Alon Diament
Research Subjects
Alon Diament has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Eran Segal
Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel
4 shared publications Adva Wolf
Pheno.AI, Tel-Aviv, Israel
2 shared publicationsAnastasia Godneva
Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel
2 shared publications- Hagai Rossman
Pheno.AI, Tel Aviv, Israel
2 shared publications - Sarah Kohn
Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel
2 shared publications - Yotam Reisner
Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel
2 shared publications
Latest Publications
- Open Access
Grounding Health AI: Architecture and Evaluation of a Domain-Expert Metabolic Health Agent
General-purpose language models generate fluent health reports that can fabricate derived clinical met-rics. In an illustrative comparison on identical two-week CGM and meal data, leading foundation models produced reports with invented MAGE values, inflated meal counts, and unreferenced complication-risk projections — failures invisible to non-expert readers and plausible enough to mislead clinicians. We describe the HPP Personal Health Agent (PHA), a metabolic health agent that grounds generation in four layers: the Human Phenotype Project (HPP), a deep-phenotyped cohort of 13,000+ participants sup-plying population references and trained predictive models; 21 domain-expert tools and trained-model wrappers that compute clinical metrics and risk predictions; declarative behavioural skills that constrain what the model may claim; and 21 automated evals across 8 categories developed via a test-driven cycle in which each eval encodes a failure mode discovered during iterative development. In a 210-report ma-trix (14 participants × 3 prompts × 5 system conditions), the gains are largest on the system’s primary use case — meal-grounded metabolic reports, the report it was designed for — where the full system raises a deterministic form/provenance score from 0.37 (the same foundation model with no tools or skills) to 0.91; this score measures structural completeness, numerical accuracy, tool grounding, and clinical-language compliance — a necessary condition for trustworthy health reporting, with clinical quality as a complementary axis examined qualitatively. A skills-vs-tools decomposition shows the two layers act on different axes: tools drive numerical accuracy (≈14% → 90% of reported metrics correct), while the declarative skills add most of the remaining gain in citations, completeness, and structure (tools alone recover only part of the gap, 0.49 from the same 0.37 baseline). The lift generalises beyond the primary use case — to a second metabolic prompt (0.72) and a cardiovascular extension (0.70), each from a 0.37–0.39 baseline. The architecture extends across clinical domains: adding a SCORE2 cardiovascular risk tool and a corresponding skill — with no changes to orchestration, eval harness, or existing tools — produced a cardiovascular risk report from the same system. Trustworthy domain-specialised health AI is a systems design problem: deep-phenotyped cohort data, domain-expert tools and models, and eval-driven development together form a replicable pattern.
Open AccessGrounding Health AI: Architecture and Evaluation of a Domain-Expert Metabolic Health Agent
General-purpose language models generate fluent health reports that can fabricate derived clinical met-rics. In an illustrative comparison on identical two-week CGM and meal data, leading foundation models produced reports with invented MAGE values, inflated meal counts, and unreferenced complication-risk projections — failures invisible to non-expert readers and plausible enough to mislead clinicians. We describe the HPP Personal Health Agent (PHA), a metabolic health agent that grounds generation in four layers: the Human Phenotype Project (HPP), a deep-phenotyped cohort of 13,000+ participants sup-plying population references and trained predictive models; 21 domain-expert tools and trained-model wrappers that compute clinical metrics and risk predictions; declarative behavioural skills that constrain what the model may claim; and 21 automated evals across 8 categories developed via a test-driven cycle in which each eval encodes a failure mode discovered during iterative development. In a 210-report ma-trix (14 participants × 3 prompts × 5 system conditions), the gains are largest on the system’s primary use case — meal-grounded metabolic reports, the report it was designed for — where the full system raises a deterministic form/provenance score from 0.37 (the same foundation model with no tools or skills) to 0.91; this score measures structural completeness, numerical accuracy, tool grounding, and clinical-language compliance — a necessary condition for trustworthy health reporting, with clinical quality as a complementary axis examined qualitatively. A skills-vs-tools decomposition shows the two layers act on different axes: tools drive numerical accuracy (≈14% → 90% of reported metrics correct), while the declarative skills add most of the remaining gain in citations, completeness, and structure (tools alone recover only part of the gap, 0.49 from the same 0.37 baseline). The lift generalises beyond the primary use case — to a second metabolic prompt (0.72) and a cardiovascular extension (0.70), each from a 0.37–0.39 baseline. The architecture extends across clinical domains: adding a SCORE2 cardiovascular risk tool and a corresponding skill — with no changes to orchestration, eval harness, or existing tools — produced a cardiovascular risk report from the same system. Trustworthy domain-specialised health AI is a systems design problem: deep-phenotyped cohort data, domain-expert tools and models, and eval-driven development together form a replicable pattern.
- Open Access
A foundation model of wearable pulse oximetry reveals physiological signatures of health and cardiometabolic risk
While Photoplethysmography (PPG) is established as a noninvasive optical tool for monitoring heart rate and oxygen saturation, its high-resolution pulsatile blood volume waveforms contain rich physiological data that extend far beyond conventional vital signs. We introduce PulseOx-FM, a foundation model, trained using self-supervised learning on 6,995,558 segments of pulse oximetry signals collected during 42,282 overnight sleep monitoring recordings of 10,704 adult participants in the Human Phenotype Project (HPP). Using chronological age as a global health benchmark, PulseOx-FM significantly outperformed existing open-source and proprietary feature extraction methods while demonstrating robust generalization in an external out-of-distribution cohort. PulseOx-FM representations predicted 71 phenotypic targets spanning cardiometabolic, and neuropsychiatric domains beyond age, sex and body mass index. Applied in the same way to 3,721 intensive-care patients, two-minute windows of routine bedside pulse oximetry from the first day of admission improved the prediction of survival beyond age, sex and the heart rate and oxygen saturation the same device reports. Nightly embeddings further tracked next-day glycemic, dietary and activity-based state within individuals, dissociating this signal from sleep architecture alone. This next-day glycemic signal was predominantly a direct physiological effect, not explained by next-day dietary intake. These findings suggest that PulseOx-FM provides a generalizable framework for encoding physiological patterns from sleep, offering a non-invasive tool for global health risk stratification and precision medicine.
Open AccessA foundation model of wearable pulse oximetry reveals physiological signatures of health and cardiometabolic risk
While Photoplethysmography (PPG) is established as a noninvasive optical tool for monitoring heart rate and oxygen saturation, its high-resolution pulsatile blood volume waveforms contain rich physiological data that extend far beyond conventional vital signs. We introduce PulseOx-FM, a foundation model, trained using self-supervised learning on 6,995,558 segments of pulse oximetry signals collected during 42,282 overnight sleep monitoring recordings of 10,704 adult participants in the Human Phenotype Project (HPP). Using chronological age as a global health benchmark, PulseOx-FM significantly outperformed existing open-source and proprietary feature extraction methods while demonstrating robust generalization in an external out-of-distribution cohort. PulseOx-FM representations predicted 71 phenotypic targets spanning cardiometabolic, and neuropsychiatric domains beyond age, sex and body mass index. Applied in the same way to 3,721 intensive-care patients, two-minute windows of routine bedside pulse oximetry from the first day of admission improved the prediction of survival beyond age, sex and the heart rate and oxygen saturation the same device reports. Nightly embeddings further tracked next-day glycemic, dietary and activity-based state within individuals, dissociating this signal from sleep architecture alone. This next-day glycemic signal was predominantly a direct physiological effect, not explained by next-day dietary intake. These findings suggest that PulseOx-FM provides a generalizable framework for encoding physiological patterns from sleep, offering a non-invasive tool for global health risk stratification and precision medicine.
- Open Access
Comprehensive Survey of Gut Microbiome Associations with Health Conditions in the Human Phenotype Project
The human gut microbiome is increasingly implicated with diverse health conditions, highlighting the importance of developing comprehensive resources to systematically map these associations. In this study, we leveraged the Human Phenotype Project (HPP) 10K cohort, a large, deeply phenotyped population study cohort with extensive metagenomic profiling, to explore associations between the gut microbiome and 37 health indications. These include conditions with established or emerging links to the microbiome, such as obesity, diabetes, hyperlipidemia, metabolic syndrome, inflammation, liver disease, cardiovascular and kidney conditions, immune and allergic diseases, gastrointestinal symptoms, mental health, and sleep-related traits. Using a curated set of approximately 200 refined phenotypic features and analyzing 1,184 microbial species, we performed robust statistical association analyses. We observed significant enrichment of associations in 14 health indications, with most associations reflecting increased microbial abundance in favorable health states, thereby suggesting potential microbial targets for intervention. This work introduces a publicly available, high-resolution resource to facilitate future research and support the development of microbiome-informed health strategies.
Open AccessComprehensive Survey of Gut Microbiome Associations with Health Conditions in the Human Phenotype Project
The human gut microbiome is increasingly implicated with diverse health conditions, highlighting the importance of developing comprehensive resources to systematically map these associations. In this study, we leveraged the Human Phenotype Project (HPP) 10K cohort, a large, deeply phenotyped population study cohort with extensive metagenomic profiling, to explore associations between the gut microbiome and 37 health indications. These include conditions with established or emerging links to the microbiome, such as obesity, diabetes, hyperlipidemia, metabolic syndrome, inflammation, liver disease, cardiovascular and kidney conditions, immune and allergic diseases, gastrointestinal symptoms, mental health, and sleep-related traits. Using a curated set of approximately 200 refined phenotypic features and analyzing 1,184 microbial species, we performed robust statistical association analyses. We observed significant enrichment of associations in 14 health indications, with most associations reflecting increased microbial abundance in favorable health states, thereby suggesting potential microbial targets for intervention. This work introduces a publicly available, high-resolution resource to facilitate future research and support the development of microbiome-informed health strategies.
- Top Cited Papers
- 27 January 2025
- Published by Springer Nature in Nature Medicine
- Vol. 31 (3) , 1026-1037
Phenome-wide associations of sleep characteristics in the Human Phenotype Project
Sleep tests commonly diagnose sleep disorders, but the diverse sleep-related biomarkers recorded by such tests can also provide broader health insights. In this study, we leveraged the uniquely comprehensive data from the Human Phenotype Project cohort, which includes 448 sleep characteristics collected from 16,812 nights of home sleep apnea test monitoring in 6,366 adults (3,043 male and 3,323 female participants), to study associations between sleep traits and body characteristics across 16 body systems. In this analysis, which identified thousands of significant associations, visceral adipose tissue (VAT) was the body characteristic that was most strongly correlated with the peripheral apnea–hypopnea index, as adjusted by sex, age and body mass index (BMI). Moreover, using sleep characteristics, we could predict over 15% of body characteristics, spanning 15 of the 16 body systems, in a held-out set of individuals. Notably, sleep characteristics contributed more to the prediction of certain insulin resistance, blood lipids (such as triglycerides) and cardiovascular measurements than to the characteristics of other body systems. This contribution was independent of VAT, as sleep characteristics outperformed age, BMI and VAT as predictors for these measurements in both male and female participants. Gut microbiome-related pathways and diet (especially for female participants) were notably predictive of clinical obstructive sleep apnea symptoms, particularly sleepiness, surpassing the prediction power of age, BMI and VAT on these symptoms. Together, lifestyle factors contributed to the prediction of over 50% of the sleep characteristics. This work lays the groundwork for exploring the associations of sleep traits with body characteristics and developing predictive models based on sleep monitoring.
- 27 January 2025
- Published by Springer Nature in Nature Medicine
- Vol. 31 (3) , 1026-1037
Top Cited PapersPhenome-wide associations of sleep characteristics in the Human Phenotype Project
Sleep tests commonly diagnose sleep disorders, but the diverse sleep-related biomarkers recorded by such tests can also provide broader health insights. In this study, we leveraged the uniquely comprehensive data from the Human Phenotype Project cohort, which includes 448 sleep characteristics collected from 16,812 nights of home sleep apnea test monitoring in 6,366 adults (3,043 male and 3,323 female participants), to study associations between sleep traits and body characteristics across 16 body systems. In this analysis, which identified thousands of significant associations, visceral adipose tissue (VAT) was the body characteristic that was most strongly correlated with the peripheral apnea–hypopnea index, as adjusted by sex, age and body mass index (BMI). Moreover, using sleep characteristics, we could predict over 15% of body characteristics, spanning 15 of the 16 body systems, in a held-out set of individuals. Notably, sleep characteristics contributed more to the prediction of certain insulin resistance, blood lipids (such as triglycerides) and cardiovascular measurements than to the characteristics of other body systems. This contribution was independent of VAT, as sleep characteristics outperformed age, BMI and VAT as predictors for these measurements in both male and female participants. Gut microbiome-related pathways and diet (especially for female participants) were notably predictive of clinical obstructive sleep apnea symptoms, particularly sleepiness, surpassing the prediction power of age, BMI and VAT on these symptoms. Together, lifestyle factors contributed to the prediction of over 50% of the sleep characteristics. This work lays the groundwork for exploring the associations of sleep traits with body characteristics and developing predictive models based on sleep monitoring.