AI Analysis for Psychotherapy

Clinical Intelligence
for every session.

Psynex automatically analyzes your therapy sessions: ICD-10 diagnoses, symptom ratings, suicidality screening – all with verifiable source references from the conversation.

See Psynex in action

Demo: 35-minute conversation being transcribed and documented

Important: All AI analyses are support tools and do not replace your clinical judgment. Every assessment must be reviewed by you. The diagnostic and therapeutic responsibility lies with you.

Automatic analysis after every session

Once the session is finished, Psynex creates a comprehensive analysis – structured, quantified, and with evidence.

ICD-10 Diagnosis Recognition

Automatic recognition of F-diagnoses from session content with primary, secondary, and differential diagnoses.

Symptom Ratings (0-10)

Quantitative assessment of anxiety, depression, sleep, energy, and stress after each session.

Suicidality Screening

5-level assessment (0-4) for systematic early detection with documented quotes.

Identify Main Topics

Automatic identification of up to 5 most important topics of each session.

Track Interventions

Recognition of therapeutic interventions and techniques used.

Source References

Every assessment backed by timestamps and direct quotes from the conversation.

Live Preview

This is what your analysis looks like

Interactive symptom progressions across all sessions. Recognize patterns, progress, and setbacks at a glance.

Demo Patient

Symptom Progress

Total Sessions

16

With Analysis

15

Most Frequent Diagnosis

Recurrent depressive disorder (9x)

Anxiety/Worries

Depression

Sleep Problems

Lack of Energy

Demo data – Your real analyses look exactly the same
Symptom Ratings

Quantified Symptom Assessment

After each session, Psynex analyzes the conversation and creates ratings for five central symptom areas on a scale of 0-10. This allows you to recognize changes over time.

Anxiety

Generalized worries, panic attacks, avoidance behavior

Depression

Sadness, hopelessness, loss of interest

Sleep Problems

Falling/staying asleep issues, early waking, nightmares

Lack of Energy

Exhaustion, lack of drive, fatigue

Tension

Stress, inner restlessness, physical tension

Analysis from 21.01.2026Completed
Anxiety7/10
Depression5/10
Sleep Problems8/10
Lack of Energy6/10
Tension4/10
Source reference (23:45)

"The sleep problems are still massive, I often lie awake until 3 AM brooding..."

ICD-10 Recognition

Automatic Diagnosis Suggestions

Psynex recognizes indicators of ICD-10-F diagnoses from session content and suggests primary, secondary, and differential diagnoses. Each suggestion is linked to evidence from the conversation.

  • Specialized in F-diagnoses (Mental Disorders)
  • Distinction: Primary, Secondary, Differential
  • Confidence rating for each suggestion
Diagnosis Suggestions
F32.1
Moderate depressive episode
Primary
High
F41.1
Generalized anxiety disorder
Secondary
Medium
F43.1
Post-traumatic stress disorder
Differential
Check

Click on a diagnosis for the associated source references

Suicidality Screening

Systematic early detection in every session

Psynex analyzes each session for linguistic indicators of suicidality and creates a 5-level assessment. This feature supports your attention – the clinical judgment always lies with you.

0
No indicators
No signs of suicidal thoughts or behaviors
1
Passive thoughts
Wish not to live anymore, without active intent
2
Active thoughts
Suicidal thoughts without concrete plan
3
With plan
Active thoughts with concrete plan
4
Acute danger
Immediate intention to act
How does the screening work?

The AI analyzes linguistic indicators such as hopelessness, statements about dying, or concrete planning. Each assessment is backed by the exact quote and timestamp, so you can immediately find the passage in the conversation and evaluate it yourself.

Full Transparency

Every AI assessment is traceable with quotes and timestamps

Clinical Authority

You maintain full control – AI supports, doesn't decide

Time Savings

Structured analyses in seconds instead of manual evaluation

Frequently Asked Questions about AI Analysis

The symptom ratings are based on analyzing linguistic indicators in the conversation. They are meant as guidance, not as clinically validated measurement instruments. The strength lies in comparability over time: When you use the same AI methodology, you can recognize relative changes well. Each rating is backed by quotes, so you can understand the assessment and correct it if needed.

Psynex specializes in the F-diagnoses (Mental and Behavioral Disorders) of ICD-10, including: Affective disorders (F30-F39), Anxiety disorders (F40-F41), Stress disorders (F43), Somatoform disorders (F45), Personality disorders (F60-F69), and others. The AI recognizes indicators and suggests diagnoses – the final diagnosis naturally remains your medical/therapeutic decision.

The screening is an attention tool, not a replacement for your clinical judgment. It analyzes linguistic cues and alerts you to potential signs that you then evaluate yourself. It can miss or misinterpret indicators. Use it as a supplementary information source, not as the sole basis for clinical decisions. In cases of acute suicidality, your established clinical protocols always apply.

"High" means that several clear indicators were found in the conversation. "Medium" shows some hints, but less clear. "Check" for differential diagnoses means that the AI sees alternative explanations for the symptoms that you should consider. These assessments are based on the quantity and clarity of linguistic indicators – not on clinical validation.

The AI analyzes the entire transcript and identifies recurring themes, emotionally charged passages, and explicitly named problem areas. It extracts up to 5 main topics per session and links each topic to the relevant conversation passages. This gives you a quick overview and allows you to dive deeper if needed.

No. Your patient data and analyses are used exclusively for the evaluations you request. No training of AI models takes place with your data. This is contractually established in our Data Processing Agreement and in the BAA with OpenAI.

The five symptom categories (anxiety, depression, sleep problems, lack of energy, tension) are currently fixed, as they cover the most common areas in psychotherapy. We are working on adding individual categories in the future. For specific analyses, you can use the context chat and ask targeted questions.

Psynex saves the analysis results of each session and can aggregate them over time. You see trends, changes, and can recognize patterns. The progress display shows you at a glance how individual symptoms have developed – helpful for therapy planning, supervision, and reports to health insurers.

Experience AI-powered Analysis

Try Psynex free for 14 days. See how automatic analyses can support your clinical work.

Start free now
AI Analysis for Psychotherapy | ICD-10 Recognition & Symptom Tracking | Psynex