Evaluation of the Accuracy of the Smart Work Injury Management (SWIM) System to Assist Case Managers in Predicting the Work Disability of Injured Workers.
Yumiki Y K Yeung, Peter Q Chen, Peter H F Ng and 1 others
PMID 38874680WHAT IT FOUND
SWIM did not predict actual sick leave or permanent disability for 442 Hong Kong injury claims.
It matched only a 4-year case manager's non-litigated sick-leave estimate.
Key findings
01SWIM's sick-leave predictions were statistically similar to CM-A's for non-litigated cases.
02SWIM's permanent disability predictions were not statistically similar to actual outcomes or any case manager.
03The mean actual sick leave days and permanent disability percentages were higher than SWIM's mean predictions for both non-litigated and litigated cases.
STILL TO COME
How it was doneWhat they foundWhat it means for OTs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
Only three case managers were compared, so their estimates may not represent case managers in general. The case managers and SWIM did not receive psychosocial information, litigation status, or how the case evolved, which may have affected actual outcomes. The study used retrospective actual outcomes from resolved claims, so predictions were compared with what happened after the case progressed. Permanent disability data were incomplete and reported inconsistently: the paper says PD data were available for 267 of 442 cases, then uses 273 for PD analyses. The findings are specific to Hong Kong workers' compensation and insurance reserving context.
Declared interests
The paper lists funding from PolyU (UGC) and Hong Kong Polytechnic University. No other conflicts are reported.
The easy way to misread this
Do not conclude that SWIM is validated for predicting work disability. It did not match actual sick leave or permanent disability outcomes, and its only similarity was with a 4-year case manager's non-litigated sick-leave estimate.