Unleashing the Power of Very Small Data to Predict Acute Exacerbations of Chronic Obstructive Pulmonary Disease

Abstract

Introduction

In this article, we explore to what extent it is possible to leverage on very small data to build machine learning (ML) models that predict acute exacerbations of chronic obstructive pulmonary disease (AECOPD).

Methods

We build ML models using the small data collected during the eHealth Diary telemonitoring study between 2013 and 2017 in Sweden. This data refers to a group of multimorbid patients, namely 18 patients with chronic obstructive pulmonary disease (COPD) as the major reason behind previous hospitalisations. The telemonitoring was supervised by a specialised hospital-based home care (HBHC) unit, which also was responsible for the medical actions needed.

Results

We implement two different ML approaches, one based on time-dependent covariates and the other one based on time-independent covariates. We compare the first approach with standard COX Proportional Hazards (CPH). For the second one, we use different proportions of synthetic data to build models and then evaluate the best model against authentic data.

Discussion

To the best of our knowledge, the present ML study shows for the first time that the most important variable for an increased risk of future AECOPDs is “maintenance medication changes by HBHC”. This finding is clinically relevant since a sub-optimal maintenance treatment, requiring medication changes, puts the patient in risk for future AECOPDs.

Conclusion

The experiments return useful insights about the use of small data for ML.

Keywords:

• machine learning
• telehealth or digital health
• COX proportional hazards
• random survival forests
• random forests
• mHealth

Data Sharing Statement

The data upon which this analysis was based are available from Professor Hans Lennart Persson in anonymised form, upon receipt of a reasonable request. Contact details are Professor Hans Lennart Persson, M.D., Ph.D., Department of Respiratory Medicine in Linköping, Linköping University, Linköping, Sweden. E-mail: [email protected]

Ethics Statement and Study Registration

All research participants gave written, informed consent and the study was approved by the Swedish Ethical Committee (dnr: 2020-03308; L. Lind) according to the guidelines of the Declaration of Helsinki and was registered at ISRCTN (ISRCTN34252610).

Acknowledgment

The authors would like to dedicate this work to the memory of a highly appreciated colleague, Dr Marina Santini. Thank you, Marina, for sharing your great knowledge and expertise.

Author Contributions

All authors made a significant contribution to the work reported, whether that is in the conception, study design, execution, acquisition of data, analysis, and interpretation, or in all these areas; took part in drafting, revising or critically reviewing the article; gave final approval of the version to be published; have agreed on the journal to which the article has been submitted; and agree to be accountable for all aspects of the work.

Disclosure

H.L.P. reports honoraria for advisory boards/lectures from AstraZeneca, Boehringer Ingelheim, GlaxoSmithCline, InterMune, Roche and the Swedish Medical Products Agency. The authors report no other conflicts of interest in this work.

Additional information

Funding

This work was supported by grants to P.K.J. and H.L.P from the Medical Research Council of Southeast Sweden (FORSS) (Grant No. FORSS-969385, FORSS-980999) and grants to L.L and H.L.P. from Sweden’s innovation agency Vinnova (Dnr: 2019-05402) in Swelife’s and Medtech4Health’s Collaborative projects for better health programme. The study sponsors had no role in study design, data collection, analysis, and interpretation; in the writing of the manuscript; nor in the decision to submit the manuscript for publication.