Personalized survival probabilities for SARS-CoV-2 positive patients by explainable machine learning

  1. Adrian G. Zucco
  2. Rudi Agius
  3. Rebecka Svanberg
  4. Kasper S. Moestrup
  5. Ramtin Z. Marandi
  6. Cameron Ross MacPherson
  7. Jens Lundgren
  8. Sisse R. Ostrowski
  9. Carsten U. Niemann

Reviewed by

Read the full article

Listed in

Log in to save this article

Abstract

Interpretable risk assessment of SARS-CoV-2 positive patients can aid clinicians to implement precision medicine. Here we trained a machine learning model to predict mortality within 12 weeks of a first positive SARS-CoV-2 test. By leveraging data on 33,938 confirmed SARS-CoV-2 cases in eastern Denmark, we considered 2723 variables extracted from electronic health records (EHR) including demographics, diagnoses, medications, laboratory test results and vital parameters. A discrete-time framework for survival modelling enabled us to predict personalized survival curves and explain individual risk factors. Performance on the test set was measured with a weighted concordance index of 0.95 and an area under the curve for precision-recall of 0.71. Age, sex, number of medications, previous hospitalizations and lymphocyte counts were identified as top mortality risk factors. Our explainable survival model developed on EHR data also revealed temporal dynamics of the 22 selected risk factors. Upon further validation, this model may allow direct reporting of personalized survival probabilities in routine care.

Article activity feed

  1. Version published to 10.1038/s41598-022-17953-y
  2. ScreenIT

    SciScore for 10.1101/2021.10.28.21265598: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    NIH rigor criteria are not applicable to paper type.

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    For diagnoses represented by International Statistical Classification of Diseases and Related Health Problems version 10 (ICD-10) codes, the selected time window was three years, while for medications represented by Anatomical Therapeutic Chemical (ATC) codes, the time window was one year.
    ATC
    suggested: None
    Feature engineering was performed in Python using the pandas61 and numpy62 libraries.
    Python
    suggested: (IPython, RRID:SCR_001658)

    Results from OddPub: Thank you for sharing your code.

    Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:
    To overcome some of these previous limitations, we used electronic health records (EHR) from eastern Denmark, identifying 33,938 patients who had at least one positive SARS-CoV-2 RT-PCR test. To enable ML algorithms, clinical data need to be encoded into features that can be computed. Multiple approaches have been suggested for encoding EHR into computationally meaningful representations30,31. We opted for a simple feature engineering approach by considering the latest values or counts in clinically relevant time windows prior to FPT depending on the type of variable. Additionally, instead of characterizing patients’ relevant history using a limited set of pre-selected variables, the set of 22 features in the final model were derived using a data-driven approach from an initial set of 2,723 features that encoded available demographics, laboratory test results, hospitalizations, vital parameters, diagnoses and medicines. This approach enabled us to reduce model complexity to a smaller feature set while avoiding potential bias introduced by pre-selecting variables. While EHR are more representative of patient populations in terms of real-world data (RWD)32, some challenges arise when processing EHR for clinical research. Data collected from routine care may present inconsistencies33 that cannot be appropriately curated for in such big data sets, especially for information regarding clinical interventions or hospitalization status. We thus selected SARS-CoV-2 positive status and...

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We found bar graphs of continuous data. We recommend replacing bar graphs with more informative graphics, as many different datasets can lead to the same bar graph. The actual data may suggest different conclusions from the summary statistics. For more information, please see Weissgerber et al (2015).

    Results from JetFighter: We did not find any issues relating to colormaps.

    Results from rtransparent:
    • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
    • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
    • No protocol registration statement was detected.

    Results from scite Reference Check: We found no unreliable references.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.

  3. Version published to 10.1101/2021.10.28.21265598v1 on medRxiv