In this paper, a new cohort identification system that exploits the semantic hierarchy of SNOMED CT is proposed to overcome the limitations of supervised machine learning-based approaches. Eligibility criteria descriptions and free-text clinical notes from the 2018 National NLP Clinical Challenge (n2c2) were processed to map to relevant SNOMED CT concepts and to measure semantic similarity between the eligibility criteria and patients. The eligibility of a patient was determined if the patient had a similarity score higher than a threshold cut-off value. The performance of the proposed system was evaluated for three eligibility criteria. The performance of the current system exceeded the previously reported results of the 2018 n2c2, achieving the average F1 score of 0.933. This study demonstrated that SNOMED CT alone can be leveraged for cohort identification tasks without referring to external textual sources for training.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10148338 | PMC |
Publication Analysis
Top Keywords
Similar Publications
Identification of key gene signatures for predicting chemo-immunotherapy efficacy in extensive-stage small-cell lung cancer using machine learning.
Lung Cancer
January 2025
Internal Medicine III, Wakayama Medical University, Wakayama, Japan.
Objectives: The lack of definitive biomarkers presents a significant challenge for chemo-immunotherapy in extensive-stage small-cell lung cancer (ES-SCLC). We aimed to identify key genes associated with chemo-immunotherapy efficacy in ES-SCLC through comprehensive gene expression analysis using machine learning (ML).
Methods: A prospective multicenter cohort of patients with ES-SCLC who received first-line chemo-immunotherapy was analyzed.
Cardiovascular Risk from Metabolic Dysfunction-Associated Steatotic Liver Disease, Cardiometabolic Risk Factor Count, and Their Longitudinal Changes: A Nationwide Cohort Study.
Am J Gastroenterol
December 2024
Department of Internal Medicine, Yonsei University College of Medicine, Seoul, Korea.
Introduction: Metabolic dysfunction-associated steatotic liver disease (MASLD) is associated with incident cardiovascular disease (CVD). However, CVD risk could vary across and within individuals with MASLD. We investigated the cardiovascular implications of MASLD, cardiometabolic risk factor count, and their longitudinal changes.
View Article and Find Full Text PDFDeep learning model for identifying acute heart failure patients using electrocardiography in the emergency room.
Eur Heart J Acute Cardiovasc Care
January 2025
Department of Medical Informatics, Korea University College of Medicine, Seoul, Republic of Korea.
Background: Acute heart failure (AHF) poses significant diagnostic challenges in the emergency room (ER) because of its varied clinical presentation and limitations of traditional diagnostic methods. This study aimed to develop and evaluate a deep-learning model using electrocardiogram (ECG) data to enhance AHF identification in the ER.
Methods: In this retrospective cohort study, we analyzed the ECG data of 19,285 patients who visited ERs of three hospitals between 2016 and 2020; 9,119 with available left ventricular ejection fraction and N-terminal prohormone of brain natriuretic peptide level data and who were diagnosed with AHF were included in the study.
Chronic kidney disease as a predictor of long-term adverse cardiovascular outcomes in patients with aortoiliac disease: a prospective cohort study.
J Cardiovasc Surg (Torino)
January 2025
Faculty of Medicine and Biomedical Sciences, Campus of Gambelas, University of Algarve, Faro, Portugal.
Background: Aortoiliac disease poses a significant cardiovascular (CV) risk, especially in individuals with chronic kidney disease. This study aimed to assess the predictive role of chronic kidney disease in long-term major adverse CV events in patients submitted to aortoiliac revascularization due to severe aortoiliac atherosclerotic disease.
Methods: From 2013 to 2023, patients who underwent aortoiliac revascularization for TASC II type D lesions, including those with chronic kidney disease, were selected from a prospective cohort study.
Development and Validation of a Routine Electronic Health Record-Based Delirium Prediction Model for Surgical Patients Without Dementia: Retrospective Case-Control Study.
JMIR Perioper Med
January 2025
Department of Surgery, Indiana University School of Medicine, Indianapolis, IN, United States.
Background: Postoperative delirium (POD) is a common complication after major surgery and is associated with poor outcomes in older adults. Early identification of patients at high risk of POD can enable targeted prevention efforts. However, existing POD prediction models require inpatient data collected during the hospital stay, which delays predictions and limits scalability.
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!