Clinical Research Directory

Machine-Learning Prediction of Pregnancy Outcomes After Assisted Reproductive Treatments

The goal of this observational study is to develop and validate a machine-learning model to predict pregnancy outcomes in women with a positive pregnancy test following assisted reproductive treatment (ART), with the primary analysis focusing on in vitro fertilization (IVF) and frozen embryo transfer (FET). The study will also include an exploratory analysis of pregnancies following intrauterine insemination (IUI). The main questions addressed by the study are: Can early blood levels of beta-human chorionic gonadotropin (beta-hCG) predict the likelihood of live birth in an IVF or FET cycle? Can early beta-hCG levels help identify pregnancies at increased risk of biochemical pregnancy or early pregnancy loss? Participants will have clinical and treatment information, including beta-hCG measurements and pregnancy outcomes, collected from medical records or during prospective follow-up. No changes to participants' medical treatment will be made as part of the study.

Timely Ordering of Pharmacogenetic Testing

The goal of this trial is to learn if a machine learning (ML) model can help optimize drug therapy in the pediatric population. The main question\[s\] it aims to answer are whether a machine learning model predicting receipt of a targeted medication within the next three months: * Increases the offering of pharmacogenetic testing prior to receipt of a targeted medication * Increases the number of patients with pharmacogenetic results prior to receipt of a targeted medication * Increases the number of patients who have alteration in medication choice or dose based on pharmacogenetic results This trial only focuses on the prediction and provision of participants with a high-risk of receiving a medication with a pharmacogenetic indication in the next three months.

Development and Validation of a Colorectal Cancer Diagnostic Model

This is a multicenter, observational study designed to develop and validate a diagnostic model for colorectal cancer and advanced colorectal neoplasia among adults undergoing routine-care colonoscopy in the Chinese population. The study will enroll adults aged 18 to 80 years who have already been scheduled or planned to undergo colonoscopy according to routine clinical care, physical examination, or screening pathways at participating medical institutions. The study will not invite, organize, require, or otherwise arrange colonoscopy for any participant. Colonoscopy, bowel preparation, anesthesia assessment, biopsy, pathology examination, and subsequent clinical management will be performed solely according to the existing clinical pathway of each participating institution. After informed consent, participants will be invited to complete a standardized electronic questionnaire before their scheduled colonoscopy. The questionnaire will collect self-reported information on demographic characteristics, lifestyle factors, environmental exposures, personal medical history, family history of colorectal cancer, prior colonoscopy history, and gastrointestinal symptoms. The study team will also abstract colonoscopy and pathology results from medical records. No additional biological specimens will be collected for research purposes. The primary clinical outcome is prevalent colorectal advanced neoplasia, defined as colorectal cancer, advanced colorectal adenoma, or advanced colorectal serrated lesion identified through colonoscopy and associated pathology. Statistical and machine-learning approaches will be used to develop and validate diagnostic models. Model performance will be evaluated by discrimination, calibration, and clinical net benefit in internal validation and multicenter external validation.

Development and Validation of an Interpretable Machine Learning Model for Predicting Venous Thromboembolism（VTE）in Intensive Care Unit (ICU) Patients

Venous thromboembolism remains a leading cause of preventable mortality in intensive care unit (ICU) patients. Existing risk-stratification tools were developed in general medical populations and lack ICU-specific predictors. This study was to develop and validate an interpretable machine learning (ML) model to predict VTE in ICU patients.

Early Functional Response as a Predictor of Clinical Outcomes in Hand Rehabilitation: A Prospective Feasibility Study Using a Digital Monitoring System

This study investigates whether early changes observed during the first weeks of hand and upper extremity rehabilitation can predict patient outcomes months later. In rehabilitation practice, clinicians make numerous decisions each session regarding exercise type, frequency, duration, and treatment approach. Most of these decisions are currently made without systematic longitudinal data. This study addresses three fundamental questions using data collected during routine clinical care: (1) Can the rate of improvement in the first weeks of treatment predict functional status months later, across both session-based and milestone-based time points? (2) Are there meaningfully different recovery profiles among hand rehabilitation patients? (3) Is there measurable variation in clinical decision-making among patients with similar profiles, and does this variation relate to outcomes? A digital patient monitoring platform developed by the principal investigator, a physiotherapist and academic researcher specializing in hand rehabilitation serves as the data collection infrastructure. The platform records standard clinical assessment measures in a structured format and has been in active clinical use at Hacettepe University prior to this study. For research purposes, the system has been expanded to include structured capture of patient-reported outcomes, patient global impression of change, treatment protocol coding, home exercise adherence, and automated calculation of early response metrics. This is a 12-month prospective observational cohort study enrolling a minimum of 60 patients. Data are stored securely on the university's institutional network. Patients are anonymized using identification codes. The study is subject to Hacettepe University Ethics Committee approval and participant informed consent. Findings are expected to generate evidence supporting data-driven clinical decision-making in rehabilitation and to provide a feasibility foundation for a larger multi-center study.

Predictive Value of Gastrointestinal Blood Flow for Enteral Nutrition Intolerance in Critically Ill Patients

This study aims to explore the correlation between gastrointestinal blood flow and the incidence of enteral nutrition intolerance (ENI) and its symptoms in critically ill patients, construct and compare predictive models including blood flow parameters, and evaluate their incremental predictive value.

Research on the Development and Validation of an Early Prediction Model for Delirium

Delirium has a high incidence rate and significantly affects patient prognosis. Diagnosis often relies on manual assessment, which is subject to strong subjectivity, high rates of missed diagnosis, and poor stability. This study employs non-contact identification technology based on machine vision analysis to quantitatively analyze characteristic biological feature data such as micro-expressions. It then investigates the correlation between these features and delirium subtypes. By integrating clinical phenotypic data and using machine learning algorithms, a multi-modal early prediction model for delirium is constructed to meet the clinical need for early warning of delirium subtypes and enhance the efficacy of delirium identification.