Machine Learning, Microcirculatory Status, Near-infrared Vision
Conditions
Brief summary
The investigators aimed to combine the image of near-infrared vision and machine learning method to evaluate the microcirculatory status of critical ill patients.
Detailed description
The heat distribution of body is determined by the circulatory status. The investigators plan to the near-infrared vision to collect heat distribution information of limbs. Then, the machine learning method will be performed to recognize the subtle differences between images. Due to lack of golden standard of microcirculatory status, indirect parameters (such as lactate clearance, capillary refill time) and clinical outcomes will be recorded to evaluate the performance of maching learning model.
Interventions
DIAGNOSTIC_TESTNear-infrared Vision Photograph
The near-infrared image will be recorded (by a infrared camera connected to a laptop) for each enrolled patient
Sponsors
Shanghai Zhongshan Hospital
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Age≥18 years; * Patients who were transfered to our ICU.
Exclusion criteria
* Abnormalities of lower limbs arteries
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Hospital mortality | From date of admission to our ICU until the date of hospital discharge or date of death from any cause, whichever came first, assessed up to 2 months. | The rate of patients who died during hospital stay. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Lacteta clearance rate | When the near-infrared image is taken for a patient, the blood gas analysis will be performed immediately to get the value of lactate. After 2-hours, another blood gas analysis will be conducted to get the second value of lactete. | The percent change of lactate between lactates measured in two time points. This parameter was usually used to guide resuscitation in septic shock. |
| Capillary refill time (CRT) | When the near-infrared image is taken for a patient, the capillary refill time will be measured immediately. | A noninvasive parameter of peripheral perfusion status. CRT was measured by applying firm pressure to the ventral surface of the right index finger distal phalanx with a glass microscope slide. The pressure was increased until the skin was blank and then maintained for 10 seconds. The time for return of the normal skin color was registered with a chronometer, and a refill time greater than 3 seconds was defined as abnormal.(Hernández 2019.JAMA) |
Contacts
Primary ContactZhe Luo
Outcome results
None listed