Chaohsin Lin1, Shuofen Hsu1, Hsiao-Feng Lu2,3, Li-Fei Pan4, Yu-Hua Yan5. 1. Department of Risk Management and Insurance, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan. 2. Department of Anesthesiology, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan. 3. College of Medicine, Chang Gung University, Kaohsiung, Taiwan. 4. Department of Medical Affair Administration, Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan. 5. Department of Medical Research, Tainan Municipal Hospital (Managed by Show Chwan Medical Care Corporation), Tainan, Taiwan.
Abstract
BACKGROUND: The main purpose of this study is to predict the all-cause risk of 30-day readmission by employing the back-propagation neural network (BPNN) in comparison with traditional risk assessment tools of LACE index and HOSPITAL scores. METHODS: This was a retrospective cohort study from January 1st, 2018 to December 31st, 2019. A total of 55,688 hospitalizations from a medical center in Taiwan were examined. The LACE index (length of stay, acute admission, Charlson comorbidity index score, emergency department visits in previous 6 months) and HOSPITAL score (hemoglobin level at discharge, discharge from an Oncology service, sodium level at discharge, procedure during hospital stay, Index admission type, number of hospital admissions during the previous year, length of stay) are calculated. We employed variables from LACE index and HOSPITAL score as the input vector of BPNN for comparison purposes. RESULTS: The BPNN constructed in the current study has a considerably better ability with a C statistics achieved 0.74 (95% CI 0.73 to 0.75), which is statistically significant larger than that of the other two models using DeLong's test. Also, it was possible to achieve higher sensitivity (70.32%) without penalizing the specificity (71.76%) and accuracy (71.68%) at its optimal threshold, which is at the 20% of patients with the highest predicted risk. Moreover, it is much more informative than the other two methods because of a considerably higher LR+ and a lower LR-. CONCLUSION: Our findings suggest that more attention should be paid to methods based on non-linear classification systems, as they lead to substantial differences in risk-scores.
BACKGROUND: The main purpose of this study is to predict the all-cause risk of 30-day readmission by employing the back-propagation neural network (BPNN) in comparison with traditional risk assessment tools of LACE index and HOSPITAL scores. METHODS: This was a retrospective cohort study from January 1st, 2018 to December 31st, 2019. A total of 55,688 hospitalizations from a medical center in Taiwan were examined. The LACE index (length of stay, acute admission, Charlson comorbidity index score, emergency department visits in previous 6 months) and HOSPITAL score (hemoglobin level at discharge, discharge from an Oncology service, sodium level at discharge, procedure during hospital stay, Index admission type, number of hospital admissions during the previous year, length of stay) are calculated. We employed variables from LACE index and HOSPITAL score as the input vector of BPNN for comparison purposes. RESULTS: The BPNN constructed in the current study has a considerably better ability with a C statistics achieved 0.74 (95% CI 0.73 to 0.75), which is statistically significant larger than that of the other two models using DeLong's test. Also, it was possible to achieve higher sensitivity (70.32%) without penalizing the specificity (71.76%) and accuracy (71.68%) at its optimal threshold, which is at the 20% of patients with the highest predicted risk. Moreover, it is much more informative than the other two methods because of a considerably higher LR+ and a lower LR-. CONCLUSION: Our findings suggest that more attention should be paid to methods based on non-linear classification systems, as they lead to substantial differences in risk-scores.
Authors: Enrico G Ferro; Eric A Secemsky; Rishi K Wadhera; Eunhee Choi; Jordan B Strom; Jason H Wasfy; Yun Wang; Changyu Shen; Robert W Yeh Journal: Health Aff (Millwood) Date: 2019-04 Impact factor: 6.301
Authors: Keith D Lind; Claire M Noel-Miller; Lindsey R Sangaralingham; Nilay D Shah; Erik P Hess; Pamela Morin; M Fernanda Bellolio Journal: Med Care Res Rev Date: 2017-07-08 Impact factor: 3.929
Authors: Wenshuo Liu; Cooper Stansbury; Karandeep Singh; Andrew M Ryan; Devraj Sukul; Elham Mahmoudi; Akbar Waljee; Ji Zhu; Brahmajee K Nallamothu Journal: PLoS One Date: 2020-04-15 Impact factor: 3.240