
To provide better mental health care for people coping with depression, anxiety, fear, grief and isolation during the crisis.
Leverage emotion analytics and metrics to gather insights into patient behaviour.
Enhance risk profiling. Measure and compare post consultation results to the patient’s state before the consultation.
Based on close to a million psychometric trained data from more than 300,000 in-person interviews with both patients and non-patients our algorithm was trained to detect the psychological cues produced by the patient’s emotional state in real time.
When patients are evaluated over mobile platforms via telehealth, the ability of clinicians and physicians to discern the patient’s true feelings is extremely useful in measuring the severity of mood swings.
Emotion recognition is also useful in gauging the effectiveness of the healing process.
This is usually indicated by a reduction of negative emotions.
When the emotional state is outside the normal psychometric range, the physician is alerted that the patient very likely needs further examination.
The system extends exploratory and confirmatory analysis to assess the underlying dimensions of PEECE.
Emotion analysis and teleconsultation saved a significant amount of time when compared to in-person visits to the hospital.
The number of in-person hospital visits was also dramatically reduced.
The result was reduced risk of exposure by patients, physicians and clinicians to the COVID virus.
Emotion recognition analysis engaged in during teleconsultation also proved particularly useful since it permitted follow-up consultations with overseas patients after they returned to their home country.
This permitted physicians to continue monitoring patient progress.
Embedding emotion recognition technology into existing telehealth platforms has created a more comprehensive and global approach to virtual care.



