1
|
Zulbayar S, Mollayeva T, Colantonio A, Chan V, Escobar M. Integrating unsupervised and supervised learning techniques to predict traumatic brain injury: A population-based study. INTELLIGENCE-BASED MEDICINE 2023; 8:100118. [PMID: 38222038 PMCID: PMC10785655 DOI: 10.1016/j.ibmed.2023.100118] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 01/16/2024]
Abstract
This work aimed to identify pre-existing health conditions of patients with traumatic brain injury (TBI) and develop predictive models for the first TBI event and its external causes by employing a combination of unsupervised and supervised learning algorithms. We acquired up to five years of pre-injury diagnoses for 488,107 patients with TBI and 488,107 matched control patients who entered the emergency department or acute care hospitals between April 1st, 2002, and March 31st, 2020. Diagnoses were obtained from the Ontario Health Insurance Plan (OHIP) database which contains province-wide claims data by physicians in Ontario, Canada for inpatient and outpatient services. A screening process was conducted on the OHIP diagnostic codes to limit the subsequent analysis to codes that were predictive of TBI, which concluded that 314 codes were significantly associated with TBI. The Latent Dirichlet Allocation (LDA) model was applied to the diagnostic codes and generated an optimal number of 19 topics that concur with published literature but also suggest other unexplored areas. Estimated word-topic probabilities from the LDA model helped us detect pre-morbid conditions among patients with TBI by uncovering the underlying patterns of diagnoses, meanwhile estimated document-topic probabilities were utilized in variable creation as form of a dimension reduction. We created 19 topic scores for each patient in the cohort which were utilized along with socio-demographic factors for Random Forest binary classifier models. Test set performances evaluated using area under the receiver operating characteristic curve (AUC) were: TBI event (AUC = 0.85), external cause of injury: falls (AUC = 0.85), struck by/against (AUC = 0.83), cyclist collision (AUC = 0.76), motor vehicle collision (AUC = 0.83). Our analysis successfully demonstrated the feasibility of using machine learning to predict TBI due to various external causes and identified the most important factors that contribute to this prediction.
Collapse
Affiliation(s)
- Suvd Zulbayar
- Dalla Lana School of Public Health, University of Toronto, Toronto, ON M5T 3M7, Canada
- Institute of Health and Policy, Management and Evaluation, University of Toronto, M5T 3M6, Canada
| | - Tatyana Mollayeva
- Dalla Lana School of Public Health, University of Toronto, Toronto, ON M5T 3M7, Canada
- Rehabilitation Sciences Institute, Temerty Faculty of Medicine, University of Toronto, Toronto, ON M5G 1V7, Canada
- Acquired Brain Injury Research Lab, Department of Occupational Science and Occupational Therapy, University of Toronto, Toronto, ON M5G 1V7, Canada
- KITE Research Institute, Toronto Rehabilitation Institute-University Health Network, Toronto, ON M5G 2A2, Canada
| | - Angela Colantonio
- Dalla Lana School of Public Health, University of Toronto, Toronto, ON M5T 3M7, Canada
- Rehabilitation Sciences Institute, Temerty Faculty of Medicine, University of Toronto, Toronto, ON M5G 1V7, Canada
- Acquired Brain Injury Research Lab, Department of Occupational Science and Occupational Therapy, University of Toronto, Toronto, ON M5G 1V7, Canada
- KITE Research Institute, Toronto Rehabilitation Institute-University Health Network, Toronto, ON M5G 2A2, Canada
- Institute of Health and Policy, Management and Evaluation, University of Toronto, M5T 3M6, Canada
- ICES, Toronto, ON, M4N 3M5, Canada
| | - Vincy Chan
- Rehabilitation Sciences Institute, Temerty Faculty of Medicine, University of Toronto, Toronto, ON M5G 1V7, Canada
- Acquired Brain Injury Research Lab, Department of Occupational Science and Occupational Therapy, University of Toronto, Toronto, ON M5G 1V7, Canada
- KITE Research Institute, Toronto Rehabilitation Institute-University Health Network, Toronto, ON M5G 2A2, Canada
- Institute of Health and Policy, Management and Evaluation, University of Toronto, M5T 3M6, Canada
| | - Michael Escobar
- Dalla Lana School of Public Health, University of Toronto, Toronto, ON M5T 3M7, Canada
| |
Collapse
|
2
|
Teterina A, Zulbayar S, Mollayeva T, Chan V, Colantonio A, Escobar M. Gender versus sex in predicting outcomes of traumatic brain injury: a cohort study utilizing large administrative databases. Sci Rep 2023; 13:18453. [PMID: 37891419 PMCID: PMC10611793 DOI: 10.1038/s41598-023-45683-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2023] [Accepted: 10/23/2023] [Indexed: 10/29/2023] Open
Abstract
Understanding the factors associated with elevated risks and adverse consequences of traumatic brain injury (TBI) is an integral part of developing preventive measures for TBI. Brain injury outcomes differ based on one's sex (biological characteristics) and gender (social characteristics reflecting norms and relationships), however, whether it is sex or gender that drives differences in early (30-day) mortality and discharge location post-TBI is not well understood. In the absence of a gender variable in existing data, we developed a method for "measuring gender" in 276,812 residents of Ontario, Canada who entered the emergency department and acute care hospitals with a TBI diagnostic code between April 1st, 2002, and March 31st, 2020. We applied logistic regression to analyse differences in diagnostic codes between the sexes and to derive a gender score that reflected social dimensions. We used the derived gender score along with a sex variable to demonstrate how it can be used to separate the relationship between sex, gender and TBI outcomes after severe TBI. Sex had a significant effect on early mortality after severe TBI with a rate ratio (95% confidence interval (CI)) of 1.54 (1.24-1.91). Gender had a more significant effect than sex on discharge location. A person expressing more "woman-like" characteristics had lower odds of being discharged to rehabilitation versus home with odds ratio (95% CI) of 0.54 (0.32-0.88). The method we propose offers an opportunity to measure a gender effect independently of sex on TBI outcomes.
Collapse
Affiliation(s)
- Anastasia Teterina
- Dalla Lana School of Public Health, University of Toronto, Health Sciences Building, 155 College Street, 6th Floor, Toronto, ON, M5T 3M7, Canada
| | - Suvd Zulbayar
- Dalla Lana School of Public Health, University of Toronto, Health Sciences Building, 155 College Street, 6th Floor, Toronto, ON, M5T 3M7, Canada
| | - Tatyana Mollayeva
- Dalla Lana School of Public Health, University of Toronto, Health Sciences Building, 155 College Street, 6th Floor, Toronto, ON, M5T 3M7, Canada
- KITE Research Institute, Toronto Rehabilitation Institute-University Health Network, Toronto, Canada
- Rehabilitation Sciences Institute, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada
- Acquired Brain Injury Research Lab, Department of Occupational Science and Occupational Therapy, University of Toronto, Toronto, Canada
| | - Vincy Chan
- KITE Research Institute, Toronto Rehabilitation Institute-University Health Network, Toronto, Canada
- Rehabilitation Sciences Institute, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada
- Acquired Brain Injury Research Lab, Department of Occupational Science and Occupational Therapy, University of Toronto, Toronto, Canada
- Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Canada
| | - Angela Colantonio
- Dalla Lana School of Public Health, University of Toronto, Health Sciences Building, 155 College Street, 6th Floor, Toronto, ON, M5T 3M7, Canada
- KITE Research Institute, Toronto Rehabilitation Institute-University Health Network, Toronto, Canada
- Rehabilitation Sciences Institute, Temerty Faculty of Medicine, University of Toronto, Toronto, Canada
- Acquired Brain Injury Research Lab, Department of Occupational Science and Occupational Therapy, University of Toronto, Toronto, Canada
- Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Canada
- ICES, Toronto, Canada
| | - Michael Escobar
- Dalla Lana School of Public Health, University of Toronto, Health Sciences Building, 155 College Street, 6th Floor, Toronto, ON, M5T 3M7, Canada.
| |
Collapse
|
3
|
Teterina A, Zulbayar S, Mollayeva T, Chan V, Colantonio A, Escobar M. Gender versus sex in predicting outcomes of traumatic brain injury: A cohort study utilizing large administrative databases. RESEARCH SQUARE 2023:rs.3.rs-2720937. [PMID: 37090525 PMCID: PMC10120777 DOI: 10.21203/rs.3.rs-2720937/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/25/2023]
Abstract
Understanding the factors associated with elevated risks and adverse consequences of traumatic brain injury (TBI) is an integral part of developing preventive measures for TBI. Brain injury outcomes differ based on one's sex (biological characteristics) and gender (social characteristics reflecting norms and relationships), however, whether it is sex or gender that drives differences in early (30-day) mortality and discharge location post-TBI event are unknown. In the absence of gender variable in existing data, we developed a method for "measuring gender" in 276,812 residents of Ontario, Canada who entered the emergency department and acute care hospitals with a TBI diagnostic code between April 1st, 2002 and March 31st, 2020. We analysed differences in diagnostic codes between the sexes to derive gender score that reflected social dimensions. Sex had a significant effect on early mortality after severe TBI with a rate ratio (95% confidence interval (CI)) of 1.54 (1.24-1.91). Gender had a more significant effect than sex on discharge location. A person expressing more female-like characteristics have lower odds of being discharged to rehabilitation versus home with odds ratio (95% CI) of 0.54 (0.32-0.88). The method we propose offers an opportunity to measure gender effect independently of sex on TBI outcomes.
Collapse
|