Introduction: This study aims to explore machine learning (ML) methods for early prediction of Alzheimer's disease (AD) and related dementias (ADRD) using the real-world electronic health records (EHRs).
Methods: A total of 23,835 ADRD and 1,038,643 control patients were identified from the OneFlorida+ Research Consortium. Two ML methods were used to develop the prediction models. Both knowledge-driven and data-driven approaches were explored. Four computable phenotyping algorithms were tested.
Results: The gradient boosting tree (GBT) models trained with the data-driven approach achieved the best area under the curve (AUC) scores of 0.939, 0.906, 0.884, and 0.854 for early prediction of ADRD 0, 1, 3, or 5 years before diagnosis, respectively. A number of important clinical and sociodemographic factors were identified.
Discussion: We tested various settings and showed the predictive ability of using ML approaches for early prediction of ADRD with EHRs. The models can help identify high-risk individuals for early informed preventive or prognostic clinical decisions.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10976442 | PMC |
| http://dx.doi.org/10.1002/alz.12967 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Optimizing the life of vascular access during follow-up.
J Cardiovasc Surg (Torino)
February 2025
Department of Vascular Surgery, ASST Settelaghi Universitary Teaching Hospital, University of Insubria, Varese, Italy.
Optimizing the longevity of vascular access in hemodialysis patients remains a critical aspect of patient care, given the significant role of arteriovenous fistulas (AVFs) and arteriovenous grafts (AVGs) in enabling effective dialysis. Vascular access complications, such as stenosis, thrombosis, and cannulation-related damage, continue to challenge both the functionality and the sustainability of these access points. Recent advancements underscore the importance of a robust follow-up strategy, integrating clinical evaluations with diagnostic tools like color Doppler ultrasound (CDU) and emerging interventional approaches such as drug-coated balloon (DCB) angioplasty.
View Article and Find Full Text PDFApplication of Contrast-Enhanced Ultrasound Parameters of Metastatic Axillary Lymph Nodes in Breast Cancer Patients in Predicting the Efficacy of Neoadjuvant Chemotherapy in Early Stage.
J Clin Ultrasound
January 2025
Inpatient Department of Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, China.
Background: To investigate the performance of contrast-enhanced ultrasound(CEUS) parameters of metastatic axillary lymph nodes (ALNs) before and after two courses of neoadjuvant chemotherapy (NAC) in breast cancer patients in predicting the efficacy of NAC.
Methods: A total of 41 postoperative breast cancer patients were selected. All patients underwent NAC, and ALN biopsy was positive before chemotherapy.
Cross-cultural validation of plasma p-tau217 and p-tau181 as precision biomarkers for amyloid PET positivity: An East Asian study in Taiwan and Korea.
Alzheimers Dement
January 2025
Department of Neurology, Neurological Institute, Taipei Veterans General Hospital, Taipei, Taiwan.
Introduction: Plasma phosphorylated tau (p-tau) biomarkers have improved Alzheimer's disease (AD) diagnosis, but data from diverse Asian populations are limited. This study evaluated plasma p-tau217 and p-tau181 levels in Korean and Taiwanese populations.
Methods: All participants (n = 270) underwent amyloid positron emission tomography (PET) and blood tests.
Online Bayesian State Estimation for Real-Time Monitoring of Growth Kinetics in Thin Film Synthesis.
Nano Lett
January 2025
Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831, United States.
Rapid validation of newly predicted materials through autonomous synthesis requires real-time adaptive control methods that exploit physics knowledge, a capability that is lacking in most systems. Here, we demonstrate an approach to enable real-time control of thin film synthesis by combining optical diagnostics with a Bayesian state estimation method. We developed a physical model for film growth and applied the direct filter (DF) method for real-time estimation of nucleation and growth rates during pulsed laser deposition (PLD).
View Article and Find Full Text PDFElectroencephalogram biomarkers as predictors of mortality and functional recovery in patients with severe traumatic brain injury: Protocol study.
MethodsX
June 2025
Neurorehabilitation and Neuromodulation Laboratory, Department of Physiological Sciences, Federal University of Espírito Santo, City of Vitória, ES, Brazil.
Traumatic brain injury (TBI) is a global public health condition that causes cognitive and behavioral deficits. This protocol assesses the potential of quantitative electroencephalogram (EEG) biomarkers, associated with inflammatory indicators, to predict mortality and functional recovery in patients with severe TBI. Through continuous monitoring and analysis of abnormal brain activity patterns, the protocol aims to personalize therapeutic interventions and improve patient quality of life.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!