SEARCH · PubMed Health

Results for “machine learning algorithms”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 181 records · Page 10Linked to original sources

PubMed2026

Diagnostic performance of machine learning models versus established risk stratification for intracranial aneurysm rupture: a systematic review and bivariate meta-analysis.

BACKGROUND: Machine learning (ML) models have been proposed to improve the discrimination of intracranial aneurysm rupture status beyond established clinical risk stratification tools. However, reported performance is heterogeneous and the relative contribution of model architecture and feature dominance remains unclear. METHODS: We performed a Preferred Reporting Items for Systematic Reviews and Meta-Analyses-diagnostic test accuracy systematic review and diagnostic meta-analysis of studies evaluating ML models for intracranial aneurysm rupture discrimination. PubMed, Embase and CENTRAL were searched to February 2026. Sensitivity and specificity were pooled using a bivariate random-effects model, with summary receiver operating characteristic curves generated across training, internal testing and external validation datasets. Models were compared with regression-based approaches and Population, Hypertension, Age, Size of aneurysm, Earlier subarachnoid haemorrhage, Site of aneurysm (PHASES) scores. Subgroup and meta-regression analyses explored associations between algorithm family and feature domain. RESULTS: Sixty-two retrospective cohorts (29 709 patients 209 models) met the inclusion criteria. In training datasets, pooled sensitivity and specificity for ML were 0.81 (95% CI 0.75 to 0.85) and 0.83 (0.80-0.86), with an area under the curve (AUC) of 0.878, exceeding PHASES (AUC 0.667). In testing datasets, ML retained higher discrimination (AUC 0.837) than regression models (0.806) and PHASES (0.646). In external validation, sensitivity was preserved (0.82), but specificity declined (0.66). Deep learning demonstrated the highest AUCs (training and testing). Incorporation of haemodynamic or radiomic features improved pooled discrimination relative to morphology alone. Evidence of small-study effects and mostly unclear Prediction Model Risk Of Bias Assessment Tool ratings were observed. CONCLUSIONS: ML approaches demonstrate higher pooled discrimination for aneurysm rupture status than conventional risk scores in retrospective datasets, but reduced external validation specificity and heterogeneity limit confidence for clinical translation. Prospective, externally validated, calibrated models are required before integration into routine cerebrovascular risk stratification.

Humans↗

PubMed2026

Multi-Omics Integration Identifies a Five-Gene Metabolic Signature With Experimental Validation in Clear Cell Renal Cell Carcinoma.

BACKGROUND: Clear cell renal cell carcinoma (ccRCC) is hallmarked by profound metabolic reprogramming; however, its intricate crosstalk with the tumor immune microenvironment (TIME) and its clinical ramifications remain inadequately elucidated. This study aims to systematically decipher the metabolic-immune interplay in ccRCC through multi-omics integration, with the goal of identifying robust prognostic biomarkers and actionable therapeutic vulnerabilities. AIMS: This study aims to systematically decipher the metabolic-immune interplay in clear cell renal cell carcinoma (ccRCC) through multi‑omics integration, and to identify robust prognostic biomarkers and actionable therapeutic vulnerabilities that can inform precision risk stratification and individualized treatment strategies. METHODS: We integrated bulk transcriptomic, genomic, and clinical data from multiple ccRCC cohorts. Differential expression and functional enrichment analyses were performed to characterize metabolic pathway alterations. Mendelian randomization (MR) was employed to infer causal relationships between metabolic disorders and ccRCC risk. A machine learning-based prognostic framework, incorporating SHAP (SHapley Additive exPlanations) for feature interpretability, was constructed and rigorously validated. TIME heterogeneity was dissected using deconvolution algorithms, while drug sensitivity, tumor mutation burden (TMB), and TIDE scores were utilized to assess therapeutic responses and immune evasion. Candidate gene function was evaluated through in vitro gain- and loss-of-function assays, with expression validated via TCGA, HPA, western blot, and qRT-PCR. RESULTS: Enrichment analysis identified coordinated dysregulation in lipid metabolism, energy homeostasis, and hypoxia response pathways. MR analysis confirmed lipid metabolism disorders as a causal risk factor for ccRCC. Our machine-learning model, centered on five core SHAP-identified features (SUCLA2, ACAT1, PC, SUCLG1, and HMGCS2), demonstrated superior predictive accuracy over conventional clinical staging. Immune profiling unveiled dichotomous TIME states: the low-risk group retained active immune surveillance, whereas the high-risk group was enriched with immunosuppressive subsets. Drug sensitivity screening pinpointed LY2109761 and carmustine as high-risk-specific candidate agents. Furthermore, TMB and TIDE analyses stratified high-risk patients displaying genomic instability and immune evasion phenotypes. Functionally, SUCLA2 knockdown significantly enhanced ccRCC cell proliferation and invasion, while its overexpression suppressed these malignant phenotypes, corroborating its tumor-suppressive role. Expression patterns of the hub genes were consistently validated across multi-level datasets and experimental assays. CONCLUSION: This study establishes a precision oncology framework for ccRCC by functionally linking metabolic biomarkers, immunophenotypes, and stratified therapeutic strategies. Importantly, we identify SUCLA2 as a potential functional tumor suppressor and a promising target for further mechanistic and translational investigation.

Humans↗

PubMed2026

From Variability to Consensus: Rescoring Harmonizes Peptide Identification across Diverse Search Engines and Data Sets.

Peptide-spectrum match (PSM) rescoring has become standard in proteomics workflows, improving peptide identification accuracy across diverse search engines. Despite the availability of multiple rescoring strategies, systematic comparisons spanning several search engines, data sets, and database configurations remain limited. Here, we benchmarked seven publicly available search engines, evaluating standard target-decoy-based false discovery rate (FDR) estimation alongside Percolator, MS2Rescore, and Oktoberfest across four data sets acquired on different mass spectrometry platforms in data-dependent mode and searched against protein databases of varying size and composition. Rescoring substantially increased identification consensus and reduced variability between search engines, with prediction-based approaches yielding the largest gains. While database size had limited impact for human data sets, it significantly affected identification rates on a metaproteomic data set. Entrapment-based evaluation indicated generally adequate FDR control across methods, although prediction-based rescoring exhibited a higher tendency toward FDR underestimation in specific configurations. Overall, advanced rescoring strategies harmonize peptide identification outcomes across search engines, thereby enhancing robustness and comparability in proteomics analyses. However, careful feature selection and appropriate database choice remain essential to ensure reliable FDR control and optimal performance across diverse experimental settings.

Search Engine↗

PubMed2026

Comparison of classic statistical methods and machine learning approaches to classify readiness.

MOTIVATION: Predicting physical and cognitive readiness in warfighters is critical for mission success. These predictions can be improved by identifying key biomarkers using multiple omics modalities. The MASTR-E study conducted by McKetney and colleagues is one of the most comprehensive multi-omics studies of saliva samples collected from warfighters, which also applied classic linear statistical (CLS) techniques to discover key biomarkers of readiness. Aligning with McKetney et al.'s assumptions, we operationalize readiness as a binary proxy, where pre-mission samples are labeled as "ready" to reflect a rested, unstressed physiological baseline, while post-mission samples are labeled "not ready" to reflect cumulative physical and cognitive load from the mission. As such, readiness here is not a direct biological or physiological construct, but an inferred state likely dominated by stress-related physiological changes. This assumption and definition is discussed further in the Introduction and Limitations sections. Here, we apply machine learning (ML) analyses to better assess generalizability, consider hidden interactions, and identify nonlinear patterns in the data. We investigated whether ML approaches could predict readiness and identify relevant biomarkers. ML models were trained on proteomics-only or metabolomics-only datasets to classify participants as ready or not ready and important model features were considered as putative biomarkers. Training and testing datasets were curated for two objectives: (i) recognize biomolecular signatures indicative of readiness within the same donor and (ii) assess generalizability across warfighters by withholding donors for testing. RESULTS: Proteomics-based models achieved AUCs of 0.907 ± 0.034 and 0.860 ± 0.063 for Objectives 1 and 2, respectively. Metabolomics-based models achieved Objective 1 AUC of 0.994 ± 0.007 and Objective 2 AUC of 0.993 ± 0.010. Comparative analysis with existing literature validates the model's feature importances, but the identified putative biomarkers significantly differ from those discovered through CLS analyses, as only one ML-identified biomarker overlapping with those identified through CLS methods. We show that these ML models and identified features are more robust to noise and generalizable across participants than those identified using CLS methods. AVAILABILITY: The analysis pipelines are provided as Jupyter notebooks, including all code and documentation, and are available publicly on GitHub at {https://github.com/netrias/ReadinessClassification}.

Machine Learning↗

PubMed2025

FluxRETAP: a REaction TArget Prioritization genome-scale modeling technique for selecting genetic targets.

MOTIVATION: Metabolic engineering is rapidly evolving as a result of new advances in synthetic biology tools and automation platforms that enable high throughput strain construction, as well as the development of machine learning tools (ML) for biology. However, selecting genetic engineering targets that effectively guide the metabolic engineering process is still challenging. ML can provide predictive power for synthetic biology, but current technical limitations prevent the independent use of ML approaches without previous biological knowledge. RESULTS: Here, we present FluxRETAP, a simple and computationally inexpensive method that leverages the prior mechanistic knowledge embedded in genome-scale models for suggesting targets for genetic overexpression, downregulation or deletion, with the final goal of increasing the production of a desired metabolite. This method can provide a list of desirable engineering targets that can be combined with current ML pipelines. FluxRETAP captured 100% of reaction targets experimentally verified to improve Escherichia coli isoprenol production, 50% of targets that experimentally improved taxadiene production in E. coli and ∼60% of genetic targets from a verified minimal constrained cut-set in Pseudomonas putida, while providing additional high priority targets that could be tested. Overall, FluxRETAP is an efficient algorithm for identifying a prioritized list of testable genetic and reaction targets. AVAILABILITY AND IMPLEMENTATION: FluxRETAP is implemented in python and released under the creative commons license. The implementation and code are freely available at: https://github.com/JBEI/FluxRETAP.

Escherichia coli↗

PubMed1997

[Risk assessment in ovarian hyperstimulation syndrome (OHS) using the machine learning system (Decision Master) in 155 in-vitro fertilisations and embryo-transfer (IVF/ET) cycles with a long stimulation protocol].

In 155 selected IVF/ET cycles stimulated with the long protocol 25 cycles with severe OHS are included which turned up later on (purposely overrepresented). An inductive machine learning program is described both in informatics and medical essentials. It is tested whether there exists an algorithm for ruling out the above-mentioned complication in the follicular phase of the same cycle already. By cross validation 89% of the OHS could be predicted and proven by practical rules using hormone and ultrasound values to avoid similar events in ongoing or further cycles.

Adult↗

PubMed2025

Assessing individual genetic susceptibility to metabolic syndrome: interpretable machine learning method.

BACKGROUND: Genome-wide association studies have provided profound insights into the genetic aetiology of metabolic syndrome (MetS). However, there is a lack of machine-learning (ML)-based predictive models to assess individual genetic susceptibility to MetS. This study utilized single-nucleotide polymorphisms (SNPs) as variables and employed ML-based genetic risk score (GRS) models to predict the occurrence of MetS, bringing it closer to clinical application. METHODS: Feature selection was performed using Least Absolute Shrinkage and Selection Operator. Six ML algorithms were employed to construct GRS models. A fivefold cross-validation was utilized to aid in the internal validation of models. The receiver operating characteristic (ROC) curve was used to select the better-performing GRS model. The SHapley Additive exPlanations (SHAP) was then applied to interpret the model. After extracting GRS, stratified analysis of BMI, age and gender was performed. Finally, these conventional risk factors and GRS were integrated through multivariate logistic regression to establish a combined model. RESULTS: A total of 17 SNPs were selected for analysis. Among the GRS models, the extreme gradient boosting (XGBoost) model demonstrated superior discriminative performance (AUC = 0.837). The XGBoost's optimal robustness was also validated through five-fold cross-validation (mean ROC-AUC = 0.706). The XGBoost-based SHAP algorithm not only elucidated the global effects of 17 SNPs across all samples, but also described the interaction between SNPs, providing a visual representation of how SNPs impact the prediction of MetS in an individual. There was a strong correlation between GRS and MetS risk, particularly observed among young individuals, males and overweight individuals. Furthermore, the model combining conventional risk factors and GRS exhibited excellent discriminative performance (AUC = 0.962) and outstanding robustness (mean ROC-AUC = 0.959). CONCLUSION: This study established a reliable XGBoost-based GRS model and a GRS prediction platform (https://metabolicsyndromeapps.shinyapps.io/geneticriskscore/) to assess individual genetic susceptibility to MetS. This model has high interpretability and can provide personalized reference for determining the necessity of primary prevention measures for MetS. Additionally, there may be interactions between traditional risk factors and GRS, and the integration of both in a comprehensive model is useful in the prediction of MetS occurrence.

Humans↗

PubMed1996

Machine learning paradigms for pattern recognition and image understanding.

In this paper some issues are considered related to the encoding of spatial information and associated perceptual learning algorithms which, it is claimed, are necessary for robust pattern and object recognition in multi-object (natural) scenes. The types of learning requirements within a 'recognition-by-parts' paradigm are contrasted with findings from alternative models.

Form Perception↗

PubMed2026

A cfDNA fragmentomics classifier for noninvasive differentiation of benign and malignant renal masses.

Noninvasive differentiation of malignant and benign renal masses remains a major clinical challenge, particularly for radiologically indeterminate lesions. Here, we developed and validated a plasma cell-free DNA (cfDNA) fragmentomics-based machine learning classifier for renal mass characterization. The model was trained on 331 participants (171 cancer, 160 benign) and independently validated on 144 participants (73 cancer, 71 benign). Three cfDNA fragmentation features, including copy number variation (CNV), fragmentation-based methylation (FRAGMA), and nucleosome footprint (NF), derived from low-pass whole-genome sequencing, were integrated into an ensemble framework. The model achieved strong discriminative performance, with area under the curve (AUC) values of 0.956 in the training cohort and 0.946 in the validation cohort, outperforming individual feature-based models. At a predefined operating threshold corresponding to 90% sensitivity, specificity reached 0.90 and 0.87, respectively. Notably, most cancer samples exhibited low tumor fraction (TF < 3%), yet the model maintained robust performance in low-TF samples (AUCs: 0.952 and 0.941, respectively). Performance remained consistent across tumor stage, grade, and histological subtypes. The classifier also demonstrated potential clinical utility in diagnostically challenging settings, including lipid-poor angiomyolipoma and oncocytoma, with 12 of 13 oncocytoma samples correctly classified in an independent cohort. In addition, the model correctly identified 85.3% of benign masses > 4 cm, for which surgical intervention is more commonly considered, and 84.6% of malignant tumors ≤ 4 cm, for which management can be challenging. Collectively, these findings support cfDNA fragmentomics as a promising noninvasive liquid biopsy approach for renal mass evaluation and clinical decision-making.

Humans↗

PubMed2026

Development and validation of a serum peptidomic signature for early detection of asymptomatic ovarian cancer: A multi-center prospective study.

Early detection of asymptomatic ovarian cancer (asym-OC) remains a critical challenge, the failure of which underlies its high mortality. Performing serum peptidomic profiling of 843 participants in the cohort SOCFCP, we distill 1,081 initial features into a 7-marker panel for asym-OC detection via a biology-informed machine-learning (ML)-based feature selection strategy. Three markers significantly revert toward non-OC levels after surgery. Integrating the panel with age, CA125, and HE4, we develop and externally validate (n = 159) a LightGBM model, ProMS+. For early-stage OC detection, ProMS+ shows a specificity of 92.6% at 95.0% sensitivity, outperforming CA125 (44.7%), HE4 (11.2%), and Risk of Ovarian Malignancy Algorithm (ROMA) (24.0%), with an area under the curve (AUC) of 0.993. In a simulated high-risk population (n = 100,000; OC prevalence = 1%), ProMS+ yields a high AUC (0.983) and a higher positive predictive value than CA125, HE4, and Age + CA125 + HE4 combined model (0.201 vs. 0.027, 0.090, and 0.064). ProMS+ offers a promising, non-invasive, and interpretable approach for the early detection of asym-OC.

Humans↗

PubMed2026

LINC01871-Mediated Sensitivity to Cyclin-Dependent Kinase 4/6 Inhibitors in Human Breast Cancer.

Breast cancer remains the most frequently diagnosed malignancy in women, and resistance to cyclin-dependent kinase 4 and 6 (CDK4/6) inhibitors limits long-term treatment efficacy. This study aimed to identify long non-coding RNAs (lncRNAs) associated with predicted sensitivity to CDK4/6 inhibitors and to investigate their biological functions in breast cancer. Transcriptomic data from The Cancer Genome Atlas (TCGA) and drug sensitivity data from the Genomics of Drug Sensitivity in Cancer 2 (GDSC2) database were integrated, and drug sensitivity was predicted using the oncoPredict algorithm. Candidate lncRNAs were identified through differential expression analysis, weighted gene co-expression network analysis, prognostic analysis, and machine learning. The biological functions of LINC01871 were subsequently evaluated using in vitro and in vivo experiments. Sixty-two lncRNAs associated with predicted sensitivity to ribociclib and palbociclib were identified, and six core lncRNAs were selected. LINC01871 showed the highest discriminatory performance for predicted drug sensitivity. Overexpression of LINC01871 was associated with increased sensitivity of breast cancer cells to ribociclib and palbociclib, inhibition of cell proliferation, promotion of apoptosis, and suppression of nuclear factor kappa B (NF-κB) signaling. Single-cell transcriptomic analysis demonstrated high LINC01871 expression in T cells and natural killer (NK) cells, while transcriptome-based immune infiltration analyses showed that high LINC01871 expression was associated with increased immune infiltration. These findings identify LINC01871 as a candidate biomarker of sensitivity to CDK4/6 inhibitors and demonstrate its tumor-suppressive effects in breast cancer. Further clinical and mechanistic studies are required to validate its predictive value and therapeutic relevance.

Humans↗

PubMed2025

Multi-criteria decision making and its application to in silico discovery of vaccine candidates for Toxoplasma gondii.

Vaccine discovery against eukaryotic parasites is not trivial and few exist. Reverse vaccinology is an in silico vaccine discovery approach, designed to identify vaccine candidates from the thousands of protein sequences encoded by a target genome. Previously, we produced the Vacceed bioinformatics pipeline for identification of parasite membrane and excreted/secreted proteins that were likely be exposed to the hosts immune system. More recently, we improved upon machine learning as the final decision-making process to identify parasite proteins that induce a protective response in an animal model. Subsequently, we combined Vacceed with metrics on B and T cell epitope types to produce a new in silico discovery workflow. In this study we extend this in silico workflow to the developability of proteins as vaccines by the incorporation of metrics on the physicochemical properties of proteins. To demonstrate this process, every Toxoplasma gondii protein was ranked in its capacity to provide exposure to the immune system (Vacceed exposure score), presence of epitopes and solubility characteristics by several multicriteria decision making (MCDM) tools (such as TOPSIS, VIKOR and MABAC). A consensus rank was subsequently generated from the results of these tools using a variety of aggregate ranking methods. Levels of uncertainty in the aggregate protein rankings was assessed by conformal interval prediction in association with a machine learning model. Several of the top ranked proteins identified by this approach were novel, uncharacterized membrane transporters or proteins associated with RNA metabolism. In conclusion, MCDM automated the decision making using well known algorithms while conformal prediction intervals varied significantly across the 8000+ proteins of T. gondii. Highly ranked proteins (e.g. the top 100) typically generated low prediction intervals, providing high levels of confidence in their ranks.

Toxoplasma↗

PubMed2025

Privacy-hardened and hallucination-resistant synthetic data generation with logic-solvers.

MOTIVATION: Machine-generated or synthetic data is a valuable resource for training artificial intelligence algorithms, evaluating rare workflows, and sharing data under stricter data legislations. However, current statistical and deep learning methods struggle with large data volumes, are prone to hallucinating scenarios incompatible with reality, and seldom quantify privacy meaningfully. RESULTS: Here, we introduce Genomator, a logic solving approach (SAT solving), which efficiently produces private and realistic representations of the original data. We demonstrate the method on genomic data, which arguably is the most complex and private information. We benchmark Genomator against state-of-the-art methodologies (Markov generation, Wasserstein Generative Adversarial Network and Conditional Restricted Boltzmann Machines), demonstrating a 40%-530% accuracy improvement and 57%-172% higher privacy. Genomator is also 3-100 times more efficient, making it the only tested method that scales to whole genomes. We show the universal trade-off between privacy and accuracy, and use Genomator's tuning capability to cater to all applications along the spectrum, from provable private representations of sensitive cohorts, to datasets with indistinguishable pharmacogenomic profiles. Demonstrating the production-scale generation of tuneable synthetic genomes hold great potential for balancing underrepresented populations in medical research and advancing global data exchange. AVAILABILITY AND IMPLEMENTATION: Genomator is available at https://github.com/csiro/genomator.

Algorithms↗

PubMed2026

Proteome-wide structural and interaction analysis using cross-linking mass spectrometry and its applications.

Deciphering the mechanisms of protein-protein interactions (PPIs) and protein structural changes within the native cellular environment is crucial for advancing drug discovery. In vivo chemical cross-linking coupled with mass spectrometry (XL-MS) captures weak, transient, and higher-order interactions that are often dysregulated under altered physiological conditions and remain challenging to detect using conventional methods. Applications of in vivo XL-MS range from targeted mapping of PPIs to large-scale identification of interactome networks within the cells. The integration of quantitative approaches further facilitates comparison across different physiological conditions. The recent incorporation of machine learning (ML) tools into XL-MS workflows is transforming the depth and efficiency of this technology. AI-driven algorithms now enable more accurate identification of cross-linked peptides and the mapping of interaction topologies. Furthermore, the synergistic coupling of in vivo XL-MS data with AI-assisted structural modeling platforms such as AlphaFold allows dynamic and high-throughput prediction of protein networks. This review discusses the broader applications of in vivo XL-MS in complex biological samples, ranging from organelles and cells to whole tissues, and highlights how AI integration is expanding structural biology toward a systems-level understanding of proteome architecture.

Mass Spectrometry↗

PubMed2026

Clinical translation of senescence-related pan-cancer multi-omics: tools for assessment and immunotherapy prediction.

Cellular senescence (CS) exerts dual roles in tumorigenesis, yet its pan-cancer molecular characteristics and clinical value remain unclear, hindering its translation to oncology and personalized therapy. To address the lack of specific and universal tools for senescence assessment and immunotherapy response prediction, this study systematically analyzed 1259 CS-related genes from the CellAge database across 31 cancer types by integrating multi-omics data, including bulk RNA-seq, single-cell/spatial transcriptomics, and CRISPR screening. We developed a rank-based algorithm SenScoreR (publicly available at https://gxhub.shinyapps.io/SenScoreR/ ) for senescence quantification, validated with 10 independent datasets, and constructed a machine learning-based predictive model CS.Sig for immunotherapy response. Results showed that tumors had significantly lower Rank-based Senescence Score (RSS) than normal tissues across 31 cancers (average diagnostic AUC = 0.895), with low RSS linked to poor survival; high RSS correlated with reduced genomic instability, enriched CD8⁺ T/NK cell/macrophage infiltration, upregulated PD-L1 expression, and elevated immune cytolytic activity. CS.Sig demonstrated robust performance in predicting ICI response (AUC = 0.716 across 10 cohorts), outperforming 13 existing signatures, while CRISPR screening identified 17 senescence-related targets (e.g., CEP55, PPP1CC) whose knockout enhanced anti-tumor immunity. Our findings clarify CS's role in maintaining tumor genomic stability and shaping immune microenvironments, and the developed SenScoreR, CS.Sig, and identified targets bridge basic CS research with clinical oncology, providing a translational resource and hypothesis basis for future experimental and clinical validation.

Journal Article↗

PubMed2025

Gene Specific Pathogenicity Predictor for Chromatin-Remodeling BAF Complex-Associated Neurodevelopmental Disorders.

Advancements in whole genome sequencing have increased the number of variants of uncertain significance (VUS) identified in patient genomes. This has created a diagnostic bottleneck for genetic counselors tasked with sifting through these variants and determining those most likely to be causative for a patient's clinical presentation. Machine learning (ML) tools can aid in identifying pathogenic variants from VUS, but there is a need for gene-specific algorithms that predict pathogenic variants with high accuracy. To address this need, we present a workflow for developing gene-specific, ensemble-learning ML tools, that leverage outputs from other algorithms, locations of variants within the gene, and evolutionary conservation data to make a prediction of pathogenicity. Variants in SMARCA2 and SMARCA4 that are associated with rare neurodevelopmental diseases were used to screen 15 ML algorithms. A random forest learner was tuned to yield a final accuracy of 0.93 on holdout data. Generalizing this predictor to other BAF complex proteins resulted in a sharp decline in performance. We trained a final predictor for all genes in the study to create a predictor that identifies pathogenic variants in these BAF subunits with an accuracy of 0.91 on holdout data. This predictor specific to BAF complex proteins performs with higher accuracy and AUROC than any other predictor. The decline in performance when generalized to other proteins emphasizes the need for the gene-specific calibration of predictors. Our workflow for the development of such models provides a quick, computationally inexpensive route for improving the ML tools available to genetic counselors.

Journal Article↗

PubMed2026

Machine learning-assisted plasma PEA proteomics enables differential diagnosis of melancholic depression and bipolar disorder.

Differentiating bipolar disorder (BD) from major depressive disorder (MDD) remains a critical unmet need in psychiatry due to overlapping clinical presentations and the absence of reliable biological markers. In this study, we assessed the capacity of multivariate machine learning models to accurately differentiate BD from MDD with melancholic features using plasma proteomic profiles obtained via Proximity Extension Assay (PEA) technology. A total of 67 participants were included (23 BD, 20 MDD, and 24 HC), and plasma protein expression was assessed using the Olink Target 96 Neurology panel. Differential proteomic analysis revealed distinct disorder-specific expression patterns, identifying 21 differentially expressed proteins in BD versus MDD, 18 in BD versus healthy controls, and 7 in MDD versus healthy controls. Using a stepwise feature reduction strategy, machine learning models were trained on three feature sets comprising all proteins, the top 20 most informative proteins, and the top 5 most beneficial proteins, and evaluated across BD-MDD, BD-HC, and MDD-HC classification tasks using five algorithms. For BD-MDD discrimination, the Random Forest model achieved the highest performance when trained on the top 5 protein set (LXN, HAGH, MATN3, PLXNB1, and CTSC), yielding an AUC of 0.905, with similarly strong performance observed using the top 20 protein set. Feature importance analysis highlighted proteins involved in neurodevelopmental processes, immune regulation, and extracellular matrix organization. Overall, these findings demonstrate that integrating plasma proteomics with machine learning enables robust differentiation between BD and MDD with melancholic features, supporting the development of scalable and biologically informed diagnostic tools for precision psychiatry.

Bipolar disorder↗

PubMed1994

Artificial intelligence within the chemical laboratory.

Various techniques within the area of artificial intelligence such as expert systems and neural networks may play a role during the problem-solving processes within the clinical biochemical laboratory. Neural network analysis provides a non-algorithmic approach to information processing, which results in the ability of the computer to form associations and to recognize patterns or classes among data. It belongs to the machine learning techniques which also include probabilistic techniques such as discriminant function analysis and logistic regression and information theoretical techniques. These techniques may be used to extract knowledge from example patients to optimize decision limits and identify clinically important laboratory quantities. An expert system may be defined as a computer program that can give advice in a well-defined area of expertise and is able to explain its reasoning. Declarative knowledge consists of statements about logical or empirical relationships between things. Expert systems typically separate declarative knowledge residing in a knowledge base from the inference engine: an algorithm that dynamically directs and controls the system when it searches its knowledge base. A tool is an expert system without a knowledge base. The developer of an expert system uses a tool by entering knowledge into the system. Many, if not the majority of problems encountered at the laboratory level are procedural. A problem is procedural if it is possible to write up a step-by-step description of the expert's work or if it can be represented by a decision tree. To solve problems of this type only small expert system tools and/or conventional programming are required.(ABSTRACT TRUNCATED AT 250 WORDS)

Artificial Intelligence↗