Rxivist logo

An Efficient and Accurate Distributed Learning Algorithm for Modeling Multi-Site Zero-Inflated Count Outcomes

By Mackenzie J Edmondson, Chongliang Luo, Rui Duan, Mitchell Maltenfort, Zhaoyi Chen, Kenneth Locke, Justine Shults, Jiang Bian, Patrick Ryan, Christopher Forrest, Yong Chen

Posted 19 Dec 2020
medRxiv DOI: 10.1101/2020.12.17.20248194

Clinical research networks (CRNs), made up of multiple healthcare systems each with patient data from several care sites, are beneficial for studying rare outcomes and increasing generalizability of results. While CRNs encourage sharing aggregate data across healthcare systems, individual systems within CRNs often cannot share patient-level data due to privacy regulations, prohibiting multi-site regression which requires an analyst to access all individual patient data pooled together. Meta-analysis is commonly used to model data stored at multiple institutions within a CRN; while relatively simple to implement, meta-analysis can result in biased estimation, notably in rare-event contexts. We present a communication-efficient, privacy-preserving algorithm for modeling multi-site zero-inflated count outcomes within a CRN. Our method, a one-shot distributed algorithm for performing hurdle regression (ODAH), models zero-inflated count data stored in multiple sites without sharing patient-level data across sites, resulting in estimates closely approximating those that would be obtained in a pooled patient-level data analysis. We evaluate our method through extensive simulations and two real-world data applications using electronic health records (EHRs): examining risk factors associated with pediatric avoidable hospitalization and modeling serious adverse event frequency associated with a colorectal cancer therapy. Relative to existing methods for distributed data analysis, ODAH offers a highly accurate, computationally efficient method for modeling multi-site zero-inflated count data.

Download data

  • Downloaded 205 times
  • Download rankings, all-time:
    • Site-wide: 117,856
    • In health informatics: 452
  • Year to date:
    • Site-wide: 37,893
  • Since beginning of last month:
    • Site-wide: 46,083

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide