# JCTS Calls for Proven AI That Improves Clinical and Translational Research

> JCTS seeks proven, real-world AI that measurably improves clinical and translational research. Submit rigorous methods, outcomes, successes and failures by July 16, 2026.

- Type: AI news
- Page: https://completeaitraining.com/news/jcts-calls-for-proven-ai-that-improves-clinical-and/
- Published: 2026-02-04
- Updated: 2026-02-20
- Author: Jeroen Erne
- Jobs: Science and research
- Reading time: 3 min

### JCTS call for papers: how AI is advancing clinical and translational research

**Date:** 03 February 2026

The Journal of Clinical and Translational Science (JCTS) is opening a thematic issue: Artificial Intelligence in Action - Tested and Proven Approaches to Transforming Clinical and Translational Science. The focus is simple: show validated AI that measurably improves clinical or translational research. Methods, data, outcomes, and lessons learned-all on the table; see related [Research](https://completeaitraining.com/tag/research/) resources for methods and evaluation guidance.

#### What JCTS is looking for

- Validated AI approaches with clear methods, strong datasets, and measurable outcomes that raise effectiveness, efficiency, generalizability, and reliability of clinical and translational research.
- Proven solutions for scaling the infrastructure and capabilities that enable AI tools across CTS teams and institutions.
- Real-world evaluations of AI in practice-implementation, effectiveness, efficiency, quality, decision-making, resource allocation, and other CTS outcomes.
- Critical analyses where AI fell short. Detail the causes-data quality, algorithmic bias, health disparities, generalizability limits, integration issues, or contextual constraints-and what to change next time.
- Broader findings on trust, interpretability, transparency, sustainability, scalability, reproducibility, generalizability, interoperability, regulatory alignment, and ethical, equitable, cost-effective deployment.
- Implementation of innovative scientific and research processes that meaningfully use AI tools.
- Methods that measure and communicate AI uncertainty to stakeholders across the CTS enterprise.
- Approaches for continuous monitoring and adaptive learning to detect performance drift and sustain accuracy, fairness, and reliability over time.
- Evaluations of how AI affects the translational science workforce, including clinical partners.
- Scalable methods for evaluating human-AI collaboration-usability, researcher and participant engagement, and workflow integration.
- Active engagement of patients and communities as collaborators throughout development and implementation.

#### Eligible AI domains

All scientifically rigorous AI domains are in scope, including:

- Predictive modeling (e.g., risk stratification for precision clinical trials)
- Unsupervised natural language processing (e.g., clinical information extraction without expert annotations for screening, outcomes, or safety signals)
- Computer vision (e.g., endpoints from medical imaging and digital pathology)
- Causal inference (e.g., counterfactual modeling, target trial emulation)
- Generative AI and AI agents (e.g., drafting research documentation, coding assistance, participant or researcher conversational agents)
- Reinforcement learning (e.g., adaptive treatment strategies and decision support)
- Multi-modal integration (e.g., combining EHR, imaging, genomic, and other sources)

#### Where your work can fit

Submissions can span the full translational spectrum-from basic discovery and early algorithm development to clinical integration and population health impact. Priority goes to work that removes a bottleneck in the translational pathway.

- Innovative AI for trial design
- Tools and strategies to improve participant recruitment and retention
- Data harmonization and interoperability methods
- Decision support systems integrated into clinical workflows
- Post-market surveillance approaches

#### What strong manuscripts show

- Clear problem definition, rigorous methods, and reproducible results with measurable impact.
- Transparency: datasets, code, and reporting aligned with established guidance where possible (e.g., [CONSORT-AI](https://www.equator-network.org/reporting-guidelines/consort-ai/?ref=completeaitraining.com) for trials).
- Evidence of reliability across settings, populations, and time-plus uncertainty estimation, monitoring, and drift mitigation.
- Thoughtful handling of bias, equity, safety, and governance-including patient and community input.
- Operational fit: usability, workflow integration, training needs, and workforce implications.

#### Key dates and how to submit

**Deadline for submission: July 16, 2026**

For details and submission guidelines, visit the JCTS website: [cambridge.org/core/journals/journal-of-clinical-and-translational-science](https://www.cambridge.org/core/journals/journal-of-clinical-and-translational-science?ref=completeaitraining.com).

#### Why this call matters

Clinical and translational teams need evidence that AI works under real constraints. This issue aims to surface what actually moves research and care forward-what scales, what sustains, and what translates to better decisions and outcomes.

#### Getting your team ready

- Pre-specify metrics and evaluation plans appropriate to the setting.
- Document uncertainty, monitoring, and guardrails from day one.
- Plan for data quality, interoperability, and governance as first-class requirements.
- Include patient, community, and clinical partner feedback throughout development and deployment.
- Consider structured training such as the [AI Learning Path for Data Scientists](https://completeaitraining.com/learningpath/ai-for-data-scientists/) to equip teams with reproducible methods and practical skills for translational AI.

---

This is the Markdown form of https://completeaitraining.com/news/jcts-calls-for-proven-ai-that-improves-clinical-and/. The whole site is mapped at https://completeaitraining.com/llms.txt.
