH) model (C-index 0.8), offering improved prediction capabilities by capturing non-linear relationships and variable interactions. To address the lack of transparency (in terms of feature importance) in Machine Learning (ML) models, the SHapley Additive exPlanation (SHAP) method is employed, which enhances model interpretability (feature importance) through visual insights. SHAP dependence plots allowed the healthcare professionals to evaluate which factors encourage the occurrence of the relapse. A statistically significant relationship between HIV co-infection (HR=3.92, 95% CI=2.03–7.58) and VL relapse was identified through -2 log-likelihood ratio and chi-square tests. These results indicate the promise of explainable artificial intelligence (XAI) for making clinical decisions and remedying recurrences in VL.

Sleep disruption is a common precursor to deterioration and relapse in people living with psychotic disorders. Understanding the temporal relationship between sleep and psychopathology is important for identifying and developing interventions which target key variables that contribute to relapse. We used a purpose-built digital platform to sample self-reported sleep and psychopathology variables over 1 year, in 36 individuals with schizophrenia. Once-daily measures of sleep duration and sleep quality, and fluctuations in psychopathology (positive and negative affect, cognition and psychotic symptoms) were captured. We examined the temporal relationship between these variables using the Differential Time-Varying Effect (DTVEM) hybrid exploratory-confirmatory model. Poorer sleep quality and shorter sleep duration maximally predicted deterioration in psychosis symptoms over the subsequent 1-8 and 1-12 days, respectively. These relationships were also mediated by negative affect and cognitive symptoms. Psychopathology variables also predicted sleep quality, but not sleep duration, and the effect sizes were smaller and of shorter lag duration. Reduced sleep duration and poorer sleep quality anticipate the exacerbation of psychotic symptoms by approximately 1-2 weeks, and negative affect and cognitive symptoms mediate this relationship. We also observed a reciprocal relationship that was of shorter duration and smaller magnitude. Sleep disturbance may play a causal role in symptom exacerbation and relapse, and represents an important and tractable target for intervention. It warrants greater attention as an early warning sign of deterioration, and low-burden, user-friendly digital tools may play a role in its early detection.

Abstract Background and Hypothesis Digital remote monitoring (DRM) captures service users’ health-related data remotely using devices such as smartphones and wearables. Data can be analyzed using advanced statistical methods (eg, machine learning) and shared with clinicians to aid assessment of people with psychosis’ mental health, enabling timely intervention. Such methods show promise in detecting early signs of psychosis relapse. However, little is known about clinicians’ views on the use of DRM for psychosis. This study explores multi-disciplinary staff perspectives on using DRM in practice. Study Design Fifty-nine mental health professionals were interviewed about their views on DRM in psychosis care. Interviews were analyzed using reflexive thematic analysis. Study Results: Five overarching themes were developed, each with subthemes: (1) the perceived value of digital remote monitoring; (2) clinicians’ trust in digital remote monitoring (3 subthemes); (3) service user factors (2 subthemes); (4) the technology-service user-clinician interface (2 subthemes); and (5) organizational context (2 subthemes). Conclusions Participants saw the value of using DRM to detect early signs of relapse and to encourage service user self-reflection on symptoms. However, the accuracy of data collected, the impact of remote monitoring on therapeutic relationships, data privacy, and workload, responsibility and resource implications were key concerns. Policies and guidelines outlining clinicians’ roles in relation to DRM and comprehensive training on its use are essential to support its implementation in practice. Further evaluation regarding the impact of digital remote monitoring on service user outcomes, therapeutic relationships, clinical workflows, and service costs is needed.

Circulating tumor DNA (ctDNA) has demonstrated great potential as a noninvasive biomarker to assess minimal residual disease (MRD) and profile tumor genotypes in patients with non‐small‐cell lung cancer (NSCLC). However, little is known about its dynamics during and after tumor resection, or its potential for predicting clinical outcomes. Here, we applied a targeted‐capture high‐throughput sequencing approach to profile ctDNA at various disease milestones and assessed its predictive value in patients with early‐stage and locally advanced NSCLC. We prospectively enrolled 33 consecutive patients with stage IA to IIIB NSCLC undergoing curative‐intent tumor resection (median follow‐up: 26.2 months). From 21 patients, we serially collected 96 plasma samples before surgery, during surgery, 1–2 weeks postsurgery, and during follow‐up. Deep next‐generation sequencing using unique molecular identifiers was performed to identify and quantify tumor‐specific mutations in ctDNA. Twelve patients (57%) had detectable mutations in ctDNA before tumor resection. Both ctDNA detection rates and ctDNA concentrations were significantly higher in plasma obtained during surgery compared with presurgical specimens (57% versus 19% ctDNA detection rate, and 12.47 versus 6.64 ng·mL−1, respectively). Four patients (19%) remained ctDNA‐positive at 1–2 weeks after surgery, with all of them (100%) experiencing disease progression at later time points. In contrast, only 4 out of 12 ctDNA‐negative patients (33%) after surgery experienced relapse during follow‐up. Positive ctDNA in early postoperative plasma samples was associated with shorter progression‐free survival (P = 0.013) and overall survival (P = 0.004). Our findings suggest that, in early‐stage and locally advanced NSCLC, intraoperative plasma sampling results in high ctDNA detection rates and that ctDNA positivity early after resection identifies patients at risk for relapse. ctDNA profiling in plasma revealed higher levels and detection rates of ctDNA during tumor resection as compared to pretreatment time points in patients with early‐stage or locally advanced NSCLC. Moreover, patients testing positive for ctDNA immediately after tumor resection had worse clinical outcomes than patients with undetectable ctDNA. Our research highlights the role of ctDNA assessment for guiding treatment in patients with respectable NSCLC.

Relapse of psychotic disorders occurs commonly even after appropriate treatment. Digital phenotyping becomes essential to achieve remote monitoring for mental conditions. We applied a personalized approach using neural-network-based anomaly detection and clustering to predict relapse for patients with psychotic disorders. We used a dataset provided by e-Prevention grand challenge (SPGC), containing physiological signals for 10 patients monitored over 2.5 years (relapse events: 560 vs. non-relapse events: 2139). We created 2-dimensional multivariate time-series profiles containing activity and heart rate variability metrics, extracted latent features via convolutional autoencoders, and identified relapse clusters. Our model showed promising results compared to the 1 st place of SPGC (area under precision-recall curve = 0.711 vs. 0.651, area under receiver operating curve = 0.633 vs. 0.647, harmonic mean = 0.672 vs. 0.649) and added to existing evidence of data collected during sleep being more informative in detecting relapse. Our study demonstrates the potential of unsupervised learning in identifying abnormal behavioral changes in patients with psychotic disorders using objective measures derived from granular, long-term biosignals collected by unobstructive wearables. It contributes to the first step towards determining relapse-related biomarkers that could improve predictions and enable timely interventions to enhance patients’ quality of life.

Quantification of minimal residual disease (MRD) following allogeneic hematopoietic cell transplantation (allo-HCT) predicts post-transplant relapse in patients with chronic lymphocytic leukemia (CLL). We utilized an MRD-quantification method that amplifies immunoglobulin heavy chain (IGH) loci using consensus V and J segment primers followed by high-throughput sequencing (HTS), enabling quantification with a detection limit of one CLL cell per million mononuclear cells. Using this IGH–HTS approach, we analyzed MRD patterns in over 400 samples from 40 CLL patients who underwent reduced-intensity allo-HCT. Nine patients relapsed within 12 months post-HCT. Of the 31 patients in remission at 12 months post-HCT, disease-free survival was 86% in patients with MRD <10 −4 and 20% in those with MRD ⩾10 −4 (relapse hazard ratio (HR) 9.0; 95% confidence interval (CI) 2.5–32; P <0.0001), with median follow-up of 36 months. Additionally, MRD predicted relapse at other time points, including 9, 18 and 24 months post-HCT. MRD doubling time <12 months with disease burden ⩾10 −5 was associated with relapse within 12 months of MRD assessment in 50% of patients, and within 24 months in 90% of patients. This IGH–HTS method may facilitate routine MRD quantification in clinical trials.

Background Age and sex were shown to influence multiple sclerosis (MS) relapse activity in the 1990s. Whether relapse risk factors are the same with new treatment paradigms is unclear. We evaluate predictors of clinical relapse following the first clinic visit (FV) across different treatment eras in a large, retrospective cohort. Methods Adults with clinically isolated syndrome or relapsing-onset MS were divided into cohorts with FV at the Brigham Multiple Sclerosis Center (Boston, MA) from 1997 to 2010 (“early”) and 2010 to 2020 (“recent”). Risk factors for relapse in 3 years after the FV were assessed for each cohort using multivariable logistic regression, and interaction terms were evaluated. Results 2192 patients were included (early: 1536; recent: 656). Younger age, female sex, relapsing-remitting disease, more prior relapses, and the use of platform therapy were associated with a future relapse in the early cohort. Age, family history of MS, and platform therapy were predictive in the recent cohort. Interaction terms for all variables were not significant. Model accuracy was similar across treatment eras. Conclusions Predictors of future relapse did not differ substantially across treatment eras. Younger age and the use of less effective therapies were strong risk factors at FV. However, significant heterogeneity exists in individuals’ relapse risk.

Myelin oligodendrocyte glycoprotein antibody-associated disease (MOGAD) is an autoimmune disorder of the central nervous system, characterized by seropositive MOG antibodies. MOGAD can present with a monophasic or relapsing course, where repeated relapses may lead to a worse prognosis and increased disability. Currently, little is known about the risk factors for predicting MOGAD relapse in a short period, and few established prediction models exist, posing a challenge to timely and personalized clinical diagnosis and treatment. From April 2018 to December 2023, we enrolled 88 patients diagnosed with MOGAD at the First Hospital of Shanxi Medical University and collected basic clinical data. The data were randomly divided into a training cohort (80%) and a validation cohort (20%). Univariate logistic regression, least absolute shrinkage and selection operator (LASSO) regression and multivariate logistic regression were used to identify independent risk factors for 1-year relapse. A prediction model was constructed, and a nomogram was developed. The receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were used to evaluate and internally validate model performance. Among 88 MOGAD patients, 29 relapsed within 1 year of onset (33%). A total of 4 independent risk factors for predicting relapse were identified: female sex ( =0.040), cortical encephalitis phenotype ( =0.032), serum MOG antibody titer ≥1:32 ( =0.007), and immunosuppressive therapy after the first onset ( = 0.045). The area under curve (AUC) value of the nomogram prediction model constructed with these four factors was 0.866 in the training cohort, and 0.864 in the validation cohort. The cutoff value of the total nomogram score was 140 points, distinguishing the low relapse risk group from the high relapse risk group ( < 0.001). The calibration curve demonstrated high consistency in prediction, and the DCA showed excellent net benefit in the prediction model. Tested by ROC curve, calibration curve, and DCA, the nomogram model also demonstrates significant value in predicting MOGAD relapse within 2 years. The nomogram model we developed can help accurately predict the relapse risk of MOGAD patients within one year of onset and assist clinicians in making treatment decisions to reduce the chance of relapse.

This research attempts to assess the prognostic significance of serum/glucocorticoid-regulated kinase 1 (SGK1) expression in peripheral blood mononuclear cells (PBMCs) of multiple myeloma (MM) individuals undergoing autologous hematopoietic stem cell transplantation (AHSCT) compared to traditional minimal residual disease (MRD) and serum free light chain (sFLC) assessments. A single-center, retrospective study was carried out involving 85 MM individuals who underwent AHSCT. SGK1 gene expression was measured in PBMCs using quantitative real-time PCR (qRT-PCR) at baseline and at defined post-transplant intervals. Concurrently, MRD status was assessed using multiparameter flow cytometry (MFC) and sFLC levels were measured. Individuals were seen for a median of 36 months post-transplant. ROC curve analysis was employed to assess the predictive power of SGK1 expression, MRD, and sFLC for relapse. SGK1 gene expression demonstrated dynamic changes in AHSCT, with levels decreasing in all risk groups, reflecting reductions in disease burden. Quantitative analysis showed that the predictive efficacy of SGK1, utilizing the area under the receiver operating characteristic (ROC) curve (area under the curve [AUC]), was highly comparable to that of MRD assessments, with SGK1 achieving an AUC of 0.86, closely approximating the MRD AUC of 0.88. Persistent high SGK1 expression, particularly discernible in individuals harboring high-risk (HR) cytogenetic profiles, was considerably associated with an elevated risk of relapse (hazard ratio for high vs. low SGK1 expression: 2.7; 95% CI: 1.4-5.3;   < 0.01). SGK1 gene expression in PBMCs serves as a promising, minimally invasive biomarker for relapse prediction in MM individuals undergoing AHSCT.

Aim The purpose of this research study was to develop and validate a gene signature based on peripheral blood mononuclear cells (PBMCs) for predicting the time to the next relapse in multiple sclerosis (MS). Methods The GSE15245 dataset ( N  = 94) was divided into a training set ( N  = 65) and a testing set ( N  = 29). First, the training set was analyzed using weighted gene co-expression network analysis (WGCNA) to identify key modules that were highly correlated with the timing of the next acute relapse. Subsequently, the hub genes within these key modules were subjected to univariate Cox regression analysis, and genes related to the recurrence time of MS were identified. The least absolute shrinkage and selection operator (LASSO) Cox regression was used to refine the extraction further. Then, the gene signatures were constructed using multivariate Cox regression. The efficacy of the model that was based on the training set database was evaluated using receiver operating characteristic (ROC) curves and validated using an independent testing set. Additionally, gene signatures were also validated for differential expression using an external independent dataset, GSE21942 ( N  = 29), along with experimental verification. Result Two key modules were identified with WGCNA. Univariate Cox regression analysis yielded 30 genes related to the relapse time of MS from these two modules, and then LASSO regression analysis further refined the selection to four genes, namely, BLK, P2RX5, GP1BA, and PF4. These four genes were used within the training dataset to build a Cox regression model, and this showed high prediction performance in the training as well as the testing datasets. Both external dataset analysis and experimental validation corroborated the differential expression of BLK and P2RX5 in patients with MS. Conclusion BLK, P2RX5, GP1BA, and PF4 emerge as potential predictors of future disease activity in individuals with MS.