Knowledge-based
Explicit clinical definitions and domain knowledge guide each assessment.
EVALRI · Independent research · California
Clinical science.
Causal inference.
Longitudinal evidence.
EVAL Research Institute develops structured clinical AI and research tools around Ad-Infer, an evolving inferential system that now integrates an LLM directed by its inference engine.
The Ad-Infer approach
Clinical reasoning that evolves with the evidence
Causal & adaptive
Direct and indirect causal relationships shape the hypotheses and the next questions.
Longitudinal
New symptoms, treatments, tests and events can revise earlier inferences over time.
Current inferential architecture
One integrated system: Ad-Infer
Ad-Infer is an evolving causal inferential system developed by Maurice M. Ohayon. EVAL-KBS brings together domain knowledge, clinical reasoning, fuzzy evaluation and learning. An integrated large language model (LLM) extends language and semantic functions under the direction of the inference engine.
Ad-InferOne integrated inferential system
Clinical representation
Domain knowledge
Concepts, questions, diagnostic criteria, exclusions, clinical context and temporal relationships.
Sleep-EVAL provides the sleep-disorders knowledge base.
→
Inferential controlEVAL-KBS
EVAL-KBS
Inference & learning
Type-2 causal reasoning, fuzzy evaluation, neural and deep-learning processes, and Bayesian belief updating.
Directs the interview, evaluates evidence and retains diagnostic authority.
↔
Internal language functions
Integrated LLM
Standardized questioning, reformulation, clarification, translation and explanations of why a question is asked.
Interprets new information in relation to direct and indirect clinical causality.
Continuous return to inference. Questions asked or skipped, understood or misunderstood, accepted or refused, and answers that support or challenge a hypothesis return to Ad-Infer. EVAL-KBS re-evaluates their clinical meaning, adjusts the belief state and directs the next step.
An evolving research platform
Nearly four decades of continuous development
Developed by Maurice M. Ohayon beginning in 1987, Ad-Infer has expanded through neural and fuzzy computation, population studies, longitudinal assessment and web-based research. Its current architecture integrates LLM functions within the same clinical reasoning process.
- 1987
Development begins
Maurice M. Ohayon begins developing Ad-Infer for clinical interviewing and inferential reasoning.
- 1992
Computational foundations
Doctoral work formalizes the architecture, including Hopfield neural computation and Zadeh fuzzy logic.
- 1990s onward
Population & longitudinal research
Domain knowledge bases support structured assessment in population samples, clinical groups and repeated interviews.
- Since 2016
Web-based assessment
Research applications extend the structured interview to web-based assessments.
- Current architecture
Integrated language-model capabilities
The evolving Ad-Infer system incorporates an LLM as an internal functional component directed by causal inference, fuzzy evaluation and the current belief state.
Products & services
Research tools built around the clinical question
Clinical trial support
Protocol-specific prescreening, structured eligibility assessment and recruitment support.
ExploreSpecific screening tools
Explicit research questions, clinically relevant features and validation for the intended use.
ExplorePatient subgroup characterization
Meaningful patient profiles across symptoms, comorbidity, treatment and functional burden.
ExploreEarly identification tools
Study patterns of change across sleep, cognition, behavior, mood and daily function.
ExploreLongitudinal assessment
Follow persistence, remission, recurrence and changing clinical trajectories.
ExploreCustom clinical AI tools
Configure domain knowledge, adaptive interviews and structured outputs within Ad-Infer.
ExploreEVAL Research Institute
Clinical science, population evidence & functional outcomes
EVAL Research Institute is an independent California-based research organization. Its work connects sleep medicine, psychiatry, neurology and related medical domains with epidemiology, computational science and longitudinal phenotyping.
Health & pharma
Clinical phenotyping, patient profiles and longitudinal evidence for research programs.
ExploreHealth care providers
Structured assessment and follow-up information for health care and research teams.
ExplorePublic health & epidemiology
Representative population samples, comparable definitions and repeated assessment.
ExploreScientific record
Selected research from 2026
Oxidative Stress, Antioxidant Defense, and Sleep-Wake Regulation in Psychiatric Disorders
Antioxidants · 2026
ExploreNeglected burden of obstructive sleep apnoea: workplace productivity loss in the USA and UK
Thorax · 2026
ExplorePrevalence, Incidence, and Persistence of Food Allergies Among U.S. Adults
Clinical & Experimental Allergy · 2026
Explore