Voice-to-SOAP — the note is drafted before the patient leaves
Speak naturally during the consult; Medixar transcribes it and drafts a structured SOAP note (Subjective, Objective, Assessment, Plan) for you to review and save, instead of typing it up after clinic. Transcription uses OpenAI's Whisper, which recognises many Indian languages; clear English dictation gives the most reliable drafts today.
The structural assumption is that voice-to-SOAP is a draft, not a finished note. Every output flows through the doctor for sign-off; the workflow does not let you skip review. That single guard rail — "AI suggests, clinician decides" — is what makes the feature deployable in a real Indian practice. Read our honest evaluation.
ICD-10 suggestions — better coding without the lookup
ICD coding is the unglamorous but expensive half of clinical AI. Indian clinics under-code chronically because doctors do not enjoy looking up codes and the front desk does not know what to look up. Insurance claim rejections trace back to coding gaps a striking percentage of the time.
Medixar reads the assessment section of the encounter and proposes matching ICD-10 codes (and ICD-11 TM2 codes for AYUSH consultations). The doctor sees the suggestions, clicks the right ones, and moves on. What that is for:
- More specific codes — fewer "other unspecified" entries that invite manual review.
- Cleaner claims — coding gaps are a common reason insurers query a claim.
- Better analytics — the practice owner gets a clean breakdown of what they are treating.
Predictive analytics — surfaced where the decision is made
Predictions only matter if they reach the clinician at the moment they need them. Medixar surfaces four predictions inline, as decision support rather than a verdict:
- No-show probability — visible on every appointment in the day list. Front desk can over-book the high-risk slots and call the medium-risk patients to confirm.
- Readmission risk — appears on the discharge summary, so high-risk patients can be given a closer follow-up.
- Length-of-stay estimate — generated at admission. Bed planning becomes data-driven instead of gut-feel.
- 7-day bed-demand forecast — visible to the bed-management team daily. Surge planning is no longer reactive.
They are decision support, not a verdict: they show where to look, and the clinician or the front desk decides what to do about it.
Drug-interaction safety — the one that fails closed
The clinical copilot category gets over-promised. We're picky about what we ship under the AI banner because the wrong design causes harm. Drug-interaction checks are the example.
Every prescription runs a drug-interaction check before it can be signed. If the interaction database is unreachable, the system fails closed — the prescription cannot be created. Better to refuse a prescription than to silently miss a major interaction. The rejection emits a structured event so ops sees the signal; the doctor gets a clear message and can re-try once the database is back.
For AYUSH practices, the safety surface widens: each new Ayurveda, Unani, Siddha or Sowa-Rigpa prescription runs its interaction checks in parallel — within the system, against the patient's constitution, and for Ayurveda against allopathic drugs — and a check that cannot complete is reported as a warning rather than silently passing. See the AYUSH page for detail.
Radiology report summaries
For X-ray, CT, MRI and ultrasound, Medixar reads the radiologist's report and extracts the findings and their severity into a structured summary the treating doctor can scan in seconds. It works from the report text — it does not interpret the images themselves.
The radiologist's signed report remains the record; the summary is a reading aid.
Agentic clinical copilot
The newest addition. The copilot watches the encounter as it builds and surfaces three kinds of nudge:
- Critical-value alerts — lab results that breach thresholds get a clear unacknowledged-result queue.
- Care-plan drafts — for chronic disease management, the copilot drafts a plan from the patient's history for the doctor to edit, instead of starting from a blank page.
- Documentation gaps — flags assessments that should have a diagnosis code attached, or a follow-up that should have a date.
What we deliberately do not ship: open-ended diagnostic suggestion. "Suggest the most likely diagnoses for this picture" is the area where current models are most likely to mislead, and where junior clinicians are most likely to over-trust the output. We will revisit when the safety profile matures.
Where does the data go?
Dictation audio is transcribed by OpenAI's Whisper API, and clinical text is processed by Anthropic's Claude API. Under both providers' commercial API terms, the data is not used to train their models. Both are listed as sub-processors in our privacy policy. Full security architecture is here.
How to evaluate AI for your practice
A practical test plan we recommend before adopting any AI scribe:
- Pick one busy clinic day. Run the AI scribe on every consult.
- Time the doctor's time-to-save-note before and after.
- Audit the first ten notes manually. Note where the AI got things wrong.
- Check the coding-rejection rate for a month before and a month after.
- Make sure the workflow forces a human-in-the-loop sign-off.
We are happy to run this test with you on staging. Book a demo and tell us your specialty.