Is the system hallucination-free?

Aakhyān does not use LLM-generated text in patient-facing output. Discharge instructions are rendered through deterministic, clinician-reviewed templates that have been approved by oncologists and clinicians. The AI extracts structured data from discharge summaries — the template converts that data into natural-language instructions. No generative text reaches the patient.

Which languages does Aakhyān currently support?

Aakhyān currently generates discharge instructions in Bengali, Hindi, English, and Assamese, all delivered as WhatsApp voice messages. The system is designed to expand to additional Indian languages as the platform scales beyond the pilot.

What happens when a drug isn’t in the lexicon?

If a medication is not yet in Aakhyān’s verified drug lexicon, the system flags it for clinician review. The drug’s brand name is preserved as-is, and every message is reviewed by the treating clinician before delivery. The clinician can edit, correct, or reject any instruction before it reaches the patient. No message is ever sent without clinician approval.

What’s the cost per patient?

During the pilot at Silchar Cancer Centre, Aakhyān is provided at no cost to the institution or the patient. At scale, the system costs INR 100–150 per patient (approximately USD 1.20–1.80) — comparable to the cost of one blood test. This covers the full communication sequence: discharge comprehension, medication adherence nudges, follow-up reminders, and on-demand information access. The project is principal-investigator initiated and self-funded.

How is patient data protected under DPDPA?

Discharge summary photographs are captured in-app and not saved to the device camera roll. Patient identifiers — names, addresses, contact details, and hospital IDs — are algorithmically redacted before any external API call. Only de-identified clinical content is processed using secure, access-controlled AI services. No patient names, contact details, or identifying information are ever exposed to external systems. Voice messages are delivered directly to the patient’s registered WhatsApp number. All processing complies with the Digital Personal Data Protection Act, 2023.

Can another hospital join the pilot?

The current pilot is at Silchar Cancer Centre. Onboarding a new centre is straightforward — no integration with existing hospital systems is required for basic deployment. If you represent a hospital or cancer centre, please reach out through our contact form.

Does Aakhyān support only cancer patients?

Currently, yes. Aakhyān is designed and validated for oncology discharge summaries, where the complexity of multi-drug regimens — chemotherapy, immunotherapy, targeted therapy, and hormonal therapy — and the consequences of misunderstanding are highest. We have long-term plans to extend the platform to other specialities where discharge communication gaps affect patient outcomes.

Does Aakhyān only send messages at discharge?

No. Aakhyān continues through the post-discharge recovery window — 30 days in the current pilot protocol. Day 0 is six structured voice messages explaining the discharge summary. Days 1–3 bring risk-stratified medication adherence nudges. An on-demand keyword reply menu is available any time — the patient texts a number to hear their medicines, hospital contact, follow-up details, or diet advice. Two days before follow-up, verified reminders arrive with department, tests, and fasting instructions. A day-before availability check (currently in pilot phase) verifies doctor and equipment availability to prevent wasted journeys.

Does the patient need to install an app?

No. Everything works through WhatsApp, which the vast majority of Indian smartphone users already have. Voice messages, medication nudges, follow-up reminders, and the on-demand information menu all arrive as standard WhatsApp messages. The reply commands (1 for medicines, 2 for hospital, etc.) use simple text replies — no app, no login, no learning curve.

The post-discharge patient journey — from hospital discharge to confident follow-up return

The Platform

Aakhyan is not a discharge voice message. It is a modular patient communication platform that extends patient care through the post-discharge window — from comprehension, through medication adherence, to follow-up continuity. The current pilot protocol evaluates this over 30 days; the platform is designed to scale with the recovery window a given care pathway requires.

Five Modules

Day 0

Discharge Comprehension

Upon clinician approval, the patient receives structured WhatsApp voice messages covering their medications, safety warnings, diet, wound care, and follow-up details — each one clear, each one in their own language, each one replayable.

Day 1–3

Medication Adherence

Patients at higher clinical risk receive earlier, more frequent nudges. Others receive a gentler check-in. The system calibrates to the patient — not the other way around.

On-Demand

Information Access

A patient never needs an app or a login. A single text message — one number — and the answer arrives in her language. Medications, follow-up dates, diet advice: everything from the discharge, accessible any time.

2 Days Before

Follow-Up Continuity

Before each follow-up, the patient receives a verified reminder: which department, which floor, what tests to bring, whether to fast. Because she traveled six hours last time and was turned away for not bringing the right report. That will not happen again.

1 Day Before

Daily Availability & Patient Notification System (DAPNS)

PILOT

The evening before her appointment, she receives a check — is her doctor available? Is the equipment working? No more six-hour journeys to find out at the counter.

What Existing Systems Do Not Offer

Capability	Typical discharge communication	Aakhyan
Discharge comprehension (Day 0)	Printed paper + verbal	Voice messages in patient’s language
Medication adherence (Day 1–3)	—	Risk-stratified nudges
On-demand information access	—	Voice reply menu
Follow-up reminders with logistics	Generic SMS	Verified reminders: dept, tests, fasting
Pre-visit availability check	—	Evening notification
Voice-first delivery in Indian languages	—	Bengali, Hindi, English, Assamese
Zero-hallucination safety architecture	—	Deterministic templates

INR 100–150 per patient (approx. USD 1.20–1.80) — the cost of one basic blood test, covering the full post-discharge communication sequence (30 days in the current pilot protocol).

References

Discharge communication deficits affect 78% of patients, with only 47% recall of verbal-only instructions (Engel et al., 2009; Hoek et al., 2020).
Communication interventions at discharge reduce readmission rates (9.1% vs 13.5%, RR 0.69), improve medication adherence (86.1% vs 79.0%, RR 1.24), and increase patient satisfaction (60.9% vs 49.5%, RR 1.41) (Becker et al., JAMA Network Open, 2021).
When GPT-4 was used to generate patient-friendly discharge summaries, 18% of outputs contained safety concerns including hallucinations and omissions (Zaretsky et al., JAMA Network Open, 2024). A deterministic, template-based approach eliminates this class of error by design.
At Cachar Cancer Hospital in Silchar, 23% of newly diagnosed head-and-neck cancer patients abandoned treatment before starting, with an additional 41% non-compliance after commencing — driven by travel distance and financial barriers (Talagadadeevi et al., Indian Journal of Palliative Care, 2024).
80.4% of cancer outpatients in India experience catastrophic health expenditure, with the poorest patients 7.4 times more likely to be affected (Prinja et al., Frontiers in Public Health, 2023).
Northeast India has the highest cancer burden in the country. Assam has been called the “cancer capital” of India, with fewer than 10% of primary health centres providing screening services (Barmon et al., BMC Health Services Research, 2025).

For the clinical trial protocol, see The Research. For regulatory alignment, see NABH Standards. To discuss deployment at your institution, contact us.