Filling the Gaps in Health Data: Using a Machine Learning Approach to Augment Partially Observed Variables Such as Smoking in Claims Data

The added value of transfer learning was greatest when low proportions of true ever-smokers were recorded, with its advantage depending on both the true prevalence of true smokers and the predictive model's performance.

Authors

Clémentine Nordon (ORCID: https://orcid.org/0000-0001-9441-9723)
Evangelos Chandakas (ORCID: https://orcid.org/0000-0002-9291-9641)
Sam Hillman
Stefan Franzén (ORCID: https://orcid.org/0000-0002-6636-9412)
Kirsty Rhodes

Institutions

AstraZeneca (Netherlands) (NL)
AstraZeneca (Singapore) (SG)
AstraZeneca (Switzerland) (CH)
AstraZeneca (Poland) (PL)
AstraZeneca (Finland) (FI)
AstraZeneca (Spain) (ES)

Publication Details

Journal: Pharmacoepidemiology and Drug Safety
Published: 2026-01-29
DOI: https://doi.org/10.1002/pds.70322
Primary Topic: Advanced Causal Inference Techniques
Type: article
Field-Weighted Citation Impact: 0.00

Funders

AstraZeneca

Controls

|||

ALL TIME

JAN

FEB

MAR

APR

MAY

JUN

JUL

AUG

SEP

OCT

article

Filling the Gaps in Health Data: Using a Machine Learning Approach to Augment Partially Observed Variables Such as Smoking in Claims Data

Clémentine Nordon, Evangelos Chandakas, Sam Hillman, Stefan Franzén et al.

Jan 29, 2026

Pharmacoepidemiology and Drug Safety

Advanced Causal Inference Techniques

article

Filling the Gaps in Health Data: Using a Machine Learning Approach to Augment Partially Observed Variables Such as Smoking in Claims Data

Clémentine Nordon, Evangelos Chandakas, Sam Hillman, Stefan Franzén, Kirsty Rhodes

January 29, 2026article en

Abstract

The added value of transfer learning was greatest when low proportions of true ever-smokers were recorded, with its advantage depending on both the true prevalence of true smokers and the predictive model's performance.

Pharmacoepidemiology and Drug SafetyVol. 35(2)

AstraZeneca (Netherlands) (NL), AstraZeneca (Singapore) (SG), AstraZeneca (Switzerland) (CH), AstraZeneca (Poland) (PL), AstraZeneca (Finland) (FI), AstraZeneca (Spain) (ES)

AstraZeneca

Good health and well-being

Openalex Percentile: Top 75%

Advanced Causal Inference Techniques

DOI Open Access PDF OpenAlex

AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Filling the Gaps in Health Data: Using a Machine Learning Approach to Augment Partially Observed Variables Such as Smoking in Claims Data — Clémentine Nordon, Evangelos Chandakas, et al. · Pharmacoepidemiology and Drug Safety (2026) | TGRS Research Map | TGRS