VERTIS-CV Event Prediction (WATCH-DM surrogate) Calculator
- VERTIS-CV Event Prediction — implementation notes and clinical context (WATCH-DM surrogate)
This tool calculates the integer WATCH-DM score (an externally published, integer-based risk score developed to predict 5-year incident heart-failure hospitalization among patients with type 2 diabetes). WATCH-DM combines routinely available clinical measures (age, BMI, blood pressure), simple blood tests (fasting plasma glucose, creatinine, HDL) and ECG/QRS and prior coronary events into an integer sum that stratifies individuals into very low, low, average, high, and very high HF risk groups. WATCH-DM has been validated in multiple cohorts and has been used in secondary analyses of cardiovascular outcome trial datasets (including VERTIS-CV) to identify patients at differing absolute risk and potential differential absolute treatment benefit from SGLT2 inhibition.
Important: I did not find a peer-reviewed publication that names a separate, standalone “VERTIS-CV Event Prediction Score.” Rather, VERTIS-CV has been analyzed using established HF risk tools (e.g., WATCH-DM, TRS-HFDM, biomarker-based HHF scores). The implementation above uses the published WATCH-DM structure (components and integer ranges) and maps routine clinical values to integer buckets to produce a total score and conventional WATCH-DM risk categories. For highest fidelity to the original integer table, you may replace the thresholds in the PHP code above with any exact table values you prefer from the original paper or validation tables; if you want, paste the published table here and I will update the code to exactly match the published buckets and point allocations.
Clinical interpretation summary: WATCH-DM is designed to flag patients with T2DM at higher risk of heart-failure hospitalization over a multi-year horizon; higher WATCH-DM points associate with higher absolute HF risk and have been shown in trial re-analyses to identify subgroups with greater absolute HF event rates (and greater absolute benefit from SGLT2 inhibitors in HF prevention contexts). This tool is educational / point-of-care risk stratification and is not in itself a management guideline; apply clinical judgement and guideline recommendations when translating predicted risk into therapy decisions.
References:
Segar MW, Vaduganathan M, Patel KV, et al. Machine learning to predict the risk of incident heart failure hospitalization among patients with diabetes: the WATCH-DM risk score. Diabetes Care. 2019;42(12):2298–2306.
Segar MW, et al. Validation of WATCH-DM and TRS-HFDM risk scores (secondary analyses/validation). Journal/AHA publication. 2022.
Cannon CP, Pratley R, Dagogo-Jack S, et al., for the VERTIS-CV Investigators. Cardiovascular Outcomes with Ertugliflozin in Type 2 Diabetes. N Engl J Med. 2020;383:1425–1435. (VERTIS-CV primary trial publication; secondary analyses applied risk scores to VERTIS-CV data).
Discussion
No discussions yet. Be the first to comment.