Greg Corrado
Greg Corrado is a senior research scientist interested in biological neuroscience, artificial intelligence, and scalable machine learning. He has published in fields ranging across behavioral economics, neuromorphic device physics, systems neuroscience, and deep learning. At Google he has worked for some time on brain inspired computing, and most recently has served as one of the founding members and the co-technical lead of Google's large scale deep neural networks project.
Authored Publications
Sort By
Performance of a Deep Learning Diabetic Retinopathy Algorithm in India
Arthur Brant
Xiang Yin
Lu Yang
Divleen Jeji
Sunny Virmani
Anchintha Meenu
Naresh Babu Kannan
Florence Thng
Lily Peng
Ramasamy Kim
JAMA Network Open (2025)
Preview abstract
Importance: While prospective studies have investigated the accuracy of artificial intelligence (AI) for detection of diabetic retinopathy (DR) and diabetic macular edema (DME), to date, little published data exist on the clinical performance of these algorithms.
Objective: To evaluate the clinical performance of an automated retinal disease assessment (ARDA) algorithm in the postdeployment setting at Aravind Eye Hospital in India.
Design, Setting, and Participants: This cross-sectional analysis involved an approximate 1% sample of fundus photographs from patients screened using ARDA. Images were graded via adjudication by US ophthalmologists for DR and DME, and ARDA’s output was compared against the adjudicated grades at 45 sites in Southern India. Patients were randomly selected between January 1, 2019, and July 31, 2023.
Main Outcomes and Measures: Primary analyses were the sensitivity and specificity of ARDA for severe nonproliferative DR (NPDR) or proliferative DR (PDR). Secondary analyses focused on sensitivity and specificity for sight-threatening DR (STDR) (DME or severe NPDR or PDR).
Results: Among the 4537 patients with 4537 images with adjudicated grades, mean (SD) age was 55.2 (11.9) years and 2272 (50.1%) were male. Among the 3941 patients with gradable photographs, 683 (17.3%) had any DR, 146 (3.7%) had severe NPDR or PDR, 109 (2.8%) had PDR, and 398 (10.1%) had STDR. ARDA’s sensitivity and specificity for severe NPDR or PDR were 97.0% (95% CI, 92.6%-99.2%) and 96.4% (95% CI, 95.7%-97.0%), respectively. Positive predictive value (PPV) was 50.7% and negative predictive value (NPV) was 99.9%. The clinically important miss rate for severe NPDR or PDR was 0% (eg, some patients with severe NPDR or PDR were interpreted as having moderate DR and referred to clinic). ARDA’s sensitivity for STDR was 95.9% (95% CI, 93.0%-97.4%) and specificity was 94.9% (95% CI, 94.1%-95.7%); PPV and NPV were 67.9% and 99.5%, respectively.
Conclusions and Relevance: In this cross-sectional study investigating the clinical performance of ARDA, sensitivity and specificity for severe NPDR and PDR exceeded 96% and caught 100% of patients with severe NPDR and PDR for ophthalmology referral. This preliminary large-scale postmarketing report of the performance of ARDA after screening 600 000 patients in India underscores the importance of monitoring and publication an algorithm's clinical performance, consistent with recommendations by regulatory bodies.
View details
Triaging mammography with artificial intelligence: an implementation study
Sarah M. Friedewald
Sunny Jansen
Fereshteh Mahvar
Timo Kohlberger
David V. Schacht
Sonya Bhole
Dipti Gupta
Scott Mayer McKinney
Stacey Caron
David Melnick
Mozziyar Etemadi
Samantha Winter
Alejandra Maciel
Luca Speroni
Martha Sevenich
Arnav Agharwal
Rubin Zhang
Gavin Duggan
Shiro Kadowaki
Atilla Kiraly
Jie Yang
Basil Mustafa
Krish Eswaran
Shravya Shetty
Breast Cancer Research and Treatment (2025)
Preview abstract
Purpose
Many breast centers are unable to provide immediate results at the time of screening mammography which results in delayed patient care. Implementing artificial intelligence (AI) could identify patients who may have breast cancer and accelerate the time to diagnostic imaging and biopsy diagnosis.
Methods
In this prospective randomized, unblinded, controlled implementation study we enrolled 1000 screening participants between March 2021 and May 2022. The experimental group used an AI system to prioritize a subset of cases for same-visit radiologist evaluation, and same-visit diagnostic workup if necessary. The control group followed the standard of care. The primary operational endpoints were time to additional imaging (TA) and time to biopsy diagnosis (TB).
Results
The final cohort included 463 experimental and 392 control participants. The one-sided Mann-Whitney U test was employed for analysis of TA and TB. In the control group, the TA was 25.6 days [95% CI 22.0–29.9] and TB was 55.9 days [95% CI 45.5–69.6]. In comparison, the experimental group's mean TA was reduced by 25% (6.4 fewer days [one-sided 95% CI > 0.3], p<0.001) and mean TB was reduced by 30% (16.8 fewer days; 95% CI > 5.1], p=0.003). The time reduction was more pronounced for AI-prioritized participants in the experimental group. All participants eventually diagnosed with breast cancer were prioritized by the AI.
Conclusions
Implementing AI prioritization can accelerate care timelines for patients requiring additional workup, while maintaining the efficiency of delayed interpretation for most participants. Reducing diagnostic delays could contribute to improved patient adherence, decreased anxiety and addressing disparities in access to timely care.
View details
Closing the AI generalisation gap by adjusting for dermatology condition distribution differences across clinical settings
Rajeev Rikhye
Aaron Loh
Grace Hong
Margaret Ann Smith
Vijaytha Muralidharan
Doris Wong
Michelle Phung
Nicolas Betancourt
Bradley Fong
Rachna Sahasrabudhe
Khoban Nasim
Alec Eschholz
Basil Mustafa
Jan Freyberg
Terry Spitz
Kat Chou
Peggy Bui
Justin Ko
Steven Lin
The Lancet eBioMedicine (2025)
Preview abstract
Background: Generalisation of artificial intelligence (AI) models to a new setting is challenging. In this study, we seek to understand the robustness of a dermatology (AI) model and whether it generalises from telemedicine cases to a new setting including both patient-submitted photographs (“PAT”) and clinician-taken photographs in-clinic (“CLIN”).
Methods: A retrospective cohort study involving 2500 cases previously unseen by the AI model, including both PAT and CLIN cases, from 22 clinics in the San Francisco Bay Area, spanning November 2015 to January 2021. The primary outcome measure for the AI model and dermatologists was the top-3 accuracy, defined as whether their top 3 differential diagnoses contained the top reference diagnosis from a panel of dermatologists per case.
Findings: The AI performed similarly between PAT and CLIN images (74% top-3 accuracy in CLIN vs. 71% in PAT), however, dermatologists were more accurate in PAT images (79% in CLIN vs. 87% in PAT). We demonstrate that demographic factors were not associated with AI or dermatologist errors; instead several categories of conditions were associated with AI model errors (p < 0.05). Resampling CLIN and PAT to match skin condition distributions to the AI development dataset reduced the observed differences (AI: 84% CLIN vs. 79% PAT; dermatologists: 77% CLIN vs. 89% PAT). We demonstrate a series of steps to close the generalisation gap, requiring progressively more information about the new dataset, ranging from the condition distribution to additional training data for rarer conditions. When using additional training data and testing on the dataset without resampling to match AI development, we observed comparable performance from end-to-end AI model fine tuning (85% in CLIN vs. 83% in PAT) vs. fine tuning solely the classification layer on top of a frozen embedding model (86% in CLIN vs. 84% in PAT).
Interpretation: AI algorithms can be efficiently adapted to new settings without additional training data by recalibrating the existing model, or with targeted data acquisition for rarer conditions and retraining just the final layer.
View details
Searching for Dermatology Information Online using Images vs Text: a Randomized Study
Jay Hartford
Natalie Salaets
Kimberley Raiford
Dounia Berrada
Harsh Kharbanda
Lou Wang
Peggy Bui
medRxiv (2024)
Preview abstract
Background Skin conditions are extremely common worldwide, and are an important cause of both anxiety and morbidity. Since the advent of the internet, individuals have used text-based search (eg, “red rash on arm”) to learn more about concerns on their skin, but this process is often hindered by the inability to accurately describe the lesion’s morphology. In the study, we surveyed respondents’ experiences with an image-based search, compared to the traditional text-based search experience.
Methods An internet-based survey was conducted to evaluate the experience of text-based vs image-based search for skin conditions. We recruited respondents from an existing cohort of volunteers in a commercial survey panel; survey respondents that met inclusion/exclusion criteria, including willingness to take photos of a visible concern on their body, were enrolled. Respondents were asked to use the Google mobile app to conduct both regular text-based search (Google Search) and image-based search (Google Lens) for their concern, with the order of text vs. image search randomized. Satisfaction for each search experience along six different dimensions were recorded and compared, and respondents’ preferences for the different search types along these same six dimensions were recorded.
Results 372 respondents were enrolled in the study, with 44% self-identifying as women, 86% as White and 41% over age 45. The rate of respondents who were at least moderately familiar with searching for skin conditions using text-based search versus image-based search were 81.5% and 63.5%, respectively. After using both search modalities, respondents were highly satisfied with both image-based and text-based search, with >90% at least somewhat satisfied in each dimension and no significant differences seen between text-based and image-based search when examining the responses on an absolute scale per search modality. When asked to directly rate their preferences in a comparative way, survey respondents preferred image-based search over text-based search in 5 out of 6 dimensions, with an absolute 9.9% more preferring image-based search over text-based search overall (p=0.004). 82.5% (95% CI 78.2 - 86.3) reported a preference to leverage image-based search (alone or in combination with text-based search) in future searches. Of those who would prefer to use a combination of both, 64% indicated they would like to start with image-based search, indicating that image-based search may be the preferred entry point for skin-related searches.
Conclusion Despite being less familiar with image-based search upon study inception, survey respondents generally preferred image-based search to text-based search and overwhelmingly wanted to include this in future searches. These results suggest the potential for image-based search to play a key role in people searching for information regarding skin concerns.
View details
Prospective Multi-Site Validation of AI to Detect Tuberculosis and Chest X-Ray Abnormalities
Sahar Kazemzadeh
Atilla Kiraly
Nsala Sanjase
Minyoi Maimbolwa
Brian Shuma
Shahar Jamshy
Christina Chen
Arnav Agharwal
Chuck Lau
Daniel Golden
Jin Yu
Eric Wu
Kat Chou
Shravya Shetty
Krish Eswaran
Rory Pilgrim
Monde Muyoyeta
NEJM AI (2024)
Preview abstract
Background
Using artificial intelligence (AI) to interpret chest X-rays (CXRs) could support accessible triage tests for active pulmonary tuberculosis (TB) in resource-constrained settings.
Methods
The performance of two cloud-based CXR AI systems — one to detect TB and the other to detect CXR abnormalities — in a population with a high TB and human immunodeficiency virus (HIV) burden was evaluated. We recruited 1978 adults who had TB symptoms, were close contacts of known TB patients, or were newly diagnosed with HIV at three clinical sites. The TB-detecting AI (TB AI) scores were converted to binary using two thresholds: a high-sensitivity threshold and an exploratory threshold designed to resemble radiologist performance. Ten radiologists reviewed images for signs of TB, blinded to the reference standard. Primary analysis measured AI detection noninferiority to radiologist performance. Secondary analysis evaluated AI detection as compared with the World Health Organization (WHO) targets (90% sensitivity, 70% specificity). Both used an absolute margin of 5%. The abnormality-detecting AI (abnormality AI) was evaluated for noninferiority to a high-sensitivity target suitable for triaging (90% sensitivity, 50% specificity).
Results
Of the 1910 patients analyzed, 1827 (96%) had conclusive TB status, of which 649 (36%) were HIV positive and 192 (11%) were TB positive. The TB AI’s sensitivity and specificity were 87% and 70%, respectively, at the high-sensitivity threshold and 78% and 82%, respectively, at the balanced threshold. Radiologists’ mean sensitivity was 76% and mean specificity was 82%. At the high-sensitivity threshold, the TB AI was noninferior to average radiologist sensitivity (P<0.001) but not to average radiologist specificity (P=0.99) and was higher than the WHO target for specificity but not sensitivity. At the balanced threshold, the TB AI was comparable to radiologists. The abnormality AI’s sensitivity and specificity were 97% and 79%, respectively, with both meeting the prespecified targets.
Conclusions
The CXR TB AI was noninferior to radiologists for active pulmonary TB triaging in a population with a high TB and HIV burden. Neither the TB AI nor the radiologists met WHO recommendations for sensitivity in the study population. AI can also be used to detect other CXR abnormalities in the same population.
View details
Searching for Dermatology Information Online using Images vs Text: a Randomized Study
Jay Hartford
Natalie Salaets
Kimberley Raiford
Dounia Berrada
Harsh Kharbanda
Lou Wang
Peggy Bui
medRxiv (2024)
Preview abstract
Background: Skin conditions are extremely common worldwide, and are an important cause of both anxiety and morbidity. Since the advent of the internet, individuals have used text-based search (eg, “red rash on arm”) to learn more about concerns on their skin, but this process is often hindered by the inability to accurately describe the lesion’s morphology. In the study, we surveyed respondents’ experiences with an image-based search, compared to the traditional text-based search experience.
Methods: An internet-based survey was conducted to evaluate the experience of text-based vs image-based search for skin conditions. We recruited respondents from an existing cohort of volunteers in a commercial survey panel; survey respondents that met inclusion/exclusion criteria, including willingness to take photos of a visible concern on their body, were enrolled. Respondents were asked to use the Google mobile app to conduct both regular text-based search (Google Search) and image-based search (Google Lens) for their concern, with the order of text vs. image search randomized. Satisfaction for each search experience along six different dimensions were recorded and compared, and respondents’ preferences for the different search types along these same six dimensions were recorded.
Results: 372 respondents were enrolled in the study, with 44% self-identifying as women, 86% as White and 41% over age 45. The rate of respondents who were at least moderately familiar with searching for skin conditions using text-based search versus image-based search were 81.5% and 63.5%, respectively. After using both search modalities, respondents were highly satisfied with both image-based and text-based search, with >90% at least somewhat satisfied in each dimension and no significant differences seen between text-based and image-based search when examining the responses on an absolute scale per search modality. When asked to directly rate their preferences in a comparative way, survey respondents preferred image-based search over text-based search in 5 out of 6 dimensions, with an absolute 9.9% more preferring image-based search over text-based search overall (p=0.004). 82.5% (95% CI 78.2 - 86.3) reported a preference to leverage image-based search (alone or in combination with text-based search) in future searches. Of those who would prefer to use a combination of both, 64% indicated they would like to start with image-based search, indicating that image-based search may be the preferred entry point for skin-related searches.
Conclusion: Despite being less familiar with image-based search upon study inception, survey respondents generally preferred image-based search to text-based search and overwhelmingly wanted to include this in future searches. These results suggest the potential for image-based search to play a key role in people searching for information regarding skin concerns.
View details
A Toolbox for Surfacing Health Equity Harms and Biases in Large Language Models
Heather Cole-Lewis
Nenad Tomašev
Liam McCoy
Leo Anthony Celi
Alanna Walton
Chirag Nagpal
Akeiylah DeWitt
Philip Mansfield
Sushant Prakash
Joelle Barral
Ivor Horn
Karan Singhal
Nature Medicine (2024)
Preview abstract
Large language models (LLMs) hold promise to serve complex health information needs but also have the potential to introduce harm and exacerbate health disparities. Reliably evaluating equity-related model failures is a critical step toward developing systems that promote health equity. We present resources and methodologies for surfacing biases with potential to precipitate equity-related harms in long-form, LLM-generated answers to medical questions and conduct a large-scale empirical case study with the Med-PaLM 2 LLM. Our contributions include a multifactorial framework for human assessment of LLM-generated answers for biases and EquityMedQA, a collection of seven datasets enriched for adversarial queries. Both our human assessment framework and our dataset design process are grounded in an iterative participatory approach and review of Med-PaLM 2 answers. Through our empirical study, we find that our approach surfaces biases that may be missed by narrower evaluation approaches. Our experience underscores the importance of using diverse assessment methodologies and involving raters of varying backgrounds and expertise. While our approach is not sufficient to holistically assess whether the deployment of an artificial intelligence (AI) system promotes equitable health outcomes, we hope that it can be leveraged and built upon toward a shared goal of LLMs that promote accessible and equitable healthcare.
View details
Preview abstract
Importance: Interest in artificial intelligence (AI) has reached an all-time high, and health care leaders across the ecosystem are faced with questions about where, when, and how to deploy AI and how to understand its risks, problems, and possibilities.
Observations: While AI as a concept has existed since the 1950s, all AI is not the same. Capabilities and risks of various kinds of AI differ markedly, and on examination 3 epochs of AI emerge. AI 1.0 includes symbolic AI, which attempts to encode human knowledge into computational rules, as well as probabilistic models. The era of AI 2.0 began with deep learning, in which models learn from examples labeled with ground truth. This era brought about many advances both in people’s daily lives and in health care. Deep learning models are task-specific, meaning they do one thing at a time, and they primarily focus on classification and prediction. AI 3.0 is the era of foundation models and generative AI. Models in AI 3.0 have fundamentally new (and potentially transformative) capabilities, as well as new kinds of risks, such as hallucinations. These models can do many different kinds of tasks without being retrained on a new dataset. For example, a simple text instruction will change the model’s behavior. Prompts such as “Write this note for a specialist consultant” and “Write this note for the patient’s mother” will produce markedly different content.
Conclusions and Relevance: Foundation models and generative AI represent a major revolution in AI’s capabilities, ffering tremendous potential to improve care. Health care leaders are making decisions about AI today. While any heuristic omits details and loses nuance, the framework of AI 1.0, 2.0, and 3.0 may be helpful to decision-makers because each epoch has fundamentally different capabilities and risks.
View details
Towards a Personal Health Large Language Model
Anastasiya Belyaeva
Nick Furlotte
Zhun Yang
Chace Lee
Erik Schenck
Yojan Patel
Jian Cui
Logan Schneider
Robby Bryant
Ryan Gomes
Allen Jiang
Roy Lee
Javier Perez
Jamie Rogers
Cathy Speed
Shyam Tailor
Megan Walker
Jeffrey Yu
Tim Althoff
Conor Heneghan
Mark Malhotra
Shwetak Patel
Shravya Shetty
Jiening Zhan
Yeswanth Subramanian
Daniel McDuff
arXiv (2024)
Preview abstract
Large language models (LLMs) can retrieve, reason over, and make inferences about a wide range of information. In health, most LLM efforts to date have focused on clinical tasks. However, mobile and wearable devices, which are rarely integrated into clinical tasks, provide a rich, continuous, and longitudinal source of data relevant for personal health monitoring. Here we present a new model, Personal Health Large Language Model (PH-LLM), a version of Gemini fine-tuned for text understanding and reasoning over numerical time-series personal health data for applications in sleep and fitness. To systematically evaluate PH-LLM, we created and curated three novel benchmark datasets that test 1) production of personalized insights and recommendations from measured sleep patterns, physical activity, and physiological responses, 2) expert domain knowledge, and 3) prediction of self-reported sleep quality outcomes. For the insights and recommendations tasks we created 857 case studies in sleep and fitness. These case studies, designed in collaboration with domain experts, represent real-world scenarios and highlight the model’s capabilities in understanding and coaching. Through comprehensive human and automatic evaluation of domain-specific rubrics, we observed that both Gemini Ultra 1.0 and PH-LLM are not statistically different from expert performance in fitness and, while experts remain superior for sleep, fine-tuning PH-LLM provided significant improvements in using relevant domain knowledge and personalizing information for sleep insights. To further assess expert domain knowledge, we evaluated PH-LLM performance on multiple choice question examinations in sleep medicine and fitness. PH-LLM achieved 79% on sleep (N=629 questions) and 88% on fitness (N=99 questions), both of which exceed average scores from a sample of human experts as well as benchmarks for receiving continuing credit in those domains. To enable PH-LLM to predict self-reported assessments of sleep quality, we trained the model to predict self-reported sleep disruption and sleep impairment outcomes from textual and multimodal encoding representations of wearable sensor data. We demonstrate that multimodal encoding is both necessary and sufficient to match performance of a suite of discriminative models to predict these outcomes. Although further development and evaluation are necessary in the safety-critical personal health domain, these results demonstrate both the broad knowledge base and capabilities of Gemini models and the benefit of contextualizing physiological data for personal health applications as done with PH-LLM.
View details
Towards Conversational Diagnostic AI
Khaled Saab
Jan Freyberg
Ryutaro Tanno
Amy Wang
Brenna Li
Nenad Tomašev
Karan Singhal
Le Hou
Albert Webson
Kavita Kulkarni
Sara Mahdavi
Juro Gottweis
Joelle Barral
Kat Chou
Arxiv (2024) (to appear)
Preview abstract
At the heart of medicine lies the physician-patient dialogue, where skillful history-taking paves the way for accurate diagnosis, effective management, and enduring trust. Artificial Intelligence (AI) systems capable of diagnostic dialogue could increase accessibility, consistency, and quality of care. However, approximating clinicians' expertise is an outstanding grand challenge. Here, we introduce AMIE (Articulate Medical Intelligence Explorer), a Large Language Model (LLM) based AI system optimized for diagnostic dialogue.
AMIE uses a novel self-play based simulated environment with automated feedback mechanisms for scaling learning across diverse disease conditions, specialties, and contexts. We designed a framework for evaluating clinically-meaningful axes of performance including history-taking, diagnostic accuracy, management reasoning, communication skills, and empathy. We compared AMIE's performance to that of primary care physicians (PCPs) in a randomized, double-blind crossover study of text-based consultations with validated patient actors in the style of an Objective Structured Clinical Examination (OSCE). The study included 149 case scenarios from clinical providers in Canada, the UK, and India, 20 PCPs for comparison with AMIE, and evaluations by specialist physicians and patient actors. AMIE demonstrated greater diagnostic accuracy and superior performance on 28 of 32 axes according to specialist physicians and 24 of 26 axes according to patient actors. Our research has several limitations and should be interpreted with appropriate caution. Clinicians were limited to unfamiliar synchronous text-chat which permits large-scale LLM-patient interactions but is not representative of usual clinical practice. While further research is required before AMIE could be translated to real-world settings, the results represent a milestone towards conversational diagnostic AI.
View details
