Frailty
Conditions
Keywords
Frailty, Cardiac surgery, Artificial intelligence, Non-contact monitoring
Brief summary
The main purpose of this study is to establish a frailty automatic evaluation index AI frailty index based on artificial intelligence multi-modal non-contact monitoring information analysis. At the same time, the study will explore the correlation between ' AI weakness index ' and perioperative and long-term prognosis and quality of life.
Detailed description
This is a prospective cohort study. Patients who undergoes elective cardiac surgery will be enrolled. We collect frailty scales, clinical information and multi-modal, non-contact monitoring information during hospitalization. One-year follow-up will be done. The non-contact monitoring information are used to predict the frailty scales to establish and validate an AI-based frailty assessment model AI frailty index. The AI frailty index will be further used to predict perioperative and long-term outcomes.
Interventions
No intervention
Sponsors
Study design
Eligibility
Inclusion criteria
* Elective cardiac surgery
Exclusion criteria
* Emergency surgery * Age ≤ 18 years * The clinical situation is unstable, such as frequent occurrence of coronary ischemia events, unstable heart failure, or acute events leading to severe discomfort symptoms or changes in vital signs * Unable to cooperate in completing research data collection due to severe neurological and psychiatric abnormalities or other reasons * Duration of postoperative ventilation \> 48 hours or inability to obtain scale data on the first day after surgery
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| One-dimensional matrix vector composed of five frailty scale results | Before and after surgery, up to 2 weeks | Consisting of five frailty scales: Edmonton frailty scale, FRAIL frailty scale, Fried frailty scale, Clinical frailty scale, and SPPB |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| 1-year adverse events | 1 year post operative | Including death, readmission, stroke, myocardial infarction, renal insufficiency or renal failure, dialysis, atrial fibrillation, peripheral vascular embolism, bleeding events, heart failure |
| EQ-5D score | 1 year post operative | The score of EQ-5D questionnaire |
| QOR-15 score | 1 year post operative | The score of QOR-15 questionnaire |
| Edmonton frailty scale score | 1 year post operative | The Edmonton frailty scale consists of 11 items for a composite score of 0 to 17, and higher scores mean a worse outcome. |
| FRAIL frailty scale score | 1 year post operative | The FRAIL frailty scale consists of 5 items, with 3 of 5 required to diagnose frailty. |
| 30-day adverse events | 30 days post operative | Including death, readmission, stroke, myocardial infarction, renal insufficiency or renal failure, dialysis, atrial fibrillation, peripheral vascular embolism, bleeding events, heart failure |
| Clinical frailty scale score | 1 year post operative | The Clinical frailty scale is scored 1 to 9 based on a semiquantitative evaluation of the patient's symptoms, mobility, inactivity, exhaustion, and disability for basic activities of daily living and instrumental activities of daily living, and higher scores mean a worse outcome. |
| Short Physical Performance Battery scale score | 1 year post operative | The Short Physical Performance Battery scale consists of 3 physical tests, with each scored 0 to 4 for a composite score of 0 to 12, and higher scores mean a better outcome. |
| Perioperative adverse events | From surgery to discharge, up to 7 days | Including all cause death, stroke, renal insufficiency, deep sternal wound infection, and reoperation |
| Area under receiver operating curve (AUC) | At the end of follow-up (1 mouth) | Area under receiver operating curve of algorithm in predicting frailty scales and outcomes |
| Fried frailty scale score | 1 year post operative | The Fried frailty scale consists of 5 items, with 3 of 5 required to diagnose frailty. |
Countries
China