1
|
Sariyer G, Ataman MG. How machine learning facilitates decision making in emergency departments: Modelling diagnostic test orders. Int J Clin Pract 2021; 75:e14980. [PMID: 34637191 DOI: 10.1111/ijcp.14980] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/08/2021] [Accepted: 10/10/2021] [Indexed: 11/28/2022] Open
Abstract
OBJECTIVES Since emergency departments (EDs) are responsible for providing initial care for patients who may need urgent medical care, they are highly sensitive to increased patient delays. A key factor that increases patient delays is ordering diagnostic tests. Therefore, understanding the factors increasing diagnostic test orders and proposing efficient models may facilitate decision making in EDs. METHODS Month and week of the year, day of the week, and daily numbers of patients encoded based on 21 different ICD-10 codes were used as input variables. Daily test frequencies of patients requiring tests from laboratory and imaging services were modelled separately by linear regression models. Although significance of the input variables was identified based on these models, obtained forecasts and residuals were further processed by machine learning techniques to obtain hybrid models. RESULTS Day of the week, and number of patients with ICD-10 codes of 'A00-B99', 'I00-I99', 'J00-J99', 'M00-M99' and 'R00-R99' were significant in both test types. In addition to these, although daily patient frequencies with 'H60-H95', 'N00-N99' and 'O00-O9A' were significant for laboratory services, 'L00-L99', 'S00-T88' and 'Z00-Z99' were significant for imaging services. Although prediction accuracies of regression models were, respectively, as 93.658% and 95.028% for laboratory and imaging services modelling, they increased to 99.997% and 99.995% with the machine learning-integrated hybrid model. CONCLUSION The significant factors identified here can predict increases in use of laboratory and imaging services. This could enable these services to be prepared in advance to reduce ED patient delays, thereby reducing ED overcrowding. The proposed model may also be efficiently used for decision making.
Collapse
Affiliation(s)
| | - Mustafa Gökalp Ataman
- Department of Emergency Medicine, Çiğli Training and Research Hospital, Bakırçay University, Izmir, Turkey
| |
Collapse
|
2
|
Zhang S, Yang Y, Xie X, Li H, Han R, Hou J, Sun J, Qian ZM, Wu S, Huang C, Howard SW, Tian F, Deng W, Lin H. The effect of temperature on cause-specific mental disorders in three subtropical cities: A case-crossover study in China. ENVIRONMENT INTERNATIONAL 2020; 143:105938. [PMID: 32688157 DOI: 10.1016/j.envint.2020.105938] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/13/2020] [Revised: 06/28/2020] [Accepted: 06/30/2020] [Indexed: 06/11/2023]
Abstract
BACKGROUND Little is known about the association between ambient temperature and cause-specific mental disorders, especially in subtropical areas. OBJECTIVE To investigate the effect of ambient temperature on mental disorders in subtropical cities. METHOD Daily morbidity data for mental disorders in three Chinese cities (Shenzhen, Zhaoqing, and Huizhou) were collected from medical record systems of local psychiatric specialist hospitals, covering patients of all ages. Case-crossover design combined with a distributed lag nonlinear model (DLNM) was used to assess the nonlinear and delayed effects of temperatures on five specific mental disorders (affective disorders, anxiety, depressive disorders, schizophrenia, and organic mental disorders), with analyses stratified by gender and age. The temperature of minimum effect was used as the reference value to calculate estimates. RESULTS We observed inversed J-shaped exposure-response curves between temperature and mental morbidity and observed that low temperatures had a significant and prolonged effect on most types of mental disorders in the three cities. For example, the effect of the cold (2.5th percentile) on anxiety was consistently observed in the three cities with an odds ratio (OR) of 1.29 (95% CI: 1.06-1.57) in Zhaoqing, 1.26 (95% CI: 1.18-1.34) in Shenzhen, and 1.45 (95% CI: 1.17-1.81) in Huizhou. Low temperature was also associated with an increased risk of depressive disorders and schizophrenia. For the high temperature exposure (97.5th percentile), we only observed a significant, harmful effect on anxiety [OR = 1.30 (95% CI: 1.08, 1.58) in Shenzhen, OR = 1.16 (95% CI: 1.00, 1.34) in Zhaoqing], affective disorders [OR = 1.32 (95% CI: 1.08, 1.62) in Shenzhen], and schizophrenia [OR = 1.24 (95% CI: 1.03, 1.48) in Zhaoqing, OR = 1.03 (95% CI: 1.00, 1.06) in Huizhou]. CONCLUSIONS Our study suggests that both low and high temperatures might be important drivers of morbidity from mental disorders, and low temperature may have a more general and wide-spread effect on this cause-specific morbidity than high temperature.
Collapse
Affiliation(s)
- Shiyu Zhang
- Department of Epidemiology, School of Public Health, Sun Yat-sen University, Guangzhou, China
| | - Yin Yang
- Department of Epidemiology, School of Public Health, Sun Yat-sen University, Guangzhou, China
| | - XinHui Xie
- Brain Function and Psychosomatic Medicine Institute, The Second People's Hospital of Huizhou, Huizhou, Guangdong, China
| | - Huan Li
- Department of Epidemiology, School of Public Health, Sun Yat-sen University, Guangzhou, China
| | - Rong Han
- Department of Psychiatry, Shenzhen Kangning Hospital, Shenzhen Mental Health Center, Shenzhen, Guangdong, China
| | - Jiesheng Hou
- The Third People's Hospital of Zhaoqing, Guangdong, China
| | - Jia Sun
- Department of Epidemiology and Biostatistics, College for Public Health & Social Justice, Saint Louis University, USA
| | - Zhengmin Min Qian
- Department of Epidemiology and Biostatistics, College for Public Health & Social Justice, Saint Louis University, USA
| | - Shaowei Wu
- Department of Occupational and Environmental Health Sciences, School of Public Health, Peking University, China
| | - Cunrui Huang
- Health Management and Policy, School of Public Health, Sun Yat-Sen University, Guangzhou, China
| | - Steven W Howard
- Department of Epidemiology and Biostatistics, College for Public Health & Social Justice, Saint Louis University, USA
| | - Fei Tian
- Department of Epidemiology, School of Public Health, Sun Yat-sen University, Guangzhou, China
| | - WenFeng Deng
- Brain Function and Psychosomatic Medicine Institute, The Second People's Hospital of Huizhou, Huizhou, Guangdong, China.
| | - Hualiang Lin
- Department of Epidemiology, School of Public Health, Sun Yat-sen University, Guangzhou, China.
| |
Collapse
|