Research on Predicting Acute Hypotension Based on Interpretable Machine Learning

Yan Zhao (), Lijing Jia and Jing Li ()
Additional contact information
Yan Zhao: Beijing Jiaotong University
Lijing Jia: Beijing Jiaotong University
Jing Li: Chinese PLA General Hospital

A chapter in LISS 2023, 2024, pp 256-269 from Springer

Abstract: Abstract Acute hypotension is a common emergency of dangerous diseases, which can cause fainting or shock, lead to irreversible organ damage and even death of patients, and require timely and effective intervention after the occurrence. If patients with acute hypotension can be accurately identified in time and effective intervention measures can be taken, the mortality and disability rate can be greatly reduced. According to the inclusion and exclusion criteria, 1535 patients (214 Experimental Group and 1321 Control Group) were extracted from the intensive care medical information Mart (MIMIC) - IV, and the cross-sectional data were extracted. Data cleaning, missing value interpolation and other pre-processing processes were carried out. Feature engineering was used to select key indicators, A set of interpretable key indicator sets (Heart Rate, Systolic Blood Pressure, International Normalized Ratio, Diastolic Blood Pressure, Thrombin Time Measurement, Carbon Dioxide, Hemoglobin Measurement, White Blood Cells, Lactate) were obtained. Four machine learning algorithms, XGBoost, LR, KNN, MLP, were used to integrate the models, and the voting algorithm was used to establish and verify the prediction models of acute hypotension. The area under the receiver operating characteristic curve (AUROC) was used to evaluate the performance of the model. The results showed that the performance of voting’s integrated model was significantly better than that of other models’ time series data (AUROC = 0.973). Through the research of medical field based on machine learning and the construction of clinical acute hypotension prediction model, this paper hopes to make contributions to domestic emergency treatment in theory and practice.

Keywords: AHE; Machine Learning; Ensemble Learning; Hypotension (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-981-97-4045-1_20

Ordering information: This item can be ordered from
http://www.springer.com/9789819740451

DOI: 10.1007/978-981-97-4045-1_20

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().