Skip to main navigation menu Skip to main content Skip to site footer

Original article

Vol. 150 No. 4748 (2020)

RheumaTool, a novel clinical decision support system for the diagnosis of rheumatic diseases, and its first validation in a retrospective chart analysis

Cite this as:
Swiss Med Wkly. 2020;150:w20369



RheumaTool is a clinical decision support system designed to support the diagnostic process in rheumatology by presenting a differential diagnosis list after the input of clinical information. The objective of this study was to evaluate the performance of RheumaTool in detecting the correct diagnosis in referrals to a rheumatology clinic.


In this retrospective chart analysis, data were gathered from patients with musculoskeletal complaints and an uncertain diagnosis who were referred to a Swiss tertiary rheumatology outpatient clinic. Data were entered into RheumaTool in a standardised fashion, while the principal diagnoses in the medical reports were blinded. RheumaTool’s output was compared to the correct diagnoses, established either by widely accepted diagnostic criteria or through the expert consensus of independent rheumatologists. Diagnostic precision, the primary endpoint, was defined as the proportion of correctly diagnosed cases among all cases.


One hundred and sixty cases with 46 different diseases were included in this analysis. RheumaTool correctly diagnosed 40% (95% confidence interval 32.4–48.1) of all cases. In 63.8% (95% confidence interval 55.7–71.1), the correct diagnosis was present in a differential diagnosis list consisting of a median of two diagnoses.


In this first validation, RheumaTool provides a useful list of differential diagnoses. However, there is not sufficient diagnostic reliability for unfiltered data entry, especially in patients with multiple concomitant musculoskeletal disorders. This must be taken into account when using RheumaTool.


  1. Chaudhry B, Wang J, Wu S, Maglione M, Mojica W, Roth E, et al. Systematic review: impact of health information technology on quality, efficiency, and costs of medical care. Ann Intern Med. 2006;144(10):742–52. doi:.
  2. IBM. O’Toole L. Versus Arthritis, Launching a cognitive virtual assistant to provide personalised support 2019. [cited 2019 Sept 26]. Available from:
  3. Gossec L, Guyard F, Leroy D, Lafargue T, Seiler M, Jacquemin C, et al. Detection of flares by decrease in physical activity, collected using wearable activity trackers, in rheumatoid arthritis or axial spondyloarthritis: an application of Machine-Learning analyses in rheumatology. Arthritis Care Res (Hoboken). 2019;71(10):1336–43. doi:.
  4. Lezcano-Valverde JM, Salazar F, León L, Toledano E, Jover JA, Fernandez-Gutierrez B, et al. Development and validation of a multivariate predictive model for rheumatoid arthritis mortality using a machine learning approach. Sci Rep. 2017;7(1):10189. doi:.
  5. Hunt DL, Haynes RB, Hanna SE, Smith K. Effects of computer-based clinical decision support systems on physician performance and patient outcomes: a systematic review. JAMA. 1998;280(15):1339–46. doi:.
  6. Beeler PE, Bates DW, Hug BL. Clinical decision support systems. Swiss Med Wkly. 2014;144:w14073.
  7. Alder H, Michel BA, Marx C, Tamborrini G, Langenegger T, Bruehlmann P, et al. Computer-based diagnostic expert systems in rheumatology: where do we stand in 2014? Int J Rheumatol. 2014;2014:672714. doi:.
  8. Leitich H, Kiener HP, Kolarz G, Schuh C, Graninger W, Adlassnig KP. A prospective evaluation of the medical consultation system CADIAG-II/RHEUMA in a rheumatological outpatient clinic. Methods Inf Med. 2001;40(3):213–20. doi:.
  9. Godo L, de Mántaras RL, Puyol-Gruart J, Sierra C. Renoir, Pneumon-IA and Terap-IA: three medical applications based on fuzzy logic. Artif Intell Med. 2001;21(1-3):153–62. doi:.
  10. Athreya BH, Cheh ML, Kingsland LC, 3rd. Computer-assisted diagnosis of pediatric rheumatic diseases. Pediatrics. 1998;102(4):E48. doi:.
  11. Schewe S, Schreiber MA. Stepwise development of a clinical expert system in rheumatology. Clin Investig. 1993;71(2):139–44. doi:.
  12. Moens HJ, van der Korst JK. Development and validation of a computer program using Bayes’s theorem to support diagnosis of rheumatic disorders. Ann Rheum Dis. 1992;51(2):266–71. doi:.
  13. Schewe S, Herzer P, Krüger K. Prospective application of an expert system for the medical history of joint pain. Klin Wochenschr. 1990;68(9):466–71. doi:.
  14. Fries JF. Experience counting in sequential computer diagnosis. Arch Intern Med. 1970;126(4):647–51. doi:.
  15. Rodríguez-González A, Torres-Niño J, Mayer MA, Alor-Hernandez G, Wilkinson MD. Analysis of a multilevel diagnosis decision support system and its implications: a case study. Comput Math Methods Med. 2012;2012:367345. doi:.
  16. Bordage G. Why did I miss the diagnosis? Some cognitive explanations and educational implications. Acad Med. 1999;74(10, Suppl):S138–43. doi:.
  17. Braithwaite RS, Scotch M. Using value of information to guide evaluation of decision supports for differential diagnosis: is it time for a new look? BMC Med Inform Decis Mak. 2013;13(1):105. doi:.
  18. Hripcsak G, Wilcox A. Reference standards, judges, and comparison subjects: roles for experts in evaluating system performance. J Am Med Inform Assoc. 2002;9(1):1–15. doi:.
  19. Miller RA. Evaluating evaluations of medical diagnostic systems. J Am Med Inform Assoc. 1996;3(6):429–31. doi:.
  20. Ammenwerth E, Nykänen P, Rigby M, de Keizer N. Clinical decision support systems: need for evidence, need for evaluation. Artif Intell Med. 2013;59(1):1–3. doi:.
  21. Berner ES. Diagnostic decision support systems: how to determine the gold standard? J Am Med Inform Assoc. 2003;10(6):608–10. doi:.

Most read articles by the same author(s)