Key result
Causal deep neural network predicts 1-year antihypertensive treatment success with ~48% F1 score.
Why the study?
To develop and validate a machine learning model to predict the most successful individual antihypertensive treatment.
Does a causal deep neural network-based machine learning model accurately predict 1-year antihypertensive treatment success (blood pressure control without moderate or severe adverse effects) and align with clinical guidelines in newly diagnosed primary hypertension patients?
Cohort (n=17,917)
Yes
Does a causal deep neural network-based machine learning model accurately predict 1-year antihypertensive treatment success (blood pressure control without moderate or severe adverse effects) and align with clinical guidelines in newly diagnosed primary hypertension patients?
A causal deep neural network model can personalize first-line hypertension therapy by predicting 1-year blood pressure control without moderate-to-severe adverse effects while achieving 95.7% alignment with JNC 8 clinical guidelines.
Answers are grounded in this paper and cite their sources.
Should not yet alter antihypertensive prescribing; leaves open prospective validation of causal neural networks in hypertension.
Objective: To develop and validate a machine learning model that predicts the most successful antihypertensive treatment for an individual. Patients and Methods: The causal, deep neural network-based model was trained on data from 16,917 newly diagnosed hypertensive patients attending Mayo Clinic's primary care practices from January 1, 2005, to December 31, 2021. Eligibility criteria included a diagnosis of primary hypertension, blood pressure and creatinine measurements before antihypertensive treatment, treatment within 9 months of diagnosis, and at least 1 year of follow up. The primary outcome was model performance in predicting the likelihood of a successful antihypertensive treatment 1 year from the start of treatment. Treatment success was defined as achieving blood pressure control with no moderate or severe adverse effects. Model validation and guideline agreement was assessed on 1000 patients. Results: In the training set of 16,917 participants (60.8±14.7 years; 8344 [49.3%] women), 33.8% achieved blood pressure control without moderate or severe adverse effects for at least a year with initial treatment. The most common treatment was angiotensin-converting enzyme inhibitor (39.1% average success), and the most successful was angiotensin-converting enzyme inhibitor-thiazide combination (44.4% average success). Our custom-built causal, deep neural network-based model exhibited the highest accuracy in predicting individualized treatment success with a precision of 51.7%, recall of 44.4%, and F1 score of 47.8%. Compared with actual physician practice on the validation set (77.9% agreement), the algorithm aligned with the Eighth Joint National Committee hypertension guidelines 95.7% of the time. Conclusion: A machine learning algorithm can accurately predict the likelihood of antihypertensive treatment success and help personalize hypertension management.
No takes yet. Share an insight, caveat, or question.
Herzog et al. (2023) conducted a cohort in Newly diagnosed primary hypertension (n=17,917). Causal deep neural network-based machine learning model for first-line antihypertensive treatment prediction vs. Actual physician practice, XGBoost model, statistical model, and Eighth Joint National Committee (JNC 8) hypertension guidelines was evaluated on Model performance in predicting individualized antihypertensive treatment success (achieving JNC 8 blood pressure control with no moderate or severe adverse effects) at 1 year. The causal deep neural network model predicted 1-year antihypertensive treatment success with 51.7% precision, 44.4% recall, 47.8% F1 score, and 95.7% JNC 8 guideline agreement.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: