A Novel Tropical Geometry-Based Interpretable Machine Learning Method: Pilot Application to Delivery of Advanced Heart Failure Therapies

Yao, Heming; Derksen, Harm; Golbus, Jessica R.; Zhang, Zuopeng; Aaronson, Keith D.; Gryak, Jonathan; Najarian, Kayvan

doi:10.1109/jbhi.2022.3211765

Cited by 8 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we propose an end-to-end algorithm that uses the interpretable machine learning method FNN [39] as the backbone and adapts it along the temporal dimension with a recurrent unit. This algorithm can capture the dynamism in the longitudinal data and generate humanly understandable clinical rules.…”

Section: Overview Of the Proposed Frameworkmentioning

confidence: 99%

“…We generate a total of seven time-series features and two static features for our analysis. The initial values of time-series data are simulated as [39,56]:…”

Section: Synthetic Dataset Generationmentioning

confidence: 99%

“…In contrast to the previously mentioned interpretable RNNs, we propose an interpretable framework referred to as EvolveFNN. EvolveFNN uses fuzzy neural networks (FNNs) [38,39] as its backbone for rule-based learning and relies on RNNs to evolve the learned rules. This interpretable ML model can handle the EHRs sequence data and present the underlying logic in human-readable languages.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

EvolveFNN: An interpretable framework for early detection using longitudinal electronic health record data

Zhang,

Wittrup,

Najarian

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

The extensive adoption of artificial intelligence in clinical decision support systems necessitates a significant presence of ML models that clinicians can easily interpret. Therefore, we developed an RNN-based interpretable method, combining the fuzzy concepts and recurrent units, to train accurate and explainable models on high-dimensional longitudinal electronic health records data. Through supervised learning, our method allows the identification of variable encoding functions and significant rules. To demonstrate its performance and capabilities in classification and rule discovery, we first tested it on a simulation dataset. The proposed methods achieved the best model performance, and the rules learned are almost identical to what we used to generate the synthetic data. Furthermore, we showcased a pilot application that proved its potential in the early detection of cardiac event onset. We constructed a prediction window of length from 30 days to 180 days and a 360-day retrospective observation window to evaluate our algorithm. Our proposed algorithm EvolveFNN with GRU unit achieved an AUPRC of 0.695 and an AUROC of 0.682 and EvolveFNN with LSTM unit achieved an AUPRC of 0.696 and an AUROC of 0.684 when the prediction window size is 180 days. The proposed algorithm obtained a comparable model performance to vanilla GRU models and remains relatively stable when the prediction window size changes. Examining the rules generated by our EvolveFNN model with the GRU unit, we found that the extracted rules align with clinical practices and existing literature. This provides potential risk factors not explored before in the population, such as chloride. To assess the generalizability of the algorithm, we conducted experiments on the MIMIC-III benchmark dataset for in-hospital mortality prediction. The results showed our proposed algorithms achieved model performance comparable to the top-performing GRU model and surpassed other approaches by providing transparent decision reasoning. In conclusion, our approach, EvolveFNN, can effectively train accurate, interpretable, and reliable models using large longitudinal electronic health records datasets, thereby offering valuable insights for clinicians.

show abstract

Section: Overview Of the Proposed Frameworkmentioning

confidence: 99%

“…We generate a total of seven time-series features and two static features for our analysis. The initial values of time-series data are simulated as [39,56]:…”

Section: Synthetic Dataset Generationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

EvolveFNN: An interpretable framework for early detection using longitudinal electronic health record data

Zhang,

Wittrup,

Najarian

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…Recently, an interpretable algorithm based on a tropical geometry-based fuzzy neural network (TGFNN) was developed [ 22 ]. Unlike traditional machine learning methods, this model incorporates existing clinical knowledge and produces a set of criteria by which to explain the rationale for its recommendations [ 22 , 23 ]. We extend that early work herein from classification to risk prediction, predicting the future need for HF advanced therapies using routinely collected clinical variables from a single hospitalization.…”

Section: Introductionmentioning

confidence: 99%

Predicting need for heart failure advanced therapies using an interpretable tropical geometry-based fuzzy neural network

Zhang,

Aaronson,

Gryak

et al. 2023

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Background Timely referral for advanced therapies (i.e., heart transplantation, left ventricular assist device) is critical for ensuring optimal outcomes for heart failure patients. Using electronic health records, our goal was to use data from a single hospitalization to develop an interpretable clinical decision-making system for predicting the need for advanced therapies at the subsequent hospitalization. Methods Michigan Medicine heart failure patients from 2013–2021 with a left ventricular ejection fraction ≤ 35% and at least two heart failure hospitalizations within one year were used to train an interpretable machine learning model constructed using fuzzy logic and tropical geometry. Clinical knowledge was used to initialize the model. The performance and robustness of the model were evaluated with the mean and standard deviation of the area under the receiver operating curve (AUC), the area under the precision-recall curve (AUPRC), and the F1 score of the ensemble. We inferred membership functions from the model for continuous clinical variables, extracted decision rules, and then evaluated their relative importance. Results The model was trained and validated using data from 557 heart failure hospitalizations from 300 patients, of whom 193 received advanced therapies. The mean (standard deviation) of AUC, AUPRC, and F1 scores of the proposed model initialized with clinical knowledge was 0.747 (0.080), 0.642 (0.080), and 0.569 (0.067), respectively, showing superior predictive performance or increased interpretability over other machine learning methods. The model learned critical risk factors predicting the need for advanced therapies in the subsequent hospitalization. Furthermore, our model displayed transparent rule sets composed of these critical concepts to justify the prediction. Conclusion These results demonstrate the ability to successfully predict the need for advanced heart failure therapies by generating transparent and accessible clinical rules although further research is needed to prospectively validate the risk factors identified by the model.

show abstract

A survey of internet of medical things: technology, application and future directions

He,

Huang,

et al. 2024

Digital Communications and Networks

View full text Add to dashboard Cite

A Novel Tropical Geometry-Based Interpretable Machine Learning Method: Pilot Application to Delivery of Advanced Heart Failure Therapies

Cited by 8 publications

References 30 publications

EvolveFNN: An interpretable framework for early detection using longitudinal electronic health record data

EvolveFNN: An interpretable framework for early detection using longitudinal electronic health record data

Predicting need for heart failure advanced therapies using an interpretable tropical geometry-based fuzzy neural network

A survey of internet of medical things: technology, application and future directions

Contact Info

Product

Resources

About