Feasibility and Validation of a Clinical Decision Support System for Diagnosis of Low-Back Pain

File
Francis Fatoye, Isaiah Oyewole, Israel Adetuwo, Ayobami Babalola, Ishaya Peni Gambo, Tadesse Gebrye, Oluwadare Esan, Michael Egwu, Chidozie Mbada
Purpose:

This study aimed to test the feasibility and validation of a CDSS based on Nwugarian Spinal Manual Therapy (NSMT) for low-back pain (LBP) diagnosis. 

Methods:

This mixed-methods study involved patients with LBP and clinicians (physiotherapists and orthopaedic surgeons). A three-interphase (patient (self-service login), clinician (interviews and tests login), and admin interphase)) CDSS developed on 10 provocative tests and 22 consensus questions algorithm was developed and tested. The feasibility testing of the CDSS was done via survey and in-depth interviews. Validation of the CDSS was in comparison with clinician diagnosis; and two diagnostic checklists (McKenzie Institute’s Lumbar Spine Assessment Algorithm (MILSAA), and Evidence-Based Practical Diagnostic Checklist (EBPDC) approaches for LBP. Sensitivity and specificity were used to test the accuracy of the CDSS for diagnostic testing. Descriptive statistics were used to summarise the findings.


Results:

The mean usability rating, perceived impact scores and total quality rating scores were 28.8±0.59 (out of 50), 25.0±3.65 (out of 30), and 18.3±0.57 (out of 22.5), respectively. There was a significant association between CDSS and MILSAA's assessment (χ2 = 5.593; p = 0.018). The sensitivity and specificity of the CDSS to diagnose LBP compared with orthopaedists, physiotherapists, MILSAA and EBPDC assessments were 60.0%, 64.7%, 85.7%, and 93.3%, respectively; and 16.7%, 50.0%, 65.2%, and 100%, respectively. The CDSS was considered feasible based on acceptability, satisfaction and implementability. 

Conclusion(s):

The CDSS demonstrated moderate to high sensitivity and specificity in identifying serious spinal pathologies, as validated by clinical experts and standard checklists. 

Implications:

A CDSS based on the NSMT is a feasible and user-friendly tool to assist in the clinical diagnosis of LBP, aiming to enhance patient outcomes and improve their quality of care.  

Funding acknowledgements:
There was no funding received in relation to the study.
Keywords:
Validation
Clinical decision support systems
Low back pain
Primary topic:
Musculoskeletal
Second topic:
Pain and pain management
Third topic:
Health promotion and wellbeing/healthy ageing/physical activity
Did this work require ethics approval?:
Yes
Name the institution and ethics committee that approved your work:
Obafemi Awolowo University Teaching Hospitals Complex
Provide the ethics approval number:
ERC/2021/10/14
Has any of this material been/due to be published or presented at another national or international conference prior to the World Physiotherapy Congress 2025?:
No

Back to the listing