Using Computational Approaches to Optimize Asthma Care Management (NIH)

Project Summary

The study will develop more accurate, computational predictive models and a novel automatic explanation function to better identify patients likely to benefit most from care management. For many chronic diseases, a small portion of patients with high vulnerabilities, severe disease, or great barriers to care consume most healthcare resources and costs. To improve outcomes and resource use, many healthcare systems use predictive models to prospectively identify high-risk patients and enroll them in care management to implement tailored care plans. For maximal benefit from costly care management with limited service capacity, only patients at the highest risk should be enrolled. But, current patient identification approaches have two limitations: 1) Low prediction accuracy causes misclassification, wasted costs, and suboptimal care. If an existing model were used for care management allocation, enrollment would miss >50% of those who would benefit most but include others unlikely to benefit. A healthcare system often has insufficient data for model training and incomplete data on many patients. A typical model uses only a few risk factors for adverse outcomes, despite many being known. Also, many predictive variables on patient and system characteristics are not found yet. 2) No explanation of the reasons for a prediction causes poor adoption of the prediction and busy care managers to spend extra time and miss suitable interventions. Care managers need to understand why a patient is predicted to be at high risk before allocating to care management and forming a tailored care plan. Existing models rarely give such explanation, forcing care managers to do detailed patient chart reviews.

To address the limitations and optimize care management for more high-risk patients to receive appropriate care, the study will: a) improve accuracy of computationally identifying high-risk patients and assess potential impact on outcomes; b) automate explanation of computational prediction results and assess the impact on model accuracy and outcomes; c) assess automatic explanations' impact on care managers' acceptance of the predictions and perceived care plan quality. The use case will be asthma that affects 9% of Americans and incurs 439,000 hospitalizations, 1.8 million emergency room visits, and $56 billion in cost annually. Asthma experts and computer scientists will use data from three leading healthcare systems; a novel, model-based transfer learning technique needing no other system's raw data; a novel, pattern-based automatic explanation technique that also improves model generalizability and accuracy; a new data source, PreManage, to make patient data more complete; and novel features on patient and system characteristics. These techniques can advance clinical machine learning for various applications, improve patient identification, and help form tailored care plans. Focus groups will be conducted with clinicians to explore generalizing the techniques to patients with chronic obstructive pulmonary disease, diabetes, and heart diseases, for whom care management is also needed. The results will potentially transform care management for better outcomes and more efficient resource use.

  Publications

  • G. Luo, P. Tarczy-Hornoch, A.B. Wilcox, and E.S. Lee. Identifying Patients Who are Likely to Receive Most of Their Care from a Specific Health Care System: Demonstration via Secondary Analysis. [pdf] JMIR Medical Informatics (JMI), Vol. 6, No. 4, e12241, Oct.-Dec. 2018, pp. 1-12.

  • G. Luo. Progress Indication for Machine Learning Model Building: A Feasibility Demonstration. [pdf] SIGKDD Explorations, Vol. 20, No. 2, Dec. 2018, pp. 1-12.

  • G. Luo. A Roadmap for Semi-automatically Extracting Predictive and Clinically Meaningful Temporal Features from Medical Data for Predictive Modeling. [pdf] Global Transitions, Vol. 1, Mar. 2019, pp. 61-82.

  • G. Luo, B.L. Stone, C. Koebnick, S. He, D.H. Au, X. Sheng, M.A. Murtaugh, K.A. Sward, M. Schatz, R.S. Zeiger, G.H. Davidson, and F.L. Nkoy. Using Temporal Features to Provide Data-Driven Clinical Early Warnings for Chronic Obstructive Pulmonary Disease and Asthma Care Management: Protocol for a Secondary Analysis. [pdf] JMIR Research Protocols (JRP), Vol. 8, No. 6, e13783, Jun. 2019, pp. 1-19.

  • G. Luo, S. He, B.L. Stone, F.L. Nkoy, and M.D. Johnson. Developing a Model to Predict Hospital Encounters for Asthma in Asthmatic Patients: Secondary Analysis. [pdf] JMIR Medical Informatics (JMI), Vol. 8, No. 1, e16080, Jan.-Mar. 2020, pp. 1-16.

  • A. Messinger, G. Luo, and R. Deterding. The Doctor will See You Now: How Machine Learning and Artificial Intelligence Can Extend Our Understanding and Treatment of Asthma. [pdf] (invited) Journal of Allergy and Clinical Immunology (JACI), Vol. 145, No. 2, Feb. 2020, pp. 476-478.

  • Q. Dong, G. Luo. Progress Indication for Deep Learning Model Training: A Feasibility Demonstration. [pdf] IEEE Access, Vol. 8, 2020, pp. 79811-79843.

  • W. Zhou, G. Luo. Parameter Sensitivity Analysis for the Progressive Sampling-Based Bayesian Optimization Method for Automated Machine Learning Model Selection. [pdf] Proc. 2020 International Workshop on Data Management and Analytics for Medicine and Healthcare (DMAH'20), Tokyo, Japan, Sep. 2020, pp. 213-227.

  • G. Luo, C.L. Nau, W.W. Crawford, M. Schatz, R.S. Zeiger, E. Rozema, and C. Koebnick. Developing a Predictive Model for Asthma-Related Hospital Encounters in Patients with Asthma in a Large, Integrated Health Care System: Secondary Analysis. [pdf] JMIR Medical Informatics (JMI), Vol. 8, No. 11, e22689, 2020, pp. 1-15.

  • Y. Tong, A.I. Messinger, and G. Luo. Testing the Generalizability of an Automated Method for Explaining Machine Learning Predictions on Asthma Patients' Asthma Hospital Visits to an Academic Healthcare System. [pdf] IEEE Access, Vol. 8, 2020, pp. 195971-195979.

  • G. Luo, M.D. Johnson, F.L. Nkoy, S. He, and B.L. Stone. Automatically Explaining Machine Learning Prediction Results on Asthma Hospital Visits in Patients with Asthma: Secondary Analysis. [pdf] JMIR Medical Informatics (JMI), Vol. 8, No. 12, e21965, 2020, pp. 1-20.

  • G. Luo, C.L. Nau, W.W. Crawford, M. Schatz, R.S. Zeiger, and C. Koebnick. Generalizability of an Automatic Explanation Method for Machine Learning Prediction Results on Asthma-Related Hospital Visits in Patients with Asthma: Quantitative Analysis. [pdf] Journal of Medical Internet Research (JMIR), Vol. 23, No. 4, e24153, 2021, pp. 1-14.

  • Y. Tong, A.I. Messinger, A.B. Wilcox, S.D. Mooney, G.H. Davidson, P. Suri, and G. Luo. Forecasting Future Asthma Hospital Encounters of Patients with Asthma in an Academic Health Care System: Predictive Model Development and Secondary Analysis Study. [pdf] Journal of Medical Internet Research (JMIR), Vol. 23, No. 4, e22796, 2021, pp. 1-18.

  • G. Luo. A Roadmap for Automating Lineage Tracing to Aid Automatically Explaining Machine Learning Predictions for Clinical Decision Support. [pdf] JMIR Medical Informatics (JMI), Vol. 9, No. 5, e27778, 2021, pp. 1-20.

  • G. Luo, B.L. Stone, X. Sheng, S. He, C. Koebnick, and F.L. Nkoy. Using Computational Methods to Improve Integrated Disease Management for Asthma and Chronic Obstructive Pulmonary Disease: Protocol for a Secondary Analysis. [pdf] JMIR Research Protocols (JRP), Vol. 10, No. 5, e27065, 2021, pp. 1-19.

  • X. Zhang, G. Luo. Ranking Rule-Based Automatic Explanations for Machine Learning Predictions on Asthma Hospital Encounters in Patients with Asthma: Retrospective Cohort Study. [pdf] JMIR Medical Informatics (JMI), Vol. 9, No. 8, e28287, 2021, pp. 1-22.

  • Y. Tong, Z.C. Liao, P. Tarczy-Hornoch, and G. Luo. Using a Constraint-Based Method to Identify Chronic Disease Patients Who are Apt to Obtain Care Mostly within a Given Health Care System: Retrospective Cohort Study. [pdf] JMIR Formative Research (JFR), Vol. 5, No. 10, e26314, 2021, pp. 1-12.

  • S. Zeng, M. Arjomandi, Y. Tong, Z.C. Liao, and G. Luo. Developing a Machine Learning Model to Predict Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study. [pdf] Journal of Medical Internet Research (JMIR), Vol. 24, No. 1, e28953, 2022, pp. 1-23.

  • S. Zeng, M. Arjomandi, and G. Luo. Automatically Explaining Machine Learning Predictions on Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study. [pdf] JMIR Medical Informatics (JMI), Vol. 10, No. 2, e33043, 2022, pp. 1-23.

  • S. Zeng, M. Arjomandi, and G. Luo. Automatically Explaining Machine Learning Predictions on Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study. Abstract at American Thoracic Society (ATS) International Conference (ATS'22), San Francisco, CA, May 2022.

  • X. Zhang, G. Luo. Error Analysis of Machine Learning Predictions on Asthma Hospital Encounters. [pdf] Abstract at American Academy of Allergy, Asthma & Immunology Annual Meeting (AAAAI'22), Phoenix, AZ, Feb. 2022.

  • G. Luo. A Roadmap for Boosting Model Generalizability for Predicting Hospital Encounters for Asthma. [pdf] JMIR Medical Informatics (JMI), Vol. 10, No. 3, e33044, 2022, pp. 1-9.

  • X. Zhang, G. Luo. Error and Timeliness Analysis for Using Machine Learning to Predict Asthma Hospital Visits: Retrospective Cohort Study. [pdf] JMIR Medical Informatics (JMI), Vol. 10, No. 6, e38220, 2022, pp. 1-9.

  • Q. Dong, X. Zhang, and G. Luo. Improving the Accuracy of Progress Indication for Constructing Deep Learning Models. [pdf] IEEE Access, Vol. 10, 2022, pp. 63754-63781. Full version [pdf]

  • X. Zhang, S.B. Zeliadt, M. Walker, M.R. Levitt, B. Ng, and G. Luo. Assessing the Robustness of a Machine Learning Model for Predicting Asthma Hospital Encounters during the COVID-19 Pandemic. [pdf] Abstract at American Thoracic Society (ATS) International Conference (ATS'23), Washington, DC, May 2023.

  • Q. Dong, G. Luo, N.E. Lane, L. Lui, L.M. Marshall, S.K. Johnston, H. Dabbous, M. O'Reilly, K.F. Linnau, J. Perry, B.C. Chang, J. Renslo, D. Haynor, J.G. Jarvik, and N.M. Cross. Generalizability of Deep Learning Classification of Spinal Osteoporotic Compression Fractures on Radiographs Using an Adaptation of the Modified-2 Algorithm-Based Qualitative Criteria. [pdf] Academic Radiology, Vol. 30, No. 12, 2023, pp. 2973-2987.

  • S. Zeng, G. Luo, D.A. Lynch, R.P. Bowler, and M. Arjomandi. Lung Volumes Differentiate the Predominance of Emphysema versus Airway Disease Phenotype in Early COPD: An Observation Study of COPDGene Cohort. ERJ Open Research, Vol. 9, No. 5, Sep. 2023, pp. 00289-2023.

  • B.C. Chang, J. Renslo, Q. Dong, S.K. Johnston, J. Perry, D.R. Haynor, G. Luo, N.E. Lane, J.G. Jarvik, and N.M. Cross. Using an Ensemble of Segmentation Methods to Detect Vertebral Bodies on Radiographs. American Journal of Neuroradiology (AJNR), Vol. 45, No. 10, 2024, pp. 1512-1520.