AI & Digital Medicine
Interpretable deep learning on brain images and physiological signals, and the digital-medicine infrastructure that turns those models into usable clinical research tools.
14 publications
2026
Digital Medicine in Neuropsychiatry: Prospects, Applications, and the Emerging Framework of Precision Psychiatry
doi:10.4103/ejpi.EJPI-D-25-00066
A review mapping how digital medicine — wearables, AI and big data — is reshaping neuropsychiatry and enabling an emerging framework of precision psychiatry.
2025
Comparison of machine learning and conventional criteria in detecting left ventricular hypertrophy and prognosis with electrocardiography
Full text · PMCdoi:10.1093/ehjdh/ztaf003
Cox regression analyses showed that LVH identified by AI algorithm (hazard ratio and 95% confidence interval: 1.587, 1.309-1.924), Sokolow-Lyon (1.19, 1.038-1.365), Cornell product (1.301, 1.124-1.505), Cornell/strain index (1.306, 1.185-1.439), Framingham criterion (1.174, 1.062-1.298), and echocardiography-confirmed LVH (1.124, 1.019-1.239) were all significantly associated with mortality.
2024
Optimization of Using Multiple Machine Learning Approaches in Atrial Fibrillation Detection Based on a Large-Scale Data Set of 12-Lead Electrocardiograms: Cross-Sectional Study
Full text · PMCdoi:10.2196/47803
In conclusion, this study successfully used machine learning methodologies, particularly the LightGBM model, to differentiate SR and AF based on power spectral features derived from 12-lead ECGs.
2023
Predicting aging trajectories of decline in brain volume, cortical thickness and fractional anisotropy in schizophrenia
Full text · PMCdoi:10.1038/s41537-022-00325-w
Our findings suggest that schizophrenia differentially affects the decline of different brain structures during the disease course.
Rapid detection of nicotine and benzoic acid in e-liquids with surface-enhanced Raman scattering and artificial intelligence-assisted spectrum interpretation
doi:10.1016/j.jpba.2023.115456
Our previous study demonstrated a surface-enhanced Raman scattering (SERS)-based approach to identify nicotine-containing e-liquids; without any pre-treatment, e-liquid can be directly tested on our solid-phase SERS substrates, made of silver nanoparticle arrays embedded in anodic aluminium oxide nanochannels (Ag/AAO).
2022
Functional MRI and ApoE4 genotype for predicting cognitive decline in amyloid-positive individuals
Full text · PMCdoi:10.1177/17562864221138154
These findings can assist clinicians in predicting changes in cognitive status in individuals with a high risk of Alzheimer's disease and can assist future studies in developing precise treatment and prevention strategies.
Smartphone-based artificial intelligence using a transfer learning algorithm for the detection and diagnosis of middle ear diseases: A retrospective deep learning study
Full text · PMCdoi:10.1016/j.eclinm.2022.101543
Our results show that the proposed method provides sufficient treatment recommendations that are comparable to those of specialists.
2021
Deep Neural Network to Differentiate Brain Activity Between Patients With First-Episode Schizophrenia and Healthy Individuals: A Multi-Channel Near Infrared Spectroscopy Study
Full text · PMCdoi:10.3389/fpsyt.2021.655292
This study aimed to differentiate between patients with FES and healthy controls (HCs) on basis of the frontotemporal activity measured by NIRS with a support vector machine (SVM) and deep neural network (DNN) classifier.
Predicting Norovirus in the United States Using Google Trends: Infodemiology Study
Full text · PMCdoi:10.2196/24554
We found that fever, gastroenteritis, poison, cruise, wedding, and watery diarrhea were important factors correlated with norovirus Google Trends.
Prediction of Probable Major Depressive Disorder in the Taiwan Biobank: An Integrated Machine Learning and Genome-Wide Analysis Approach
Full text · PMCdoi:10.3390/jpm11070597
Our study suggests that an integrated machine learning and genome-wide analysis approach may offer an advantageous method to establish bioinformatics tools for discriminating MDD patients from healthy controls.
Validation of Machine Learning-Based Individualized Treatment for Depressive Disorder Using Target Trial Emulation
Full text · PMCdoi:10.3390/jpm11121316
In emulation of clinical trials, the model-selected regimen was associated with a reduced treatment failure rate.
2020
Development of an Al-Based Web Diagnostic System for Phenotyping Psychiatric Disorders
Full text · PMCdoi:10.3389/fpsyt.2020.542394
Discussion: Together, our approach under the EDNN framework demonstrated the potential future direction of making a schizophrenia diagnosis based on structural brain imaging data.
Prediction of Antidepressant Treatment Response and Remission Using an Ensemble Machine Learning Framework
Full text · PMCdoi:10.3390/ph13100305
Our study demonstrates that the ensemble machine learning framework may present a useful technique to create bioinformatics tools for discriminating non-responders from responders prior to antidepressant treatments.
2018
A Deep Learning Approach for Predicting Antidepressant Response in Major Depression Using Clinical and Genetic Biomarkers
Full text · PMCdoi:10.3389/fpsyt.2018.00290
By using the SNP dataset that was original to a genome-wide association study, we selected 10 SNPs (including ABCA13 rs4917029, BNIP3 rs9419139, CACNA1E rs704329, EXOC4 rs6978272, GRIN2B rs7954376, LHFPL3 rs4352778, NELL1 rs2139423, NUAK1 rs2956406, PREX1 rs4810894, and SLIT3 rs139863958) which were associated with antidepressant treatment response.