Computational pathology researcher in AI for oncology — multimodal survival prediction and explainable AI
2
papers here
1
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-17) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Publication-count and output-volume metrics are not yet available for this profile, so output is unscored. This axis would measure the number and cadence of peer-reviewed papers, venue quality, and first/corresponding-author share across the career record.
Impact—
Citation-based impact metrics (citations, h-index, highly-cited papers) are absent from the current data, so impact is unscored. It would measure how widely the work influences computational pathology research and clinical AI practice over time.
Focus100/100
The radar assigns focus a perfect 100, and the underlying field distribution backs this: every paper in the current Evolve catalog (2 of 2, both 2026 arXiv preprints) falls under computational pathology / AI for oncology. Work spans survival modeling with whole-slide images and genomics plus an XAI taxonomy paper, but all of it targets a single application domain rather than spreading across fields.
Collaboration60/100
Collaboration scores 60, derived from 19 distinct coauthors in the input data. The frequent-coauthor list — including Francesco Ciompi, Nasir Rajpoot, Geert Litjens, Anne L. Martel, Joe Yeong, and Michael Feldman — points to an active computational-pathology network. In both cataloged papers the researcher holds a middle author position without corresponding role, consistent with contributing within larger teams rather than leading as first or corresponding author.
Activity—
Publishing-activity data (yearly output, recent submission cadence) is insufficient here, so activity is unscored. This axis would track how consistently the researcher publishes over recent years and whether momentum is rising, stable, or slowing.
Reproducibility55/100
Reproducibility scores 55, averaged over just one scored paper (reproPapers = 1): the MIST survival-prediction preprint, whose readiness Evolve rates as medium. The review credits credible external validation across 4 survival cohorts but flags that reported gains lack significance tests and are modest versus WSI-only baselines. Because the sample is a single paper, this score should be read as an early, low-confidence signal.
Research summary
Jana Lipkova is a researcher in computational pathology and AI for oncology, profiled here from public bibliographic data resolved to ORCID 0000-0001-8101-4794. The current Evolve catalog holds two 2026 arXiv preprints, both with the researcher in a middle author position and neither as corresponding author. The first, MIST: Multimodal Survival Prediction with Genomic-Guided Histology Attention, uses cross-attention so that genomic data guides whole-slide-image analysis for survival prediction; Evolve's review calls the external evidence credible across 4 survival cohorts, while noting the reported gains lack significance tests and are modest relative to WSI-only baselines, with medium reproducibility readiness (radar reproducibility 55, averaged over one scored paper). The second is a methods paper on explainable AI (XAI) in computational pathology, offering definitions, a taxonomy, and recommendations — a sign of interest in making pathology AI interpretable, not just accurate. Focus is the standout dimension at 100: every cataloged paper sits in a single field, computational pathology / AI for oncology. Collaboration scores 60 on 19 distinct coauthors, with frequent coauthors including Francesco Ciompi, Nasir Rajpoot, Geert Litjens, Anne L. Martel, Joe Yeong, and Michael Feldman — a network consistent with the digital pathology setting of the cataloged work. Output, impact, and activity dimensions are unscored because the underlying bibliometric data is not yet available. Institution and country are not present in the input data.
Collaboration pattern
With 19 distinct coauthors in the input data, collaboration is team-based rather than solitary. The frequent-coauthor list includes names consistent with the computational-pathology setting of the cataloged work — Francesco Ciompi, Nasir Rajpoot, Geert Litjens, Anne L. Martel, Joe Yeong, Michael Feldman, and Dimitrios Makris — alongside Shubham Innani, Suhang You, Adam Shephard, and Bhakti Baheti. Both cataloged papers place Lipkova in a middle author position without corresponding authorship, consistent with a contributing role within larger research teams rather than first- or last-author leadership.
Research keywords
Highlights
Genomic-guided histology attention for survival prediction (MIST)
External validation across 4 survival cohorts — with statistical caveats
Co-authorship on XAI definitions, taxonomy, and recommendations for computational pathology
The second cataloged 2026 arXiv preprint, 'Explainable Artificial Intelligence (XAI) in Computational Pathology: Definitions, Taxonomy, and Recommendations,' lists Lipkova as a middle author; Evolve has not yet published a verdict, keywords, or reproducibility rating for it.
Timeline
- 2026Posted to arXiv as a middle author on MIST, a multimodal survival-prediction model using genomic-guided histology attention; Evolve rates its reproducibility readiness as medium.
- 2026Co-authored the arXiv paper 'Explainable Artificial Intelligence (XAI) in Computational Pathology: Definitions, Taxonomy, and Recommendations', again in a middle author position.
- 2026Both cataloged outputs fall in a single field — computational pathology / AI for oncology — supporting a perfect focus score of 100, with 19 distinct coauthors recorded in the data.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometric scores rest on a very small sample: the reproducibility mean covers only 1 scored paper, and the field distribution covers a single cataloged paper.
- Output, impact, and activity dimensions lack underlying bibliometric data and are deliberately unscored rather than estimated.
- Institution, country, and career history are absent from the input data; identity is resolved via ORCID 0000-0001-8101-4794 and public bibliographic records.
- Only two papers (both 2026 arXiv preprints) appear in the Evolve catalog; peer-reviewed venue publications are not represented in this snapshot.