Application of Artificial Intelligence Using Wearable Technology in Patients With Advanced Chronic Liver Disease (ACLD): a Trajectomics Approach.
试验速览
- 阶段
- 不适用
- 状态
- 已完成
- 发起方
- 入组人数
- 8
- 试验地点
- 1
- 主要终点
- Feasibility and accuracy of machine learning analysis of individual health data collected by wearable device.
研究概览
简要总结
The research project studies the possibility of using an artificial intelligence-based system in patients with advanced chronic liver disease (liver cirrhosis) to record variations in a patient's health status, with the aim of early identification of clinical improvement or deterioration. The system is based on the collection and processing of various clinical parameters through an Apple Watch. The study aims to evaluate whether the data generated by this system correlate with patients' clinical evolution and whether its use may ultimately contribute to improved care management and quality of life.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Prospective
入排标准
- 年龄范围
- 18 Years 至 75 Years（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Adults aged 18-75 years
- •Diagnosis of advanced chronic liver disease (ACLD).
- •hospitalized for hepatic decompensation or acute-on-chronic liver failure (ACLF), including ascites, hepatorenal syndrome, hepatic encephalopathy, bacterial infection, gastrointestinal bleeding, or jaundice; or
- •outpatient with Child-Pugh B cirrhosis and no evidence of hepatic decompensation or ACLF at enrolment.
- •Willing and able to provide written informed consent.
排除标准
- •Inability or refusal to provide written informed consent
- •Inability to wear or correctly use the Apple Watch
- •Patients with hepatocellular carcinoma beyond the Milan Criteria (one lesion up to 5 cm or 3 lesions up to 3 cm in diameter)
- •Presence of hepatic decompensation or ACLF
结局指标
主要结局
Feasibility and accuracy of machine learning analysis of individual health data collected by wearable device.
时间窗: From enrollment to the end of the study (6 months)
The primary outcome is to assess the feasibility and accuracy of machine learning analysis of individual health data collected by wearable device and to describe their patterns during hospitalization due to symptoms of decompensation or ACLF and in outpatients until hospitalization due to decompensation or ACLF in patients with liver cirrhosis. Health data continuously collected through a dedicated wearable device application comprise: heart rate and heart rate variability (HR; HRV), oxygen saturation (SpO₂), ECG (QRS, PQ, PT Tpe interval), sleep quality and duration, daily step count, tremor intensity (Hz), typing speed (taps/time). The single unit of measure used to assess the feasibility of the wearable device is the usable data acquisition rate (%), defined as the percentage of monitoring data successfully collected and suitable for analysis.
次要结局
未报告次要终点
研究者
Antonio Galante
Director
Fondazione Epatocentro Ticino