A Transformer-Based Model Trained on Large Scale Claims Data for Prediction of Severe COVID-19 Disease Progression

Abstract

In situations like the COVID-19 pandemic, healthcare systems are under enormous pressure as they can rapidly collapse under the burden of the crisis. Machine learning (ML) based risk models could lift the burden by identifying patients with high risk of severe disease progression. Electronic Health Records (EHRs) provide crucial sources of information to develop these models because they rely on routinely collected healthcare data. However, EHR data is challenging for training ML models because it contains irregularly timestamped diagnosis, prescription, and procedure codes. For such data, transformer-based models are promising. We extended the previously published Med-BERT model by including age, sex, medications, quantitative clinical measures, and state information. After pre-training on approximately 988 million EHRs from 3.5 million patients, we developed models to predict Acute Respiratory Manifestations (ARM) risk using the medical history of 80,211 COVID-19 patients. Compared to XGBoost and Random Forests, our transformer-based models more accurately forecast the risk of developing ARM after COVID-19 infection. We used Integrated Gradients and Bayesian networks to understand the link between the essential features of our model. Finally, we evaluated adapting our model to Austrian in-patient data. Our study highlights the promise of predictive transformer-based models for precision medicine.

Competing Interest Statement

SV, DK, and WL received salaries from Steiermaerkische Krankenanstaltengesellschaft m.b.H. (KAGes) (Graz, Austria). The company had no influence on the scientific results presented in this paper.

Funding Statement

This research was performed in the context of the "COPERIMOplus" initiative and supported by the Fraunhofer "Internal Programs" under Grant No. Anti-Corona 840266.

Author Declarations

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The data analyzed in this study are from two sources. On the one hand, we used the commercial database IBM Explorys Therapeutic Dataset. Since it contains no information about clinical trials and is entirely de-identified, an Institutional Review Board was not required to authorize the use of these data. On the other hand, we utilized data from the Austrian hospitals, which was approved by the Medical University of Graz's ethics committee (IRB00002556, EK-Number: 30-146 ex 17/18).

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable.

Yes

Data Availability

The data are part of the commercial IBM Explorys Therapeutic dataset. This study's code is accessible to the public at https://github.com/SCAI-BIO/ExMed-BERT.

留言 (0)

沒有登入
gif