EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The evaluation crisis in artificial intelligence‐driven computational biology: Pitfalls and solutions

Tsung Fei Khang, Joshua W K Ho, Lin Hou, Jiangning Song, Limsoon Wong

Quantitative Biology · 2026-12 · 14 (4)

DOI: 10.1002/qub2.70058 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Quantitative Biology, online erschienen am 23.09.2026. Verfasst von Tsung Fei Khang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Mathematical Sciences, Faculty of Science Universiti Malaya Kuala Lumpur Malaysia. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence (AI) is rapidly transforming computational biology. However, closer scrutiny reveals that many reported results do not hold under rigorous evaluation. This paper identifies prevalent, recurring issues in the field, including narrow datasets, hidden confounders that make supposedly independent test data effectively indistinguishable from the training data (the doppelgänger effect), misleading performance metrics, and over‐reliance on overly easy test cases. We argue that meaningful assessment must go beyond metric‐centric model evaluation to encompass biological realism, data diversity, confounding control, and interpretability. Crucially, AI studies in computational biology should deliver not only predictive performance but also genuine biological insight and transferable methodological understanding. To address these systemic limitations, we propose a unifying framework, VALID, comprising the following five guiding principles for rigorous AI in biology: Veracious biological grounding and novelty, artifact control and methodological rigor, legitimate generalization, inspectable preprocessing, and deployment‐aware performance. Together, these principles serve as a diagnostic lens for structuring our discussion throughout this paper. We further illustrate common pitfalls through representative examples and provide actionable guidance for authors, reviewers, and editors aimed at improving the rigor and scientific value of AI‐driven computational biology.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencebiological validitycomputational biologygeneralizationmodel evaluation

Autor:innen und Institutionen

  • Institute of Mathematical Sciences, Faculty of Science Universiti Malaya Kuala Lumpur Malaysia.
  • Universiti Malaya Centre for Data Analytics Universiti Malaya Kuala Lumpur Malaysia.
  • School of Biomedical Sciences, Li Ka Shing Faculty of Medicine The University of Hong Kong Hong Kong China.
  • School of Biomedical Engineering The University of Hong Kong Hong Kong China.
  • Centre for Health AI Research and Translation (CHART), Li Ka Shing Faculty of Medicine The University of Hong Kong Hong Kong China.
  • Department of Statistics and Data Science Tsinghua University Beijing China.

Zitieren

APA

Khang, T. F., Ho, J. W. K., Hou, L., Song, J., & Wong, L. (2026). The evaluation crisis in artificial intelligence‐driven computational biology: Pitfalls and solutions. Quantitative Biology, 14(4). https://doi.org/10.1002/qub2.70058

Vancouver

Khang TF, Ho JWK, Hou L, Song J, Wong L. The evaluation crisis in artificial intelligence‐driven computational biology: Pitfalls and solutions. Quantitative Biology. 2026;14(4). doi:10.1002/qub2.70058

BibTeX
@article{Khang2026,
  author = {Khang, Tsung Fei and Ho, Joshua W K and Hou, Lin and Song, Jiangning and Wong, Limsoon},
  title = {The evaluation crisis in artificial intelligence‐driven computational biology: Pitfalls and solutions},
  journal = {Quantitative Biology},
  year = {2026},
  volume = {14},
  number = {4},
  doi = {10.1002/qub2.70058}
}
Kostenlos starten →