Communications Medicine

High-dimensional medical datasets present challenges in feature selection, where traditional methods often prioritize spurious correlations over causally relevant variables, compromising model interpretability and clinical utility. We introduce CausalDRIFT, a causal feature selection algorithm grounded in the Frisch-Waugh-Lovell theorem and Double Machine Learning, which estimates the Average Treatment Effect (ATE) of each feature on clinical outcomes while adjusting for confounders. We evaluate...

The purpose of this paper is to present a detailed investigation of the advantages of employing GraphLIME (Local Interpretable Model Explanations for Graph Neural Networks) for the trustworthy prediction of diabetes mellitus. Our pursuit involves identifying the strengths of GraphLIME combined with the attention-mechanism over the standard coupling of deep learning neural networks with the original LIME method. The system build this way, provided us a proficient method for extracting the most re...

Multiplex immunofluorescence (mIF) imaging can provide comprehensive quantitative and spatial information for multiple immune markers for tumour immunoprofiling. However, application at scale to clinical trial samples sourced from multiple institutions is challenging due to pre-analytical heterogeneity. This study reports an analytical approach to the largest multiparameter immunoprofiling study of clinical trial samples to date. We analysed 12,592 tissue microarray (TMA) spots from 3,545 colore...

ImportanceSodium glucose cotransporter 2 inhibitors (SGLT2i), glucagon-like peptide-1 receptor analogues (GLP1ra) and dipeptidyl peptidase-4 inhibitors (DPP4i) improve hyperglycaemia and, in the case of SGLT2i and GLP1ra, reduce the risk of major adverse cardiovascular events (MACE) in type 2 diabetes. It is not clear whether efficacy varies by age or sex. ObjectiveAssess whether age or sex are associated with differences in efficacy of SGL2i, GLP1ra and DPP4i. Data sourcesMedline, Embase and ...

Cancer remains one of the most significant global health challenges. De-spite advances in treatment, early detection remains a critical concern. The increasing availability of Electronic Health Records (EHR) offers a unique opportunity to enhance our understanding of patient health trajectories and develop more accurate risk prediction models. However, the complexity and heterogeneity of EHR data pose significant challenges for analysis and modeling. Over the years, a range of models, from tradi...

Due to complexity of advanced epithelial cancers, it is necessary to implement patient specific combination therapies if we are to markedly improve patient outcomes. However, our ability to select and implement patient specific combination therapies based on dynamic molecular changes in the tumor and tumor ecosystem in response to therapy remains extremely limited. In a pilot study, we evaluated the feasibility of real-time deep analysis of serial tumor samples from triple negative breast cancer...

BackgroundInter-individual variability in lipid response to statin therapy poses a major challenge in cardiovascular risk reduction, particularly among patients with type 2 diabetes mellitus (T2DM), who exhibit complex dyslipidemia and elevated cardiovascular risk. While randomized trials provide population-level estimates of treatment efficacy, individualized prediction of lipid changes, and corresponding uncertainty, remains limited. Using rich clinical data from the Action to Control Cardiova...

Accurately predicting patient clinical outcomes is a complex task that requires integrating diverse factors, including individual characteristics, treatment histories, and environmental influences. This challenge is further exacerbated by missing data and inconsistent data quality, which often hinder the effectiveness of traditional single-task learning (STL) models. Multi-Task Learning (MTL) has emerged as a promising paradigm to address these limitations by jointly modeling related prediction ...

BackgroundBeta-cell monogenic forms of diabetes are the area of diabetes care with the strongest support for precision medicine. We reviewed treatment of hyperglycemia in GCK-related hyperglycemia, HNF1A- HNF4A- and HNF1B-diabetes, Mitochondrial diabetes (MD) due to m.3243A>G variant, 6q24-transient neonatal diabetes (TND) and SLC19A2-diabetes. MethodsSystematic reviews with data from PubMed, MEDLINE and Embase were performed for the different subtypes. Individual and group level data was extra...

There is a problem of clinical trial failure, as each new drug should surpass the effectiveness of existing treatment regimens, which becomes increasingly challenging over time. Another significant issue is treating patients who have developed resistance to the current therapies. Essentially, the use of drug combinations or off-label drug use, where the indication does not match the diagnosis, is akin to an experiment, as there is insufficient data on which drug or combination to use. This wor...

Because humans age at different rates, a persons physical appearance may yield insights into their biological age and physiological health more reliably than their chronological age. In medicine, however, appearance is incorporated into medical judgments in a subjective and non-standardized fashion. In this study, we developed and validated FaceAge, a deep learning system to estimate biological age from easily obtainable and low-cost face photographs. FaceAge was trained on data from 58,851 heal...

The increasing availability of electronic health records (EHRs) provides opportunities to apply machine learning (ML) methods in support of clinical decision-making. The temporal nature of laboratory values in EHR data records makes them particularly suitable for temporal deep learning (DL) architectures that model patient trajectories over time. However, despite this potential, the application of temporal DL models to longitudinal laboratory data has largely been limited to intensive care unit ...

Clinical research relies on high-quality patient data, however, obtaining big data sets is costly and access to existing data is often hindered by privacy and regulatory concerns. Synthetic data generation holds the promise of effectively bypassing these boundaries allowing for simplified data accessibility and the prospect of synthetic control cohorts. We employed two different methodologies of generative artificial intelligence - CTAB-GAN+ and normalizing flows (NFlow) - to synthesize patient ...

Reference intervals (RI) are the best-established methodology used for the interpretation of numerical clinical level data in healthcare and clinical practice. As the test results are interpreted by comparing with the (population-derived) reference intervals, the quality of the calculation and implementation of reference intervals play a major role in decision-making process at the subject level. Here we describe the IRIS workflow to compute Individual Reference Intervals (IRI) based on multiple...

IntroductionThe Nocturnal Glycemic Stability Index (NGSI) is a novel quantitative metric designed to comprehensively assess overnight glucose stability by integrating amplitude, frequency, and temporal patterns of glycemic fluctuations. NGSI addresses this gap by providing a multidimensional, sensitive measure tailored to the nocturnal period, enhancing risk stratification and therapeutic optimization in diabetes management. ObjectiveTo develop and validate the NGSI, a novel metric designed to ...

BackgroundType 1 diabetes (T1D) results from immune-mediated destruction of insulin-producing beta cells. Efforts to prevent T1D have focused on modulating immune responses and supporting beta cell health; however, heterogeneity in disease progression and responses to therapies have made these efforts difficult to translate to clinical practice, highlighting the need for precision medicine approaches to T1D prevention. MethodsTo understand the current state of knowledge regarding precision appr...

Alterations in sulfated glycans are associated with several pathological conditions, including cancer. However, analysis of sulfated glycans poses challenges, making the investigation of sulfated glycan profiles a topic of significant interest in the search for novel biomarkers for early BC detection. We used a glycoblotting-based sulphoglycomics workflow to examine sulfated N-glycans present in the serum of Ethiopian patients with BC. Seven mono-sulfated glycans were significantly upregulated i...

Questionnaires that capture patient-reported symptomatology provide low-cost but potentially high-value data for the de novo discovery of disease phenotype, severity, and responsiveness to intervention groupings within an umbrella condition. The availability of comprehensive electronic health records (EHRs) has nonetheless overshadowed the use of questionnaires data for symptom analysis in the context of COVID-19. We analyzed de-identified questionnaires from post-acute COVID-19 cohorts at the U...

Treatment effect estimation (TEE) refers to the estimation of causal effects, and it aims to compare the difference among treatment strategies on important outcomes. Current machine learning based methods are mainly trained on labeled data with specific treatments or outcomes of interest, which can be sub-optimal if the labeled data are limited. In this paper, we propose a novel transformer-based pre-training and fine-tuning framework called CURE for TEE from observational data. CURE is pre-trai...

ContextIdentifying Maturity-Onset Diabetes of the Young (MODY) in patients with diabetes is essential because treatment differs significantly from other forms of diabetes. We identified patients with MODY gene variants and evaluated their clinical characteristics and responses to treatment. Evidence AcquisitionWe identified 106 patients with genetic MODY variants. Demographics, islet autoantibodies at diabetes diagnosis, co-morbidities, and response to treatment by genetic variant were evaluate...