Finale Doshi‐Velez

11.4k total citations · 4 hit papers
102 papers, 3.4k citations indexed

About

Finale Doshi‐Velez is a scholar working on Artificial Intelligence, Epidemiology and Pharmacology. According to data from OpenAlex, Finale Doshi‐Velez has authored 102 papers receiving a total of 3.4k indexed citations (citations by other indexed papers that have themselves been cited), including 71 papers in Artificial Intelligence, 9 papers in Epidemiology and 7 papers in Pharmacology. Recurrent topics in Finale Doshi‐Velez's work include Machine Learning in Healthcare (19 papers), Explainable Artificial Intelligence (XAI) (18 papers) and Topic Modeling (13 papers). Finale Doshi‐Velez is often cited by papers focused on Machine Learning in Healthcare (19 papers), Explainable Artificial Intelligence (XAI) (18 papers) and Topic Modeling (13 papers). Finale Doshi‐Velez collaborates with scholars based in United States, United Kingdom and Switzerland. Finale Doshi‐Velez's co-authors include Andrew Slavin Ross, Isaac S. Kohane, Yaorong Ge, Leo Anthony Celi, Marzyeh Ghassemi, Been Kim, Joseph Futoma, Morgan Simons, Trishan Panch and Mohammed Saeed and has published in prestigious journals such as Nature Medicine, PLoS ONE and IEEE Transactions on Pattern Analysis and Machine Intelligence.

In The Last Decade

Finale Doshi‐Velez

97 papers receiving 3.3k citations

Hit Papers

Do no harm: a roadmap for responsible machine learning fo... 2018 2026 2020 2023 2019 2018 2020 2024 100 200 300 400 500

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name h Career Trend Papers Cites
Finale Doshi‐Velez United States 25 1.9k 667 329 299 280 102 3.4k
Katherine Heller United States 23 985 0.5× 329 0.5× 151 0.5× 167 0.6× 135 0.5× 57 2.0k
Riccardo Miotto United States 18 2.2k 1.2× 674 1.0× 839 2.6× 331 1.1× 214 0.8× 48 4.7k
Shaker El–Sappagh Egypt 39 2.3k 1.2× 403 0.6× 815 2.5× 443 1.5× 152 0.5× 146 5.3k
Volodymyr Kuleshov United States 13 1.1k 0.6× 656 1.0× 743 2.3× 262 0.9× 88 0.3× 29 2.9k
Giuseppe De Pietro Italy 32 1.7k 0.9× 248 0.4× 366 1.1× 698 2.3× 481 1.7× 211 4.4k
Haipeng Shen United States 25 940 0.5× 1.1k 1.6× 757 2.3× 163 0.5× 87 0.3× 85 4.6k
Sijia Liu United States 24 1.8k 0.9× 214 0.3× 257 0.8× 185 0.6× 104 0.4× 159 3.2k
Parisa Rashidi United States 32 1.6k 0.8× 668 1.0× 450 1.4× 2.0k 6.7× 198 0.7× 144 6.3k
Javier Andreu-Pérez United Kingdom 18 885 0.5× 153 0.2× 482 1.5× 359 1.2× 510 1.8× 77 2.9k
Suchi Saria United States 27 1.3k 0.7× 942 1.4× 486 1.5× 97 0.3× 119 0.4× 80 4.0k

Countries citing papers authored by Finale Doshi‐Velez

Since Specialization
Citations

This map shows the geographic impact of Finale Doshi‐Velez's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Finale Doshi‐Velez with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Finale Doshi‐Velez more than expected).

Fields of papers citing papers by Finale Doshi‐Velez

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Finale Doshi‐Velez. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Finale Doshi‐Velez. The network helps show where Finale Doshi‐Velez may publish in the future.

Co-authorship network of co-authors of Finale Doshi‐Velez

This figure shows the co-authorship network connecting the top 25 collaborators of Finale Doshi‐Velez. A scholar is included among the top collaborators of Finale Doshi‐Velez based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Finale Doshi‐Velez. Finale Doshi‐Velez is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

20 of 20 papers shown
1.
Zhou, Yu, Tommaso Proietti, Kristin Nuckols, et al.. (2025). Estimating Upper Extremity Fugl-Meyer Assessment Scores From Reaching Motions Using Wearable Sensors. IEEE Journal of Biomedical and Health Informatics. 29(6). 4134–4146. 3 indexed citations
2.
Pan, Weiwei, et al.. (2025). Preference-based assistance optimization for lifting and lowering with a soft back exosuit. Science Advances. 11(15). eadu2099–eadu2099. 3 indexed citations
3.
Lage, Isaac, Thomas H. McCoy, Roy H. Perlis, & Finale Doshi‐Velez. (2022). Efficiently identifying individuals at high risk for treatment resistance in major depressive disorder using electronic health records. Journal of Affective Disorders. 306. 254–259. 10 indexed citations
4.
Lage, Isaac, Melanie F. Pradier, Thomas H. McCoy, Roy H. Perlis, & Finale Doshi‐Velez. (2022). Do clinicians follow heuristics in prescribing antidepressants?. Journal of Affective Disorders. 311. 110–114. 3 indexed citations
5.
Kim, Been & Finale Doshi‐Velez. (2021). Machine Learning Techniques for Accountability. AI Magazine. 42(1). 47–52. 13 indexed citations
6.
Wang, Kai, et al.. (2021). Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Making by Reinforcement Learning. arXiv (Cornell University). 34. 8 indexed citations
7.
Graule, Moritz A., et al.. (2020). Incorporating Interpretable Output Constraints in Bayesian Neural Networks. Neural Information Processing Systems. 33. 12721–12731. 1 indexed citations
8.
Lu, Mingyu, et al.. (2020). Is Deep Reinforcement Learning Ready for Practical Applications in Healthcare? A Sensitivity Analysis of Duel-DDQN for Sepsis Treatment. arXiv (Cornell University). 1 indexed citations
9.
Futoma, Joseph, et al.. (2020). Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs. Neural Information Processing Systems. 33. 19805–19816. 1 indexed citations
10.
Pradier, Melanie F., Michael C. Hughes, Thomas H. McCoy, et al.. (2020). Predicting change in diagnosis from major depression to bipolar disorder after antidepressant initiation. Neuropsychopharmacology. 46(2). 455–461. 18 indexed citations
11.
Doshi‐Velez, Finale, et al.. (2019). Unsupervised Learning of PCFGs with Normalizing Flow. 2442–2452. 17 indexed citations
12.
Hughes, Michael C., et al.. (2018). Semi-Supervised Prediction-Constrained Topic Models. International Conference on Artificial Intelligence and Statistics. 1067–1076. 6 indexed citations
13.
Doshi‐Velez, Finale & Been Kim. (2017). A Roadmap for a Rigorous Science of Interpretability.. arXiv (Cornell University). 55 indexed citations
14.
Fan, Angela, Finale Doshi‐Velez, & Luke Miratrix. (2017). Promoting Domain-Specific Terms in Topic Models with Informative Priors.. arXiv (Cornell University). 1 indexed citations
15.
Kim, Been, Julie Shah, & Finale Doshi‐Velez. (2015). Mind the Gap: a generative approach to interpretable feature selection and extraction. Neural Information Processing Systems. 28. 2260–2268. 53 indexed citations
16.
Doshi‐Velez, Finale, David Pfau, Frank Wood, & Nicholas Roy. (2015). Bayesian Nonparametric Methods for Partially-Observable Reinforcement Learning. DSpace@MIT (Massachusetts Institute of Technology). 6 indexed citations
17.
Ghassemi, Marzyeh, Finale Doshi‐Velez, Rohit Joshi, et al.. (2014). Unfolding physiological state: mortality modelling in intensive care units. DSpace@MIT (Massachusetts Institute of Technology). 32 indexed citations
18.
Doshi‐Velez, Finale & George Konidaris. (2012). Transfer Learning by Discovering Latent Task Parametrizations. Neural Information Processing Systems. 1 indexed citations
19.
Doshi‐Velez, Finale, David Wingate, Nicholas Roy, & Joshua B. Tenenbaum. (2010). Nonparametric Bayesian Policy Priors for Reinforcement Learning. DSpace@MIT (Massachusetts Institute of Technology). 23. 532–540. 18 indexed citations
20.
Doshi‐Velez, Finale. (2009). The Infinite Partially Observable Markov Decision Process. Neural Information Processing Systems. 22. 477–485. 44 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact

Rankless by CCL
2026