Start Date
16-8-2018 12:00 AM
Description
Cancer, a major threat to public health worldwide, causes substantial financial burdens. Cancer readmission time interval, or Out-of-Hospital Days (OHD) between two consecutive hospital admissions, has been widely adopted as an important measure of healthcare service quality. However, there is a paucity of models focusing on OHD and associated risk factors due to limited access to cancer patients’ data and absence of important factors (e.g., geographic factors) in the data. We utilize OHD (>30) as the result of cancer patient’s conditions (e.g., personal, medical) and treatment costs. We analyze a sample of 22,231 admissions extracted from 635,261 cancer patient Electronic Health Records (EHR) from 190 hospitals in China. We apply text mining on free-form address fields to extract patients’ home address and hospitals’ location information. Using hierarchical linear regression, we find various types of factors significantly influence OHD: age, marital status, number of admissions and whether the treating hospital is in the same province as the patient.
Recommended Citation
Huangfu, Luwen; Hayne, Stephen; Ma, James; and Roberts, Nicholas, "Exploratory Study for Readmission in Cancer Patients" (2018). AMCIS 2018 Proceedings. 23.
https://aisel.aisnet.org/amcis2018/Health/Presentations/23
Exploratory Study for Readmission in Cancer Patients
Cancer, a major threat to public health worldwide, causes substantial financial burdens. Cancer readmission time interval, or Out-of-Hospital Days (OHD) between two consecutive hospital admissions, has been widely adopted as an important measure of healthcare service quality. However, there is a paucity of models focusing on OHD and associated risk factors due to limited access to cancer patients’ data and absence of important factors (e.g., geographic factors) in the data. We utilize OHD (>30) as the result of cancer patient’s conditions (e.g., personal, medical) and treatment costs. We analyze a sample of 22,231 admissions extracted from 635,261 cancer patient Electronic Health Records (EHR) from 190 hospitals in China. We apply text mining on free-form address fields to extract patients’ home address and hospitals’ location information. Using hierarchical linear regression, we find various types of factors significantly influence OHD: age, marital status, number of admissions and whether the treating hospital is in the same province as the patient.