Prediction of incident myocardial infarction using machine learning applied to harmonized electronic health record data

Mandair, Divneet; Tiwari, Premanand; Simon, Steven R.; Colborn, Kathryn; Rosenberg, Michael

doi:10.1186/s12911-020-01268-x

Cited by 25 publications

(26 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although these approaches tended to improve the prediction accuracy as assessed by the F1 score and other measures of classification, they resulted in models that tended to predict a rhythm-control strategy more often than one was actually used, suggesting that they were overfitting the data. This result is consistent with previous work using machine learning to predict rare outcomes from EHR data by our team, including the prediction of AF itself [ 33 ] and myocardial infarction [ 32 ].…”

Section: Discussionsupporting

confidence: 92%

“…Second, we found that only neural networks could provide the computational power to produce accurate prediction models with big data inputs; none of the other approaches provided an AUC over 0.5 (F1 score>0.0) when applied to big data inputs. This result is also similar to previous findings with the application of machine learning to EHR data [ 32 , 33 ] and suggests the power of deep learning over standard methods, which has been demonstrated widely across a range of applications [ 44 - 46 ].…”

Section: Discussionsupporting

confidence: 89%

“…Within the space of clinical decision-making, such opacity can be a problem as it not only prevents users from gaining trust in the model but also provides little feedback in terms of how potential factors might be modified to change a decision. Our group has previously described the application of machine learning methods to EHRs for the prediction of incident AF and other outcomes [ 32 , 33 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning Methodologies for Prediction of Rhythm-Control Strategy in Patients Diagnosed With Atrial Fibrillation: Observational, Retrospective, Case-Control Study

Kim¹,

Simon²,

Powers³

et al. 2021

JMIR Med Inform

Self Cite

View full text Add to dashboard Cite

Background The identification of an appropriate rhythm management strategy for patients diagnosed with atrial fibrillation (AF) remains a major challenge for providers. Although clinical trials have identified subgroups of patients in whom a rate- or rhythm-control strategy might be indicated to improve outcomes, the wide range of presentations and risk factors among patients presenting with AF makes such approaches challenging. The strength of electronic health records is the ability to build in logic to guide management decisions, such that the system can automatically identify patients in whom a rhythm-control strategy is more likely and can promote efficient referrals to specialists. However, like any clinical decision support tool, there is a balance between interpretability and accurate prediction. Objective This study aims to create an electronic health record–based prediction tool to guide patient referral to specialists for rhythm-control management by comparing different machine learning algorithms. Methods We compared machine learning models of increasing complexity and used up to 50,845 variables to predict the rhythm-control strategy in 42,022 patients within the University of Colorado Health system at the time of AF diagnosis. Models were evaluated on the basis of their classification accuracy, defined by the F1 score and other metrics, and interpretability, captured by inspection of the relative importance of each predictor. Results We found that age was by far the strongest single predictor of a rhythm-control strategy but that greater accuracy could be achieved with more complex models incorporating neural networks and more predictors for each participant. We determined that the impact of better prediction models was notable primarily in the rate of inappropriate referrals for rhythm-control, in which more complex models provided an average of 20% fewer inappropriate referrals than simpler, more interpretable models. Conclusions We conclude that any health care system seeking to incorporate algorithms to guide rhythm management for patients with AF will need to address this trade-off between prediction accuracy and model interpretability.

show abstract

Section: Discussionsupporting

confidence: 92%

Section: Discussionsupporting

confidence: 89%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Methodologies for Prediction of Rhythm-Control Strategy in Patients Diagnosed With Atrial Fibrillation: Observational, Retrospective, Case-Control Study

Kim¹,

Simon²,

Powers³

et al. 2021

JMIR Med Inform

Self Cite

View full text Add to dashboard Cite

show abstract

“…While DL models often result in accurate predictions, it is hard to interpret and rationalize the results. Moreover, studies show that for harmonized EHRs data, a DL model did not show superior benefits compared with traditional methods [ 23 ].…”

Section: Introductionmentioning

confidence: 99%

Personalized hypertension treatment recommendations by a data-driven model

Huerta

Cordella

et al. 2023

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Hypertension is a prevalent cardiovascular disease with severe longer-term implications. Conventional management based on clinical guidelines does not facilitate personalized treatment that accounts for a richer set of patient characteristics. Methods Records from 1/1/2012 to 1/1/2020 at the Boston Medical Center were used, selecting patients with either a hypertension diagnosis or meeting diagnostic criteria (≥ 130 mmHg systolic or ≥ 90 mmHg diastolic, n = 42,752). Models were developed to recommend a class of antihypertensive medications for each patient based on their characteristics. Regression immunized against outliers was combined with a nearest neighbor approach to associate with each patient an affinity group of other patients. This group was then used to make predictions of future Systolic Blood Pressure (SBP) under each prescription type. For each patient, we leveraged these predictions to select the class of medication that minimized their future predicted SBP. Results The proposed model, built with a distributionally robust learning procedure, leads to a reduction of 14.28 mmHg in SBP, on average. This reduction is 70.30% larger than the reduction achieved by the standard-of-care and 7.08% better than the corresponding reduction achieved by the 2nd best model which uses ordinary least squares regression. All derived models outperform following the previous prescription or the current ground truth prescription in the record. We randomly sampled and manually reviewed 350 patient records; 87.71% of these model-generated prescription recommendations passed a sanity check by clinicians. Conclusion Our data-driven approach for personalized hypertension treatment yielded significant improvement compared to the standard-of-care. The model implied potential benefits of computationally deprescribing and can support situations with clinical equipoise.

show abstract

“…Another approach is harmonizing EHR under standard data models like Observational Medical Outcomes Partnership (OMOP) and Fast Healthcare Interoperability Resources (FHIR). These data models put well-known limitations on granularity of EHR and cannot handle variations in the data patterns themselves 14,15 . These challenges hinder wide-spread adoption of EHR-based ML/DL models across multiple institutions.…”

Section: Introductionmentioning

confidence: 99%

Generalizable Model Design for Clinical Event Prediction using Graph Neural Networks

Tariq

Kaur

et al. 2023

Preprint

View full text Add to dashboard Cite

While many machine learning and deep learning-based models for clinical event prediction leverage various data elements from electronic healthcare records such as patient demographics and billing codes, such models face severe challenges when tested outside of their institution of training. These challenges are rooted in differences in patient population characteristics and medical practice patterns of different institutions. We propose a solution to this problem through systematically adaptable design of graph-based convolutional neural networks (GCNN) for clinical event prediction. Our solution relies on unique property of GCNN where data encoded as graph edges is only implicitly used during prediction process and can be adapted after model training without requiring model re-training. Our adaptable GCNN-based prediction models outperformed all comparative models during external validation for two different clinical problems, while supporting multimodal data integration. These results support our hypothesis that carefully designed GCNN-based models can overcome generalization challenges faced by prediction models.

show abstract

Prediction of incident myocardial infarction using machine learning applied to harmonized electronic health record data

Cited by 25 publications

References 33 publications

Machine Learning Methodologies for Prediction of Rhythm-Control Strategy in Patients Diagnosed With Atrial Fibrillation: Observational, Retrospective, Case-Control Study

Machine Learning Methodologies for Prediction of Rhythm-Control Strategy in Patients Diagnosed With Atrial Fibrillation: Observational, Retrospective, Case-Control Study

Personalized hypertension treatment recommendations by a data-driven model

Generalizable Model Design for Clinical Event Prediction using Graph Neural Networks

Contact Info

Product

Resources

About