2025
Acoustic-based machine learning approaches for depression detection in Chinese university students
Wei Y, Qin S, Liu F, Liu R, Zhou Y, Chen Y, Xiong X, Zheng W, Ji G, Meng Y, Wang F, Zhang R. Acoustic-based machine learning approaches for depression detection in Chinese university students. Frontiers In Public Health 2025, 13: 1561332. PMID: 40443925, PMCID: PMC12119278, DOI: 10.3389/fpubh.2025.1561332.Peer-Reviewed Original ResearchConceptsPatient Health Questionnaire-9Mel-frequency cepstral coefficientsLinear discriminant analysisMachine learning algorithmsAcoustic featuresLearning algorithmsIdentification of depressionMonitoring of depressionCross-sectional studyGlobal public health problemSHapley Additive exPlanationsDepression screeningSelf-report methodsPublic health problemIdentifying DepressionLinear discriminant analysis modelDepression assessmentSupport vector classificationAutomated identificationMachine learning approachArea under the curveHealth problemsOpenSMILE toolkitLogistic regressionCepstral coefficientsVisualizing functional network connectivity differences using an explainable machine-learning method
Sendi M, Itkyal V, Edwards-Swart S, Chun J, Mathalon D, Ford J, Preda A, van Erp T, Pearlson G, Turner J, Calhoun V. Visualizing functional network connectivity differences using an explainable machine-learning method. Physiological Measurement 2025, 46: 045009. PMID: 40245920, DOI: 10.1088/1361-6579/adce52.Peer-Reviewed Original ResearchConceptsCognitive control networkFunctional network connectivitySubcortical networksSHapley Additive exPlanationsExplainable machine learningMachine learning modelsStatistical learning approachResting-state functional magnetic resonance imagingFunctional magnetic resonance imagingClassification accuracyLack interpretabilityMachine-learning methodsMachine learningSynthetic dataLearning approachLearning modelsNetwork connectivityAging AdultsRandom forestOlder aged adultsNetworkSomatomotor networkConnectivity differencesNeural mechanismsCatBoost model
2024
Prospective and External Validation of an Ensemble Learning Approach to Sensitively Detect Intravenous Fluid Contamination in Basic Metabolic Panels
Spies N, Militello L, Farnsworth C, El-Khoury J, Durant T, Zaydman M. Prospective and External Validation of an Ensemble Learning Approach to Sensitively Detect Intravenous Fluid Contamination in Basic Metabolic Panels. Clinical Chemistry 2024, 71: 296-306. PMID: 39545815, DOI: 10.1093/clinchem/hvae168.Peer-Reviewed Original ResearchSHapley Additive exPlanationsLearning approachDetection of contamination eventsUnsupervised learning approachLearning-based methodsMachine learning-based methodsEnsemble learning approachMachine learning pipelineEnsemble learningLearning pipelineMatthews correlation coefficientAlgorithmic fairnessReal worldSHapley Additive exPlanations valuesCurrent workflowsClinical workflowWorkflowOperational burdenBasic metabolic panelIntravenous (IVPipelineInternal validation setValidation setFlagging ratesPerformance assessmentA Comprehensive, Artificial Intelligence, Digital Twin Platform Based on Multimodal Real-World Data Integration for Personalized Medicine in Hematology
D'Amico S, Sauta E, Asti G, Delleani M, Zazzetti E, Campagna A, Lanino L, Maggioni G, Ubezio M, Todisco G, Russo A, Tentori C, Buizza A, Franchi M, Dall'Olio L, Bicchieri M, Zampini M, Brindisi M, Ficara F, Riva E, Ventura D, Crisafulli L, Pinocchio N, Della Porta A, Jacobs F, Zambelli A, Savevski V, Santoro A, Sole F, Platzbecker U, Fenaux P, Diez-Campelo M, Garcia-Manero G, Haferlach T, Kordasti S, Castellani G, Efficace F, Santini V, Zeidan A, Komrokji R, Della Porta M. A Comprehensive, Artificial Intelligence, Digital Twin Platform Based on Multimodal Real-World Data Integration for Personalized Medicine in Hematology. Blood 2024, 144: 2221-2221. DOI: 10.1182/blood-2024-209634.Peer-Reviewed Original ResearchArtificial intelligenceData sharingDigital twinFederated learning platformSynthetic data generatorSHapley Additive exPlanationsImage dataDT platformDecision support systemMultimodal longitudinal dataAI-based toolsUnstructured informationAI frameworkData model formatElectronic health recordsMultimodal dataMultimodal informationPatient informationData integrationAI modelsData generationCentral repositoryTechnology implementation methodMultiple sources of informationReal world
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply