Predictability-Computability-Stability workflow for veridical data science in the age of artificial intelligence
Clinical Snapshot
PICO Framework
| P — Population | Data science practitioners and researchers working with AI-driven methodologies |
| I — Intervention | Predictability-Computability-Stability (PCS) framework for veridical data science |
| C — Comparator | Traditional statistical frameworks for data science workflows |
| O — Outcomes | Reproducibility, uncertainty quantification, and reliability of data-driven findings in AI applications |
Bottom Line
This methodological paper presents an updated Predictability-Computability-Stability framework aimed at improving reproducibility and uncertainty quantification in data science workflows. While the framework addresses important challenges in the reproducibility crisis affecting AI-driven research, the paper lacks empirical validation of its effectiveness. The approach appears theoretically sound and could benefit healthcare applications where data-driven decisions have significant clinical implications. However, practitioners should await further validation studies before widespread implementation. The framework may be particularly relevant for Australian healthcare contexts involving large-scale data analytics, such as PBS claims analysis or clinical decision support systems, where reproducibility and uncertainty quantification are critical for regulatory compliance and patient safety.
Key Findings
Effect Size: Not quantified - methodological framework
Primary Outcome: Streamlined PCS workflow for addressing uncertainty in data science life cycle
Nnt Or Sensitivity: Framework demonstrates uncertainty quantification in data cleaning stage through case study
Clinical Application
Moderate - requires training in PCS methodology and potential workflow modifications Relevant to TGA digital health guidelines and NHMRC research integrity frameworks; applicable to PBS data analytics and clinical decision support systems Healthcare data scientists, clinical researchers using AI/ML methods, health informatics professionals
Abstract
Data science is a pillar of artificial intelligence (AI), which is transforming nearly every domain of human activity, from the social and physical sciences to engineering and medicine. While data-driven findings in AI offer unprecedented power to extract insights and guide decision-making, many are difficult or impossible to replicate. A key reason for this challenge is the uncertainty introduced by the many choices made throughout the data science life cycle (DSLC). Traditional statistical frameworks often fail to account for this uncertainty. The Predictability-Computability-Stability (PCS) framework for veridical (truthful) data science (VDS) offers a principled approach to addressing this challenge throughout the DSLC. This paper presents an updated and streamlined PCS workflow, tailored for practitioners and enhanced with guided use of generative AI (GenAI). We include a running example to display the PCS framework in action and conduct a related case study that showcases the uncertainty in downstream predictions caused by judgement calls in the data cleaning stage. This article is part of the theme issue 'Statistical workflow'.
References
- 1.Rewolinski, Z. T., & Yu, B. (2026). Predictability-Computability-Stability workflow for veridical data science in the age of artificial intelligence. Philosophical Transactions of the Royal Society A, 384(2276). https://doi.org/10.1098/rsta.2024.0605
Related Research
Journal of medical Internet research
Advancing Human-Centered AI in Clinical Decision Support: Sociocognitive Human-in-the-Loop Study in HIV Care
2 Aug 2026
Neurological research
Federated deep learning model for epilepsy seizure detection using electroencephalogram (EEG) signal
2 Aug 2026
Neural networks : the official journal of the International Neural Network Society
MFBD: Model-free backdoor defense based on vision-language pre-trained models
2 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service