Sleep-EVAL Knowledge Base

First created | 01/12/1994

Last edited | 05/11/2012

Summary by Maurice M. Ohayon, MD, DSc, PhD

Reference to cite:

1) Ohayon MM. Sleep-EVAL, Knowledge Based System for the Diagnosis of Sleep and Mental Disorders. Registration #437699, Copyright Office, Canadian Intellectual Property Office. Ottawa: Industry Canada, 1994. (English, French, German, Italian, Portuguese, Spanish, Finnish, Swedish, Korean, Chinese versions).

2) Ohayon MM. Improving decision making processes with the fuzzy logic approach in the epidemiology of sleep disorders. J Psychosom Res 1999 Oct;47(4):297-311

The inference engine uses its knowledge base to pose questions, to infer hypotheses and to deduce diagnostic conclusions

Decisional Trees and Questionnaires

The knowledge base of Sleep-EVAL contains the knowledge representation of several thousand questions assessing:

Socio-demographic information

Age,
gender,
marital status,
residence,
employment,
income,
educational level,
etc...

Sleep/wake schedule

For work-days, week-end or merely days off, and vacation periods:

Bedtime,
Sleep latency,
Total time in bed during a 24-hour period ,
Morning awakening,
etc...

Evening activities just preceding bedtime and activities in bed

Watching television,
Reading,
Eating,
Working,
etc...

Duration of these activities when in bed.

Quality of nocturnal sleep or longest sleep period

Satisfaction with sleep duration,
Sleep latency (time to fall asleep),
Dreading bedtime,
Nightmares,
Dreams,
Restorative function of sleep,
Depth of sleep,
Ease of getting started in the morning,
Staying in bed upon awkening,
Ease of waking up at right time,
Frequency, causes and duration of awakenings during sleep

Symptoms or behaviors occurring in sleep

Snoring,
tooth grinding,
Sleep talking,
Breathing pauses,
Sleep starts,
Violent behaviors during sleep,
Restless legs,
Pain in legs,
Nocturnal incontinence,
etc...

Sleep habits and sleep hygiene

Insomnia symptoms, daytime sleepiness

The Chalder fatigue scale

Episodic psychic symptoms

Hypnagogic and hypnopompic hallucinations

Impacts of sleep problems on driving

Impacts of sleep problems on health

Daily intake of Substances

Tobacco,
Caffeine,
Alcohol,
Psychotropic drugs
Street drugs

Name, quantity, frequency, effects, behavioral modifications, cognitive effects.

Medications

Current usage of sleep enhancing medication,
Anxiety-reducing medication,
Antidepressant medication
Other Medications with their allegedly reported indication.

Qualifiers: time, frequency, schedule of intake, prescribers, effects on sleep.
Previous usage of similar drugs

Medical history (including medication indications)

Medical consultations in the last 12 month period (Consulted physician, number of consultations),
Hospitalizations (number, duration and reason)
Physical illnesses,
Weight,
Height,
Blood Pressure

Assessment of social life

Relationships with friends, spouse and children
Frequency of social meetings during the past year with friends, relatives, etc...
Overall social life,
Amount of time given to leisure during the past two months,
Presence of a close friend
Availability of psychological support if needed

Several pain scales and questionnaires

Psychosis scales and questionnaires

Depression scales (Hamilton, Montgomery-Asberg) and

questionnaires

Anxiety scales and questionnaires

Cognitive evaluations

Mac Nair Scale

Mini-Mental State Examination

Quality of Life

Autonomy Scale

Disability Scale

Fuzzy Set of Answers

Each question must be answered according to a fuzzy set of answers and rules. The system is allowed to explore and ask more questions until the subject is understanding the set of questions. When no agreement can be found, a flag is displayed for the manager of the study.

Four types of fuzzy sets are used in order to evaluate:

frequency,
quantity,
intensity,
quality,
and finally the level of adhesion to the answer by a progressive scale.

Positive and Differential diaGNOSIS

Positive and differential diagnosis of Mental Disorders

According to DSM-IV (American Psychiatric Association, 1994) classification

Positive and differential diagnosis of Sleep Disorders

According to the International Classification of Sleep Disorders (ICSD-97) (American Academy of Sleep Medicine, 1997)

Past and current Organic diseases

According to the International Classification of Disease (ICD-10, WHO).

Documentation (clinical, biological, radiological examinations) are collected.

Comorbid conditions are investigated but limited to the current knowledge.

Health care and health economics

A lot of information concerning the costs of the care are collected.

The search is based upon medical acts which could be evaluated at the end of the study.

References

Ohayon MM. Sleep-EVAL, Knowledge Based System for the Diagnosis of Sleep and Mental Disorders. Registration #437699, Copyright Office, Canadian Intellectual Property Office. Ottawa: Industry Canada, 1994. (English, French, German, Italian, Portuguese, Spanish, Finnish, Swedish, Korean, Chinese versions).
Ohayon M. Knowledge Based System Sleep-EVAL: Decisional Trees and Questionnaires. Quebec National Library, ISBN 2-921483-06-8, 1995.
Ohayon MM. Improving decision making processes with the fuzzy logic approach in the epidemiology of sleep disorders. J Psychosom Res 1999 Oct;47(4):297-311

More Information

Sleep-EVAL Aims

When the first epidemiological survey was launched in 1992, we were looking for an assessment tool that could be used by interviewers with little knowledge about sleep disorders.

The Sleep-EVAL Expert System

Sleep-EVAL, an artificial intelligent computer program, is an Expert System for evaluation and diagnosis of Sleep and Mental Disorders in general and clinical populations

Knowledge Base
The inference engine uses its knowledge base to pose questions, to infer hypotheses and to deduce diagnostic conclusion

Inference Engine
Sleep-EVAL is a non-monotonic, level-2 expert system endowed with the ability to make logical connections based on patient information (causal reasoning mode).

Fuzzy Logic
Inference models such as probabilistic and fuzzy systems can be used to integrate uncertainty in both symptomatic assessment and diagnostic attribution. It therefore becomes possible to extend boundaries and attribute a degree of certainty to a diagnosis.
A probabilistic model can be easily computed from an existent binary data set.
A fuzzy model can also be calculated from an existent data set, but the model is obviously much more precise when the data are expressed in categorical terms.

SLEEP-EVAL© RESEARCH