1
|
Kita K, Fujimori T, Suzuki Y, Kaito T, Takenaka S, Kanie Y, Furuya M, Wataya T, Nishigaki D, Sato J, Tomiyama N, Okada S, Kido S. Automated entry of paper-based patient-reported outcomes: Applying deep learning to the Japanese orthopaedic association back pain evaluation questionnaire. Comput Biol Med 2024; 172:108197. [PMID: 38452472 DOI: 10.1016/j.compbiomed.2024.108197] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2023] [Revised: 02/05/2024] [Accepted: 02/18/2024] [Indexed: 03/09/2024]
Abstract
BACKGROUND Health-related patient-reported outcomes (HR-PROs) are crucial for assessing the quality of life among individuals experiencing low back pain. However, manual data entry from paper forms, while convenient for patients, imposes a considerable tallying burden on collectors. In this study, we developed a deep learning (DL) model capable of automatically reading these paper forms. METHODS We employed the Japanese Orthopaedic Association Back Pain Evaluation Questionnaire, a globally recognized assessment tool for low back pain. The questionnaire comprised 25 low back pain-related multiple-choice questions and three pain-related visual analog scales (VASs). We collected 1305 forms from an academic medical center as the training set, and 483 forms from a community medical center as the test set. The performance of our DL model for multiple-choice questions was evaluated using accuracy as a categorical classification task. The performance for VASs was evaluated using the correlation coefficient and absolute error as regression tasks. RESULT In external validation, the mean accuracy of the categorical questions was 0.997. When outputs for categorical questions with low probability (threshold: 0.9996) were excluded, the accuracy reached 1.000 for the remaining 65 % of questions. Regarding the VASs, the average of the correlation coefficients was 0.989, with the mean absolute error being 0.25. CONCLUSION Our DL model demonstrated remarkable accuracy and correlation coefficients when automatic reading paper-based HR-PROs during external validation.
Collapse
Affiliation(s)
- Kosuke Kita
- Department of Artificial Intelligence Diagnostic Radiology, Graduate School of Medicine, Osaka University, Suita, Osaka, Japan
| | - Takahito Fujimori
- Department of Orthopedic Surgery, Graduate School of Medicine, Osaka University, Osaka, Japan.
| | - Yuki Suzuki
- Department of Artificial Intelligence Diagnostic Radiology, Graduate School of Medicine, Osaka University, Suita, Osaka, Japan
| | - Takashi Kaito
- Department of Orthopedic Surgery, Osaka Rosai Hospital, Osaka, Japan
| | - Shota Takenaka
- Department of Orthopedic Surgery, Japan Community Health Care Organization Osaka Hospital, Osaka, Japan
| | - Yuya Kanie
- Department of Orthopedic Surgery, Graduate School of Medicine, Osaka University, Osaka, Japan
| | - Masayuki Furuya
- Department of Orthopedic Surgery, Graduate School of Medicine, Osaka University, Osaka, Japan
| | - Tomohiro Wataya
- Department of Artificial Intelligence Diagnostic Radiology, Graduate School of Medicine, Osaka University, Suita, Osaka, Japan
| | - Daiki Nishigaki
- Department of Artificial Intelligence Diagnostic Radiology, Graduate School of Medicine, Osaka University, Suita, Osaka, Japan
| | - Junya Sato
- Department of Artificial Intelligence Diagnostic Radiology, Graduate School of Medicine, Osaka University, Suita, Osaka, Japan
| | - Noriyuki Tomiyama
- Department of Artificial Intelligence Diagnostic Radiology, Graduate School of Medicine, Osaka University, Suita, Osaka, Japan
| | - Seiji Okada
- Department of Orthopedic Surgery, Graduate School of Medicine, Osaka University, Osaka, Japan
| | - Shoji Kido
- Department of Artificial Intelligence Diagnostic Radiology, Graduate School of Medicine, Osaka University, Suita, Osaka, Japan
| |
Collapse
|