1
|
Lin PC, Chang WS, Hsiao KY, Liu HM, Shia BC, Chen MC, Hsieh PY, Lai TW, Lin FH, Chang CC. Development of a Machine Learning Algorithm to Correlate Lumbar Disc Height on X-rays with Disc Bulging or Herniation. Diagnostics (Basel) 2024; 14:134. [PMID: 38248010 PMCID: PMC10814412 DOI: 10.3390/diagnostics14020134] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2023] [Revised: 12/28/2023] [Accepted: 01/02/2024] [Indexed: 01/23/2024] Open
Abstract
Lumbar disc bulging or herniation (LDBH) is one of the major causes of spinal stenosis and related nerve compression, and its severity is the major determinant for spine surgery. MRI of the spine is the most important diagnostic tool for evaluating the need for surgical intervention in patients with LDBH. However, MRI utilization is limited by its low accessibility. Spinal X-rays can rapidly provide information on the bony structure of the patient. Our study aimed to identify the factors associated with LDBH, including disc height, and establish a clinical diagnostic tool to support its diagnosis based on lumbar X-ray findings. In this study, a total of 458 patients were used for analysis and 13 clinical and imaging variables were collected. Five machine-learning (ML) methods, including LASSO regression, MARS, decision tree, random forest, and extreme gradient boosting, were applied and integrated to identify important variables for predicting LDBH from lumbar spine X-rays. The results showed L4-5 posterior disc height, age, and L1-2 anterior disc height to be the top predictors, and a decision tree algorithm was constructed to support clinical decision-making. Our study highlights the potential of ML-based decision tools for surgeons and emphasizes the importance of L1-2 disc height in relation to LDBH. Future research will expand on these findings to develop a more comprehensive decision-supporting model.
Collapse
Affiliation(s)
- Pao-Chun Lin
- Department of Biomedical Engineering, National Taiwan University, Taipei City 10617, Taiwan; (P.-C.L.); (F.-H.L.)
- Department of Neurosurgery, Fu Jen Catholic University Hospital, Fu Jen Catholic University, New Taipei City 24352, Taiwan
| | - Wei-Shan Chang
- Graduate Institute of Business Administration, College of Management, Fu Jen Catholic University, New Taipei City 24352, Taiwan; (W.-S.C.); (K.-Y.H.); (B.-C.S.); (M.-C.C.)
- Artificial Intelligence Development Center, Fu Jen Catholic University, New Taipei City 24352, Taiwan
| | - Kai-Yuan Hsiao
- Graduate Institute of Business Administration, College of Management, Fu Jen Catholic University, New Taipei City 24352, Taiwan; (W.-S.C.); (K.-Y.H.); (B.-C.S.); (M.-C.C.)
- Artificial Intelligence Development Center, Fu Jen Catholic University, New Taipei City 24352, Taiwan
| | - Hon-Man Liu
- Department of Radiology, Fu Jen Catholic University Hospital, Fu Jen Catholic University, New Taipei City 24352, Taiwan;
| | - Ben-Chang Shia
- Graduate Institute of Business Administration, College of Management, Fu Jen Catholic University, New Taipei City 24352, Taiwan; (W.-S.C.); (K.-Y.H.); (B.-C.S.); (M.-C.C.)
- Artificial Intelligence Development Center, Fu Jen Catholic University, New Taipei City 24352, Taiwan
| | - Ming-Chih Chen
- Graduate Institute of Business Administration, College of Management, Fu Jen Catholic University, New Taipei City 24352, Taiwan; (W.-S.C.); (K.-Y.H.); (B.-C.S.); (M.-C.C.)
- Artificial Intelligence Development Center, Fu Jen Catholic University, New Taipei City 24352, Taiwan
| | - Po-Yu Hsieh
- Industrial Technology Research Institute (ITRI), Hsinchu City 310401, Taiwan; (P.-Y.H.); (T.-W.L.)
| | - Tseng-Wei Lai
- Industrial Technology Research Institute (ITRI), Hsinchu City 310401, Taiwan; (P.-Y.H.); (T.-W.L.)
| | - Feng-Huei Lin
- Department of Biomedical Engineering, National Taiwan University, Taipei City 10617, Taiwan; (P.-C.L.); (F.-H.L.)
| | - Che-Cheng Chang
- Department of Neurology, Fu Jen Catholic University Hospital, Fu Jen Catholic University, New Taipei City 24352, Taiwan
- PhD Program in Nutrition and Food Science, Fu Jen Catholic University, New Taipei City 24352, Taiwan
| |
Collapse
|
2
|
Okuzu Y, Goto K, Kuroda Y, Kawai T, Matsuda S. How Do Spinal Parameters Change in Patients Who Have Improvement of Low Back Pain After Total Hip Arthroplasty? A Propensity Score-Matched Cohort Study. J Arthroplasty 2024; 39:132-137. [PMID: 37331437 DOI: 10.1016/j.arth.2023.06.021] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/10/2023] [Revised: 06/09/2023] [Accepted: 06/09/2023] [Indexed: 06/20/2023] Open
Abstract
BACKGROUND Many studies have demonstrated that low back pain (LBP) improves after total hip arthroplasty (THA). However, the mechanism underlying this improvement remains unclear. We aimed to investigate changes in the spinal parameters of patients who had LBP improvement after THA to elucidate the mechanism of LBP improvement. METHODS We included 261 patients who underwent primary THA between December 2015 and June 2021 and had a preoperative visual analog scale score of ≥ 2 for LBP. The patients were classified into the LBP-improved or LBP-continued groups based on the visual analog scale for LBP at 1 year after THA. Preoperative and postoperative changes in the coronal and sagittal spinal parameters were compared between the 2 groups after propensity score matching for age, sex, body mass index, and preoperative spinal parameters. RESULTS A total of 161 patients (61.7%) were classified into the LBP-improved group. After 85 patients in both groups were matched, the LBP-improved group showed significant differences in spinal parameter changes, which were a higher lumbar lordosis (LL) (P = .04) and lower sagittal vertical axis (SVA) (P = .02) and pelvic incidence (PI) minus LL (PI-LL) (P = .01) postoperatively, whereas the LBP-continued group showed worsened changes in LL and SVA and PI-LL mismatch. CONCLUSION Patients who had LBP improvement after THA had significant differences in spinal parameter changes in LL, SVA, and PI-LL. These spinal parameters may be the key factors in the mechanism of LBP improvement after THA.
Collapse
Affiliation(s)
- Yaichiro Okuzu
- Department of Orthopaedic Surgery, Kyoto University Graduate School of Medicine, Sakyo-ku, Kyoto, Japan
| | - Koji Goto
- Department of Orthopaedic Surgery, Kyoto University Graduate School of Medicine, Sakyo-ku, Kyoto, Japan
| | - Yutaka Kuroda
- Department of Orthopaedic Surgery, Kyoto University Graduate School of Medicine, Sakyo-ku, Kyoto, Japan
| | - Toshiyuki Kawai
- Department of Orthopaedic Surgery, Kyoto University Graduate School of Medicine, Sakyo-ku, Kyoto, Japan
| | - Shuichi Matsuda
- Department of Orthopaedic Surgery, Kyoto University Graduate School of Medicine, Sakyo-ku, Kyoto, Japan
| |
Collapse
|