Avinatan Hassidim
Authored Publications
Sort By
Towards Conversational AI for Disease Management
Anil Palepu
Khaled Saab
David Stutz
Kavita Kulkarni
Sara Mahdavi
Joelle Barral
James Manyika
Ryutaro Tanno
Adam Rodman
arXiv (2025)
Preview abstract
While large language models (LLMs) have shown promise in diagnostic dialogue, their capabilities for effective management reasoning - including disease progression, therapeutic response, and safe medication prescription - remain under-explored. We advance the previously demonstrated diagnostic capabilities of the Articulate Medical Intelligence Explorer (AMIE) through a new LLM-based agentic system optimised for clinical management and dialogue, incorporating reasoning over the evolution of disease and multiple patient visit encounters, response to therapy, and professional competence in medication prescription. To ground its reasoning in authoritative clinical knowledge, AMIE leverages Gemini's long-context capabilities, combining in-context retrieval with structured reasoning to align its output with relevant and up-to-date clinical practice guidelines and drug formularies. In a randomized, blinded virtual Objective Structured Clinical Examination (OSCE) study, AMIE was compared to 21 primary care physicians (PCPs) across 100 multi-visit case scenarios designed to reflect UK NICE Guidance and BMJ Best Practice guidelines. AMIE was non-inferior to PCPs in management reasoning as assessed by specialist physicians and scored better in both preciseness of treatments and investigations, and in its alignment with and grounding of management plans in clinical guidelines. To benchmark medication reasoning, we developed RxQA, a multiple-choice question benchmark derived from two national drug formularies (US, UK) and validated by board-certified pharmacists. While AMIE and PCPs both benefited from the ability to access external drug information, AMIE outperformed PCPs on higher difficulty questions. While further research would be needed before real-world translation, AMIE's strong performance across evaluations marks a significant step towards conversational AI as a tool in disease management.
View details
Systematic Data Driven Detection of Unintentional Changes in Traffic Light Plans
Dan Karliner
Eliav Buchnik
Shai Ferster
Tom Kalvari
Omer Litov
Nitzan Tur
Danny Veikherman
Jack Haddad
2024
Preview abstract
Abstract—Traffic light plans determine the time allocated to each movement within an intersection. The plan has high influence on vehicle travel performance such as on the average delay time or the probability to stop in the intersection. Traffic engineers of a city control its traffic lights and can make changes in their plans to improve traffic performance. As it is not always easy to predict the impact of such changes, their potential impact can also be negative. We present an experimental study of real changes in traffic plans in 12 cities with a total of over 12000 intersections within a time period of over 40 days. We focus on changes of the cycle time of plans that highly impacted performance metrics such as delay. We compare the overall impact of such changes and dive into several of them through a careful analysis. To the best of our knowledge, our study is one of the largest in its scope among experimental studies of traffic conditions in recent years.
View details
Health AI Developer Foundations
Atilla Kiraly
Sebastien Baur
Kenneth Philbrick
Fereshteh Mahvar
Liron Yatziv
Tiffany Chen
Bram Sterling
Nick George
Fayaz Jamil
Jing Tang
Kai Bailey
Akshay Goel
Abbi Ward
Lin Yang
Shravya Shetty
Daniel Golden
Tim Thelin
Rory Pilgrim
Can "John" Kirmizi
arXiv (2024)
Preview abstract
Robust medical Machine Learning (ML) models have the potential to revolutionize healthcare by accelerating clinical research, improving workflows and outcomes, and producing novel insights or capabilities. Developing such ML models from scratch is cost prohibitive and requires substantial compute, data, and time (e.g., expert labeling). To address these challenges, we introduce Health AI Developer Foundations (HAI-DEF), a suite of pre-trained, domain-specific foundation models, tools, and recipes to accelerate building ML for health applications. The models cover various modalities and domains, including radiology (X-rays and computed tomography), histopathology, dermatological imaging, and audio. These models provide domain specific embeddings that facilitate AI development with less labeled data, shorter training times, and reduced computational costs compared to traditional approaches. In addition, we utilize a common interface and style across these models, and prioritize usability to enable developers to integrate HAI-DEF efficiently. We present model evaluations across various tasks and conclude with a discussion of their application and evaluation, covering the importance of ensuring efficacy, fairness, and equity. Finally, while HAI-DEF and specifically the foundation models lower the barrier to entry for ML in healthcare, we emphasize the importance of validation with problem- and population-specific data for each desired usage setting. This technical report will be updated over time as more modalities and features are added.
View details
Alignment of brain embeddings and artificial contextual embeddings in natural language points to common geometric patterns
Ariel Goldstein
Avigail Grinstein-Dabush
Haocheng Wang
Zhuoqiao Hong
Bobbi Aubrey
Samuel A. Nastase
Zaid Zada
Eric Ham
Harshvardhan Gazula
Eliav Buchnik
Werner Doyle
Sasha Devore
Patricia Dugan
Roi Reichart
Daniel Friedman
Orrin Devinsky
Adeen Flinker
Uri Hasson
Nature Communications (2024)
Preview abstract
Contextual embeddings, derived from deep language models (DLMs), provide
a continuous vectorial representation of language. This embedding space
differs fundamentally from the symbolic representations posited by traditional
psycholinguistics. We hypothesize that language areas in the human brain,
similar to DLMs, rely on a continuous embedding space to represent language.
To test this hypothesis, we densely record the neural activity patterns in the
inferior frontal gyrus (IFG) of three participants using dense intracranial arrays
while they listened to a 30-minute podcast. From these fine-grained spatiotemporal neural recordings, we derive a continuous vectorial representation
for each word (i.e., a brain embedding) in each patient. We demonstrate that
brain embeddings in the IFG and the DLM contextual embedding space have
common geometric patterns using stringent zero-shot mapping. The common
geometric patterns allow us to predict the brain embedding of a given left-out
word in IFG based solely on its geometrical relationship to other nonoverlapping words in the podcast. Furthermore, we show that contextual
embeddings better capture the geometry of IFG embeddings than static word
embeddings. The continuous brain embedding space exposes a vector-based
neural code for natural language processing in the human brain.
View details
Preview abstract
Computing efficient traffic signal plans is often based on the amount of traffic in an intersection, its distribution over the various intersection movements and hours as well as on performance metrics such as traffic delay. In their simple and typical form plans are fixed in the same hour over weekdays. This allows low operation costs without the necessity for traffic detection and monitoring tools. A critical factor on the potential efficiency of such plans is the similarity of traffic patterns over the days along each of the intersection movements. We refer to such similarity as the traffic stability of the intersection and define simple metrics to measure it based on traffic volume and traffic delay. In this paper, we propose an automatic probe data based method, for city-wide estimation of traffic stability. We discuss how such measures can be used for signal planning such as in selecting plan resolution or as an indication as which intersections can benefit from dynamic but expensive traffic detection tools. We also identify events of major changes in traffic characteristics of an intersection. We demonstrate the framework by using real traffic statistics to study the traffic stability in the city of Haifa along its 162 intersections. We study the impact of the time of day on the stability, detect major changes in traffic and find intersections with high and low stability.
View details
QUANTITATIVE APPROACH FOR COORDINATION, AT SCALE, OF SIGNALIZED 2 INTERSECTION PAIRS
Jack Haddad
Nitzan Tur
Danny Veikherman
Eliav Buchnik
Shai Ferster
Tom Kalvari
Dan Karliner
Omer Litov
2024
Preview abstract
The coordination of signalized intersections in urban cities improves both traffic operations and environmental aspects. Traffic signal coordination has a long history, where the impact of offset on delays and emissions at signalized intersections have been investigated through simulations and a limited number of experimental findings. Coordinating intersections is often justified by specific engineering requirements and judgment. However, as a consequence, many intersections in cities remain uncoordinated.
In this paper, we examine the potential benefits of coordinating signalized intersections at scale. Unlike previous studies, our analysis is based on aggregated anonymized probe data analysis and does not need to explicitly model traffic-oriented issues such as queue spillback and platoon dispersion. We follow a decentralized approach by considering intersection pairs, i.e. a system of two signalized intersections which can be spatially coupled, but have different cycle lengths. We introduce a new method for coordinating those signalized intersections. The method first evaluates the effect of different offsets on vehicle travel times and emissions. Then, it coordinates the two intersections by setting a common cycle and finding the optimal offset that minimizes emissions and travel times. We present the analysis for several case studies from real intersections at Jakarta, Rio de Janeiro, Kolkata, and Haifa. Finally, we evaluated our method by implementing it in a real experimental study at Jakarta. We collaborated with the city to implement the optimal offset that we had determined, and we compared the results before and after coordination.
View details
AI Increases Global Access to Reliable Flood Forecasts
Asher Metzger
Dana Weitzner
Frederik Kratzert
Guy Shalev
Martin Gauch
Sella Nevo
Shlomo Shenzis
Tadele Yednkachw Tekalign
Vusumuzi Dube
arXiv (2023)
Preview abstract
Floods are one of the most common natural disasters, with a disproportionate impact in developing countries that often lack dense streamflow gauge networks. Accurate and timely warnings are critical for mitigating flood risks, but hydrological simulation models typically must be calibrated to long data records in each watershed. Here we show that AI-based forecasting achieves reliability in predicting extreme riverine events in ungauged watersheds at up to a 5-day lead time that is similar to or better than the reliability of nowcasts (0-day lead time) from a current state of the art global modeling system (the Copernicus Emergency Management Service Global Flood Awareness System). Additionally, we achieve accuracies over 5-year return period events that are similar to or better than current accuracies over 1-year return period events. This means that AI can provide flood warnings earlier and over larger and more impactful events in ungauged basins. The model developed in this paper was incorporated into an operational early warning system that produces publicly available (free and open) forecasts in real time in over 80 countries. This work highlights a need for increasing the availability of hydrological data to continue to improve global access to reliable flood warnings.
View details
Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback
Paul Roit
Johan Ferret
Geoffrey Cideron
Matthieu Geist
Sertan Girgin
Léonard Hussenot
Nikola Momchev
Piotr Stanczyk
Nino Vieillard
Olivier Pietquin
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (2023), 6252–6272
Preview abstract
Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input. This phenomenon is emphasized in tasks like summarization, in which the generated summaries should be corroborated by their source article. In this work we leverage recent progress on textual entailment models to directly address this problem for abstractive summarization systems. We use reinforcement learning with reference-free, textual-entailment rewards to optimize for factual consistency and explore the ensuing trade-offs, as improved consistency may come at the cost of less informative or more extractive summaries. Our results, according to both automatic metrics and human evaluation, show that our method considerably improves the faithfulness, salience and conciseness of the generated summaries.
View details
A Neural Encoder for Earthquake Rate Forecasting
Oleg Zlydenko
Brendan Meade
Alexandra Sharon Molchanov
Sella Nevo
Yohai bar Sinai
Scientific Reports (2023)
Preview abstract
Forecasting the timing of earthquakes is a long-standing challenge. Moreover, it is still debated how to formulate this problem in a useful manner, or to compare the predictive power of different models.
Here, we develop a versatile neural encoder of earthquake catalogs, and apply it to the fundamental problem of earthquake rate prediction, in the spatio-temporal point process framework. The epidemic
type aftershock sequence model (ETAS) effectively learns a small number of parameters to constrain assumed functional forms for the space and time relationships of earthquake sequences (e.g., Omori-Utsu law). Here we introduce learned spatial and temporal embeddings for point process earthquake forecast models that capture complex correlation structures. We demonstrate the generality of this neural representation as compared with ETAS model using train-test data splits and how it enables the incorporation of additional geophysical information. In rate prediction tasks, the generalized model shows > 4% improvement in information gain per earthquake and the simultaneous learning of anisotropic spatial structures analogous to fault traces. The trained network can be also used to perform short-term prediction tasks, showing similar improvement while providing a 1,000-fold reduction in run-time.
View details
Caravan - A global community dataset for large-sample hydrology
Frederik Kratzert
Nans Addor
Tyler Erickson
Martin Gauch
Lukas Gudmundsson
Daniel Klotz
Sella Nevo
Guy Shalev
Scientific Data, 10 (2023), pp. 61
Preview abstract
High-quality datasets are essential to support hydrological science and modeling. Several CAMELS (Catchment Attributes and Meteorology for Large-sample Studies) datasets exist for specific countries or regions, however these datasets lack standardization, which makes global studies difficult. This paper introduces a dataset called Caravan (a series of CAMELS) that standardizes and aggregates seven existing large-sample hydrology datasets. Caravan includes meteorological forcing data, streamflow data, and static catchment attributes (e.g., geophysical, sociological, climatological) for 6830 catchments. Most importantly, Caravan is both a dataset and open-source software that allows members of the hydrology community to extend the dataset to new locations by extracting forcing data and catchment attributes in the cloud. Our vision is for Caravan to democratize the creation and use of globally-standardized large-sample hydrology datasets. Caravan is a truly global open-source community resource.
View details
