Machine Learning-Based Prediction of Drug-Induced QTc Changes in a Large Finnish Biobank Cohort.

Code ↔ Paper

6 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 6 matches

[1] § Methods › Statistical Methods ↔ R/xgb_optmizer.R, lines 61–99 · score 0.75 · child weight, mlrMBO, depth, hyperparameters, subsample, optimization
[2] § Methods › Statistical Methods ↔ R/nested_xgboost_cox_cv_inner_loop.R, lines 1–12 · score 0.74 · nested cross validated, tune model, loops, split, inner, xgboost
[3] § Methods › Statistical Methods ↔ vignettes/linear_plot.Rmd, lines 44–60 · score 0.67 · chronic kidney disease, heart failure, coronary, diabetes, PGS, risk
[4] § Methods › Statistical Methods ↔ vignettes/linear.Rmd, lines 52–75 · score 0.66 · chronic kidney disease, heart failure, coronary, diabetes, risk, sex
[5] § Methods › Variable Definitions ↔ vignettes/linear.Rmd, lines 52–75 · score 0.60 · Chronic kidney disease, Heart failure, Coronary, Diabetes
[6] § Methods › Variable Definitions ↔ vignettes/linear_plot.Rmd, lines 44–60 · score 0.60 · Chronic kidney disease, Heart failure, Coronary, Diabetes

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The paper is loaded by your browser, with JavaScript: read it at doi.org or on Europe PMC.

The authors' code

R Markdown · 171 lines · 6.6 KB · no license · 2 matches

The registry keeps no copy of this file: its repository has no license, so its authors keep all their rights to it. Your browser shows it from its source, with JavaScript.

It can be read at the source: vignettes/linear_plot.Rmd.

Overview

Authors: Ville Langén^1,2, Aleksi Winstén^3,4, Konsta Teppo^5,6, Timo Pohjonen⁷, Jari Laukkanen^7,8, Arto Mannermaa^9,10, Teemu J Niiranen^1,5, Joonatan Palmu¹

ORCID iDs: Ville Langén, Aleksi Winstén, Konsta Teppo, Timo Pohjonen, Jari Laukkanen, Arto Mannermaa, Teemu J Niiranen, Joonatan Palmu

Division of Medicine, Turku University Hospital and University of Turku, Turku, Finland
Department of Geriatric Medicine, Turku University Hospital and University of Turku, Turku, Finland
Department of Mathematics and Statistics, University of Turku, Turku, Finland
FinnGen Consortium, Helsinki, Finland
Department of Internal Medicine, University of Turku, Turku, Finland
Cardiac Unit, Department of Internal Medicine, Satasairaala, Pori, Finland
Central Finland Biobank, Wellbeing Services County of Central Finland, Jyväskylä, Finland
Department of Medicine, Institute of Clinical Medicine, University of Eastern Finland, Kuopio, Finland
Biobank of Eastern Finland, University of Eastern Finland, Kuopio, Finland
Kuopio University Hospital, Kuopio, Finland

Institutions: University of Turku (Finland); Turku University Hospital (Finland); University of Eastern Finland (Finland); Kuopio University Hospital (Finland)

Journal: Clinical and translational science, volume 19, issue 5, article e70577

Dates: received 21 December 2025; accepted 20 April 2026; published online 4 May 2026; in print May 2026

Type: Research article · Language: English

License: CC BY-NC

Identifiers: DOI 10.1111/cts.70577 · PMID 42083122 · PMCID PMC13139045 · OpenAlex W7160303939

Open access: gold, a free copy (OpenAlex)

Status: code verified

Categories: genetics / omics (modality), other (modality), human (organism), clinical / translational (subfield)

Methods: Statistics, Smoothing, state filtering, decompositions, Machine learning

Keywords: biobank research, drug safety, machine learning, polygenic risk score, QT interval

MeSH: Long QT Syndrome*, Machine Learning*, Aged, Biological Specimen Banks, Cohort Studies, Electrocardiography, Female, Finland, Genetic Risk Score, Humans, Male, Middle Aged, Prediction Algorithms, Predictive Learning Models, Risk Assessment (* major topic)

Topic: Cardiac electrophysiology and arrhythmias (Cardiology and Cardiovascular Medicine, Medicine), according to OpenAlex

Funding: State Research Funding of the Wellbeing Services County of Southwest Finland; Paavo Nurmi Foundation; Alkoholitutkimussäätiö; Business Finland (UH 4386/31/2016, HUS 4685/31/2016); Paavo Nurmen Säätiö; The Finnish Foundation for Alcohol studies; The Finnish Foundation for Cardiovascular Research; The Finnish Medical Foundation

Citations: not cited yet (Europe PMC); 24 references in the paper

Abstract

Prolongation of the QT interval is a known precursor to serious arrhythmias and sudden cardiac death, often triggered by medication use. Current medication risk evaluation platforms rely on literature‐based synthesis and may lag behind real‐world developments. We aimed to evaluate whether a machine learning (ML) model trained on real‐world genomic and medication data can identify associations between drug use and QTc duration, potentially enabling automated risk detection in clinical workflows. We included 10,208 individuals from the FinnGen biobank Expansion Area 3 substudy, integrating prescription records, clinical variables, and genetic information. We applied a nested‐cross‐validation approach to develop an ML framework to predict QTc duration using clinical characteristics, recent medication purchases, and polygenic score for QTc duration. We performed conventional linear regression analyses to estimate the robustness of the findings. Only a minority of ML‐detected drug–QTc associations aligned with known effects listed in expert‐curated reference. Several apparent false positives were observed, and effect sizes for true positives, such as amiodarone, were small and likely interpreted as clinically not meaningful (+1 ms in ML vs. +49 ms in linear regression). These findings highlight challenges in using ML to detect meaningful drug effects on ECG. ML models did not reliably identify medications associated with QT‐interval prolongation. Consequently, risk quantification using QTc as an intermediate marker of electrophysiological vulnerability was limited in this framework. While new approaches continue to develop in medication safety assessment, a systematic evidence review conducted by clinical pharmacology experts is unlikely to be supplanted in the foreseeable future.

Reproduced under the paper's license (CC BY-NC), from the paper cited above.

Repositories

Its files are read in the Code ↔ Paper reader above, with 6 matches between paragraphs and lines of code.

Zenodo 15223007

License: CC-BY-4.0

State: the link answers, verified on 27 September 2026

Evidence: files inventoried

Size: 1 file

Software Heritage: not checked

Found in: “Data Availability Statement”

Not found: README, license file, CITATION.cff, environment file, tests, continuous integration, documentation

Tools: tidyverse (34 files), XGBoost (15 files), ggplot2 (5 files), data.table (4 files), patchwork (3 files), caret (2 files), broom (1 file)

Availability: 1 check, the latest on 27 September 2026: the link answers (HTTP 200)

27 September 2026: the link answers (HTTP 200)

42 files

R/add_randomized_cat_column.R — R, 14 lines
R/add_randomized_column.R — R, 11 lines
R/cantor_pairing.R — R, 10 lines
R/detect_factors.R — R, 20 lines
R/generate_pca_grouping.R — R, 16 lines
R/get_model_matrix.R — R, 1 line
R/mysavefactory.R — R, 35 lines
R/nested_xgboost_cox_cv.R — R, 14 lines
R/nested_xgboost_cox_cv_concordance.R — R, 13 lines
R/nested_xgboost_cox_cv_harrell.R — R, 13 lines
R/nested_xgboost_cox_cv_inner_loop.R — R, 105 lines
R/nested_xgboost_cox_cv_load.R — R, 13 lines
R/nested_xgboost_cox_cv_model_matrix.R — R, 18 lines
R/nested_xgboost_cox_cv_outer_loop.R — R, 39 lines
R/nested_xgboost_cox_cv_pdp.R — R, 37 lines
R/nested_xgboost_cox_cv_save.R — R, 13 lines
R/shap_rename.R — R, 13 lines
R/shapviz_avg.R — R, 26 lines
R/xgb_inner_loop.R — R, 74 lines
R/xgb_linear_scores.R — R, 15 lines
R/xgb_load.R — R, 20 lines
R/xgb_model_matrix.R — R, 16 lines
R/xgb_optmizer.R — R, 99 lines
R/xgb_outer_loop.R — R, 44 lines
R/xgb_save.R — R, 14 lines
get_packages.R — R, 40 lines
src/add_covariates_to_atc.R — R, 40 lines
src/add_prs_scores_to_the_full_data_frame.R — R, 31 lines
src/atc_codes.R — R, 56 lines
src/ekg_luku.R — R, 20 lines
src/qt_variants_to_covariants_and_atc.R — R, 45 lines
vignettes/linear.Rmd — R, 162 lines
vignettes/linear_plot.Rmd — R, 171 lines
vignettes/nested_cv_cad.Rmd — R, 234 lines
vignettes/nested_cv_combine.Rmd — R, 505 lines
vignettes/prepare_data.Rmd — R, 85 lines
vignettes/xgboost.R — R, 37 lines
vignettes/xgboost.Rmd — R, 157 lines
vignettes/xgboost_plot.Rmd — R, 125 lines
workflows/mirror_cran.R — R, 12 lines
workflows/xgboost.R — R, 37 lines
README.md — Text, 93 lines

At the source: doi.org/10.5281/zenodo.15223007

jjmpal/ecg_qtc

License: none: the authors keep all their rights

State: the link answers, verified on 27 September 2026

Evidence: files inventoried

Commit: abca3806d39a31fbf5d61b2d664e2aef5ad9b713, 20 April 2025

Languages: R (41)

Size: 52 files, 41 scripts

Software Heritage: not archived

Found in: the Zenodo archive record

Holds: README, environment (DESCRIPTION), documentation, 7 notebooks

Not found: license file, CITATION.cff, tests, continuous integration

Tools: tidyverse (34 files), XGBoost (15 files), ggplot2 (5 files), data.table (4 files), patchwork (3 files), caret (2 files), broom (1 file)

Availability: 1 check, the latest on 27 September 2026: the link answers

27 September 2026: the link answers

42 files, not copied: shown from their source

OSCR keeps no copy of these files: this repository has no license that allows it. The reader above shows each one from its source, fetched by your browser at commit abca380, when its fingerprint is the one OSCR verified. How this works.

R/add_randomized_cat_column.R — R, 14 lines, shown from its source
R/add_randomized_column.R — R, 11 lines, shown from its source
R/cantor_pairing.R — R, 10 lines, shown from its source
R/detect_factors.R — R, 20 lines, shown from its source
R/generate_pca_grouping.R — R, 16 lines, shown from its source
R/get_model_matrix.R — R, 1 line, shown from its source
R/mysavefactory.R — R, 35 lines, shown from its source
R/nested_xgboost_cox_cv.R — R, 14 lines, shown from its source
R/nested_xgboost_cox_cv_concordance.R — R, 13 lines, shown from its source
R/nested_xgboost_cox_cv_harrell.R — R, 13 lines, shown from its source
R/nested_xgboost_cox_cv_inner_loop.R — R, 105 lines, 1 match, shown from its source
R/nested_xgboost_cox_cv_load.R — R, 13 lines, shown from its source
R/nested_xgboost_cox_cv_model_matrix.R — R, 18 lines, shown from its source
R/nested_xgboost_cox_cv_outer_loop.R — R, 39 lines, shown from its source
R/nested_xgboost_cox_cv_pdp.R — R, 37 lines, shown from its source
R/nested_xgboost_cox_cv_save.R — R, 13 lines, shown from its source
R/shap_rename.R — R, 13 lines, shown from its source
R/shapviz_avg.R — R, 26 lines, shown from its source
R/xgb_inner_loop.R — R, 74 lines, shown from its source
R/xgb_linear_scores.R — R, 15 lines, shown from its source
R/xgb_load.R — R, 20 lines, shown from its source
R/xgb_model_matrix.R — R, 16 lines, shown from its source
R/xgb_optmizer.R — R, 99 lines, 1 match, shown from its source
R/xgb_outer_loop.R — R, 44 lines, shown from its source
R/xgb_save.R — R, 14 lines, shown from its source
get_packages.R — R, 40 lines, shown from its source
src/add_covariates_to_atc.R — R, 40 lines, shown from its source
src/add_prs_scores_to_the_full_data_frame.R — R, 31 lines, shown from its source
src/atc_codes.R — R, 56 lines, shown from its source
src/ekg_luku.R — R, 20 lines, shown from its source
src/qt_variants_to_covariants_and_atc.R — R, 45 lines, shown from its source
vignettes/linear.Rmd — R, 162 lines, 2 matches, shown from its source
vignettes/linear_plot.Rmd — R, 171 lines, 2 matches, shown from its source
vignettes/nested_cv_cad.Rmd — R, 234 lines, shown from its source
vignettes/nested_cv_combine.Rmd — R, 505 lines, shown from its source
vignettes/prepare_data.Rmd — R, 85 lines, shown from its source
vignettes/xgboost.R — R, 37 lines, shown from its source
vignettes/xgboost.Rmd — R, 157 lines, shown from its source
vignettes/xgboost_plot.Rmd — R, 125 lines, shown from its source
workflows/mirror_cran.R — R, 12 lines, shown from its source
workflows/xgboost.R — R, 37 lines, shown from its source
README.md — Text, 93 lines, shown from its source

At the source: github.com/jjmpal/ECG_QTC/tree/v1.2

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

2 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
82 scripts, each with its path and the digest of its content;
6 matches between paragraphs of the paper and lines of the code (method lexical-v1);
neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

No dataset and no data link were found in the paper.

Data Availability Statement

The analysis codes for this study have been deposited in the Zenodo repository with the following DOI 10.5281/zenodo.15223007 (https://doi.org/10.5281/zenodo.15223007).

Reproduced under the paper's license (CC BY-NC), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 8 authors, 5 keywords, 15 MeSH terms, 8 funders, 22 references.

Cite

This paper

Langén, V., Winstén, A., Teppo, K., Pohjonen, T., Laukkanen, J., Mannermaa, A., Niiranen, T. J., & Palmu, J. (2026). Machine Learning-Based Prediction of Drug-Induced QTc Changes in a Large Finnish Biobank Cohort. Clinical and translational science, 19(5), e70577. https://doi.org/10.1111/cts.70577

BibTeX

@article{langen2026machine, author = {Langén, Ville and Winstén, Aleksi and Teppo, Konsta and Pohjonen, Timo and Laukkanen, Jari and Mannermaa, Arto and Niiranen, Teemu J and Palmu, Joonatan}, title = {{Machine Learning-Based Prediction of Drug-Induced QTc Changes in a Large Finnish Biobank Cohort}}, journal = {Clinical and translational science}, year = {2026}, month = may, volume = {19}, number = {5}, pages = {e70577}, publisher = {Wiley}, issn = {1752-8054}, doi = {10.1111/cts.70577}, url = {https://doi.org/10.1111/cts.70577}, pmid = {42083122}, pmcid = {PMC13139045} }

RIS

TY - JOUR AU - Langén, Ville AU - Winstén, Aleksi AU - Teppo, Konsta AU - Pohjonen, Timo AU - Laukkanen, Jari AU - Mannermaa, Arto AU - Niiranen, Teemu J AU - Palmu, Joonatan TI - Machine Learning-Based Prediction of Drug-Induced QTc Changes in a Large Finnish Biobank Cohort T2 - Clinical and translational science J2 - Clin Transl Sci PY - 2026 DA - 2026/05/01 VL - 19 IS - 5 SP - e70577 SN - 1752-8054 PB - Wiley DO - 10.1111/cts.70577 UR - https://doi.org/10.1111/cts.70577 LA - en ER -

CSL-JSON

{ "id": "10.1111/cts.70577", "type": "article-journal", "title": "Machine Learning-Based Prediction of Drug-Induced QTc Changes in a Large Finnish Biobank Cohort", "container-title": "Clinical and translational science", "author": [ { "family": "Langén", "given": "Ville" }, { "family": "Winstén", "given": "Aleksi" }, { "family": "Teppo", "given": "Konsta" }, { "family": "Pohjonen", "given": "Timo" }, { "family": "Laukkanen", "given": "Jari" }, { "family": "Mannermaa", "given": "Arto" }, { "family": "Niiranen", "given": "Teemu J" }, { "family": "Palmu", "given": "Joonatan" } ], "container-title-short": "Clin Transl Sci", "volume": "19", "issue": "5", "page": "e70577", "DOI": "10.1111/cts.70577", "PMID": "42083122", "PMCID": "PMC13139045", "ISSN": "1752-8054", "publisher": "Wiley", "URL": "https://doi.org/10.1111/cts.70577", "language": "en", "issued": { "date-parts": [ [ 2026, 5, 1 ] ] } }

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s42003-026-10957-8 [code]: Brain defence by the extracellular matrix protein Cochlin.
Journal: Communications biology
In common: caret, XGBoost, broom, 4 other tools
[2] doi:10.1038/s41592-026-03211-w [code]: Spatial isoform sequencing at single-cell resolution reveals cell-type-specific spatial isoform variability in multiple brain cell types.
Journal: Nature methods
In common: caret, XGBoost, broom, 3 other tools, genetics / omics
[3] doi:10.3390/ijms27156925 [code]: XGBoost-SHAP Interpretable Modeling Identifies and Validates an Eight-Gene Biomarker for Hepatic Encephalopathy Risk Prediction in Cirrhosis.
Journal: International journal of molecular sciences
In common: caret, XGBoost, data.table, 3 other tools, genetics / omics
[4] doi:10.1126/sciadv.aec9291 [code]: Computational mechanisms of perception in autism revealed using games inspired by rodent operant tasks.
Journal: Science advances
In common: caret, broom, data.table, 3 other tools
[5] doi:10.1016/j.xpro.2026.104695 [code]: Protocol for single-cell epigenetic profiling in human organoids and tumoroids with Epi-CyTOF.
Journal: STAR protocols
In common: caret, broom, data.table, 3 other tools
[6] doi:10.1186/s13073-026-01704-z [code]: Gene expression profiling enables refined parcellation of cortical layers in the heterogeneous human cerebral cortex.
Journal: Genome medicine
In common: XGBoost, data.table, patchwork, 2 other tools, genetics / omics, 1 reference
[7] doi:10.1093/neuonc/noag128 [code]: Spatially-resolved single-cell imaging of melanoma brain metastases identifies localized immune patterns predictive of immune checkpoint blockade response.
Journal: Neuro-oncology
In common: caret, data.table, patchwork, 2 other tools, clinical / translational, genetics / omics
[8] doi:10.1038/s41398-026-04131-1 [code]: Multimodal phenotypic classification of generalized anxiety and panic using structural MRI data and psychosocial factors: machine learning results from the German National Cohort (NAKO) study.
Journal: Translational psychiatry
In common: caret, broom, data.table, 2 other tools, clinical / translational
[9] doi:10.1038/s41467-026-77170-3 [code]: DNA methylation profiling identifies long-range epigenetic silencing of clustered protocadherins as a key determinant of meningioma progression.
Journal: Nature communications
In common: caret, broom, data.table, 2 other tools, genetics / omics
[10] doi:10.7717/peerj.21426 [code]: Integrated transcriptomic identification and validation reveal key autophagy-associated biomarkers in sleep deprivation.
Journal: PeerJ
In common: caret, data.table, patchwork, 2 other tools, genetics / omics

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.