NCT06798688尚未招募不适用
Software Algorithm Using Machine Learning and Threshold Based Methods for Predicting Exacerbations and Deterioration
适应症
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 入组人数
- 20
- 主要终点
- Identifying readmissions using respiratory biomarkers
研究概览
简要总结
In this study, the sponsor would like to collaborate with Institution and Investigator to aggregate participants data and to pilot its software algorithm using machine learning and threshold based methods for predicting exacerbations and deterioration within a 60 days period post-discharge.
研究设计
- 研究类型
- Observational
- 观察模型
- Case Only
- 时间视角
- Retrospective
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Subject age 18 or older
- •Receives all primary and specialty care at Institution
- •Participants will be enrolled at discharge (and not designate hospital or ED)
- •A history of one of the following diagnoses:
- •a. c. Chronic obstructive pulmonary disease
- •At least two documented exacerbations of the above disease in the past 12 months as defined by the following corresponding criteria:
- •a. Chronic obstructive pulmonary disease exacerbation: all three of (1) increase in frequency and severity or severity of cough, (2) increase in volume and/or change of character of sputum production, and (3) increase in dyspnea, and requiring treatment with short-acting bronchodilators, antibiotics, and oral or intravenous glucocorticoids.
- •Participants able to provide informed consent.
- •Participants will be enrolled at discharge (and not designate hospital or ED)
排除标准
- •Participants with neuromuscular diseases and seizures
- •Participants enrolled in hospice care or life expectancy less than three months.
- •Participants living more than 60 miles away from Institution and Investigator
- •Participants with expected out of state travel within a 30-day period or travel to a location with no internet access.
结局指标
主要结局
Identifying readmissions using respiratory biomarkers
时间窗: 60-days
To validate respiratory-based biomarkers in models to predict exacerbations - benchmarking to be done versus physician assess exacerbations, emergency department visits, hospitalizations and any other visit.
次要结局
- Validate compliance and usability(60-days)
研究者
相似试验
暂停
不适用
The use of artificial intelligence and mobile health technologies to identify patients at the highest risk of atrial fibrillation (irregular and often abnormally fast heart rate)Atrial fibrillation (AF)Circulatory SystemISRCTN17993837Chelsea and Westminster Hospital NHS Foundation Trust1,800
尚未招募
Unknown
Development of Machine Learning Algorithm for Optimizing Anti-Hypertensive MedicatioDiseases of the circulatory systemKCT0008921Asan Medical Center200
已完成
不适用
Deep learning prognostic model for pancreatic cancerNeoplasmsKCT0007154Asan Medical Center2,584
尚未招募
Unknown
se of AI in Cardiovascular Risk Prediction.CTRI/2023/07/054781A
尚未招募
Unknown
Development of Artificial Intelligence based program to assess the level of maturation of bone and to detect any abnormalities in the upper spine by using head x-rays (side view) of children having cleft, that is, split in the upper lip and palate.CTRI/2023/09/057228Gaithoiliu Kamei