Using Data Analytics to Predict Hospital Mortality in Sepsis Patients

Abstract

Predictive analytics can be used to anticipate the risks associated with some patients, and prediction models can be employed to alert physicians and allow timely proactive interventions. Recently, health care providers have been using different types of tools with prediction capabilities. Sepsis is one of the leading causes of in-hospital death in the United States and worldwide. In this study, the authors used a large medical dataset to develop and present a model that predicts in-hospital mortality among Sepsis patients. The predictive model was developed using a dataset of more than one million records of hospitalized patients. The independent predictors of in-hospital mortality were identified using the chi-square automatic interaction detector. The authors found that adding hospital attributes to the predictive model increased the accuracy from 82.08% to 85.3% and the area under the curve from 0.69 to 0.84, which is favorable compared to using only patients' attributes. The authors discuss the practical and research contributions of using a predictive model that incorporates both patient and hospital attributes in identifying high-risk patients.

The path from big data analytics capabilities to value in hospitals: a scoping review

“…The benefits that are the most frequently expected are operational ( n =83). BDA is expected to help improve the quality of clinical decisions ( n =34) [ 39 , 45 , 57 , 77 ] and outcomes ( n =27) [ 37 , 53 , 54 , 58 , 61 , 78 ]. It is also expected to enable cost-reduction ( n =38) by reducing unnecessary care [ 41 , 56 , 64 , 79 – 81 ] and admissions [ 58 , 82 , 83 ]; productivity gains ( n =26) by optimizing resource usage in care and administrative units [ 32 , 84 , 85 ]; or service improvement ( n =27) by providing healthcare professionals new operational tools to support their practices [ 44 , 82 ].…”

Artificial Intelligence for Healthcare in India

“…It addresses both the lack of skilled doctors (Economic Times, 2018) among a multitude of ways within healthcare (Saha, 2018). It can be used to address data quality issues with Electronic Health Records (EHR) data, so it then may be used in applications such as predictive modelling in preventative health programs or predictive therapy (Eubanks, 2017;Khumalo et al, 2019;Alnsour et al, 2019). It is encouraging to note that the AI technology is found to have contributed effective supports to the Indian healthcare system.…”