ElyCia Lifesciences Pvt. Ltd. · Eureka! 2026 Finals · EU2698236

TBot

A handheld, non-sputum breath test for tuberculosis triage.

Dr. Ruwise E. A.
Founder, Executive Director & Principal Investigator

TBot handheld reader, concept render
STAGETRL 3 → 4
SENSINGVOC array + analyte-specific EC
PARTNERSCSIR-NIIST · C-DAC · AMTZ
IP3 patents + PCT · TM filed
REGULATORYCDSCO / MDR 2017 · ICMR-reviewed

Problem

Tuberculosis is India's biggest infectious killer, and screening keeps missing it

~¼of the world's TB is in India
~28%of the world's TB deaths
~26 lakhcases notified in 2024, a record
~1 lakhcases still "missing" at first contact
wk 1wk 97–9 wkstypical diagnostic delay

How it's screened today

Symptoms
Sputum microscopy or molecular tests
Chest X-ray
Each dependent on
the patient producing sputuma laboratoryan X-ray unit

Why that falls short

✕

Many patients cannot produce sputum: children, people living with HIV, early disease

✕

Primary health centres: often no X-ray and no lab

Screening stalls where the burden is highest

ElyCia Lifesciences

Source: WHO Global Tuberculosis Report 2025

Solution · how the device works

A pathogen-specific breath test that runs where the patient already is

DESIGN PROTOTYPE · DRAG TO ROTATE

TBot reads a patient's breath in minutes: no sputum, no X-ray, no lab. It pairs a multi-sensor breath array with a TB-marker-specific electrochemical cartridge, capturing both the broad breath signature and the specific markers the TB bacterium itself releases.

Inside TBot

  • 1Disposable mouthpiece
  • 2Bacterial / viral filter
  • 3UV-C self-sterilisation
  • 4Flow + CO₂ capnography
  • 5Heated conditioning
  • 6Multi-sensor array
  • 7TB-marker EC cartridge
  • 8Edge-AI processor
  • 9Touchscreen result
  • 10Battery · USB-C

What makes TBot different

A molecular test inside a low-cost, reusable reader, and a category nobody holds yet

Differentiated feature

Generic e-nose pattern only TBot + TB biomarkers(EC cartridge) molecular specificity

A disposable, TB-marker-specific electrochemical cartridge gives molecular specificity a generic e-nose cannot, inside a reusable, low-cost handheld reader with UV-C self-sterilisation.

Modular by design

one reusable reader TB · now Pneumonia COPD more…

Reusable reader + swappable disease-specific cartridge. The same platform extends to other respiratory diseases after TB.

Why now

Breath-VOC science · 20 yrs Low-cost printed sensors On-device AI 0 breath-based TB tests cleared worldwide

Two decades of breath-VOC science, low-cost printed-sensor manufacturing and on-device AI now make a cheap, specific, field-deployable test possible, and no breath-based TB test has been cleared anywhere in the world yet. The category is open.

ElyCia Lifesciences

How it works · one breath, four simple steps

About two minutes of normal breathing, run by a frontline health worker

01

Guided exhale

Disposable mouthpiece; a filter blocks germs. 1–2 min, no training.

→
02

Alveolar gating

Capnography isolates the deep-lung fraction where TB markers concentrate.

Phase-III CO₂ plateau = the only air sent to the sensors

→
03

Dual-channel read

Multi-sensor array plus the TB-marker EC cartridge read the sample.

→
04

Decide & refer

Edge-AI returns TB / not-TB; UV-C sterilises the path between patients.

No sputumNo X-rayNo lab at the point of careRefer → NAAT confirmsLive run on the next slide ▶
ElyCia Lifesciences

Virtual test run · simulation

Run a TBot test, start to finish

SIMULATION · ILLUSTRATIVE DATA
0:00
~2 minnormal breathing
3.0 Ldeep-lung air
< 4 minto result
  1. Fit
  2. Breathe
  3. Read
  4. Fuse
  5. Result
  6. Clean
Validity checks
Flow path sensors
Capnography gateDeep-lung air 0.0 / 3.0 L
Channel A · sensor array MOX · PID · ECp₁ —
Channel B · TB biomarker cartridgep₂ —
Decision-level fusionscore —
ResultPress Start to run the test

System architecture

Capnography-synchronised breath capture, two complementary sensing channels

Patient interface · infection control

Single-use mouthpiece · bacterial/viral filter · one-way valve

→

Sample conditioning

Heated above dew point; humidity held at a set-point that stabilises both sensor types

→

Channel A · multi-sensor array

embedded breath analyzer
VOC patternMOX e-nose (BME688): qualitative signature
Quantitative gasAlphasense electrochemical sensors

In-array breath-phase & reference: flow · CO₂ capnography · temperature · humidity · pressure

Channel B · TB-marker EC sensor

molecular-specific
Pre-concentrationenriches the trace marker
→
Recognition-film 4-electrode arraysingle-use, functionalised
→
Quantitativemarker readout

Detects the four mycobacterial marker markers (lead: the lead marker): molecular specificity a generic e-nose cannot give. Developed as a standalone module (CSIR-NIIST); not built into the MSA embedded system in the current phase.

→

Embedded system

Capnography-synchronised alveolar windowing · environmental compensation · ML pattern classifier

Decision-level fusion
TB triage result

refer if positive

Between-patient decontamination: disposable consumables + UV-C decontaminable flow path.

Broad VOC pattern + TB-specific markers, fused on-device. Capnography windows the deep-lung fraction; conditioning holds humidity where MOX and electrochemical sensors are stable.

ElyCia Lifesciences

The science & what's new

Validated chemistry, and a first-of-its-kind breath interface

Proven chemistry

TB releases four specific marker markers into breath. A proprietary recognition film captures them. Validated in solution at CSIR-NIIST for the lead marker, the lead marker.

CV and DPV of the lead marker on the recognition film, 20–110 µM
~0.1 µM

limit of detection

0.1–110 µM

linear range

Characterised by XRD / SEM and cyclic + differential-pulse voltammetry.

The breakthrough: electrolyte film interface

PRIOR APPROACH Breath (gas)Trap /condenseInto liquidEC sensor TBOT Breath (gas)Electrolyte-film-coated sensor: marker dissolves in,concentrates and is read in one step

Electrochemistry needs a liquid; breath is a gas, so every prior group had to trap breath into liquid first. Our electrolyte film provides the liquid and concentrates the signal in a single step. No trapping, no condensation.

Non-sputum

reaches children, HIV & extrapulmonary cases

Pathogen-specific

names a TB molecule, not just a pattern

Infrastructure-free

no lab, X-ray or connectivity

Protected & de-risked

3 patents + PCT; FTO cleared, 9 jurisdictions

ElyCia Lifesciences

EC cartridge · 3D exploded view · drag to rotate

The single-use cartridge, layer by layer

CONCEPT MODEL · NOT TO SCALE
6TB biomarker moleculespartition into the gel · one colour per marker
5Electrolyte filmelectrolyte + gas→liquid capture in one step
4Selectivity layeroptional · generic marker selectivity
3Recognition layerproprietary · binds the markers
2Screen-printed array4 working (one per marker) + control · carbon counter · Ag reference
1Flexible substrate (PET)+ edge connector

Single-use cartridge, reusable reader. DPV/SWV resolves each marker at its own potential against an internal redox reference; the control electrode is subtracted.

ElyCia Lifesciences

AI / ML · two channels, one decision

Two ML channels, one fused decision

The MSA learns the breath-pattern shift · the EC module scores the TB marker · a fixed layer fuses both. GC-MS is the reference truth both models train against.

MSA
pattern
channel
Signal → features

alveolar gating · R/R₀ baseline · per-litre volume-norm · humidity control · PCA drift-correction → BME688 step-response (slope · AUC · step-ratios · EMA) · PID peak/AUC · capnogram etCO₂ / phase-III

ModelPLS-DA / elastic-net logisticstability-selected · nested CVp₁ pattern score
⟩
Decision-level combiner (118)

Calibrated fusion of p₁ + p₂ into one score, with a confidence estimate and an explicit indeterminate (repeat) zone rather than a forced call.

Task C: deterministic validity gating guards every sample before fusion.

TB / not-TB + confidence → refer if positive
EC
marker
channel
Signal → features

baseline + NIP control-electrode subtraction · internal-redox (ferrocene-class) referencing → per-marker DPV/SWV peak current · peak potential · integrated charge · redox kinetics

ModelRegularised SVM / random forestlocked firmware (116)p₂ marker score
GC-MS reference truth: quantifies breath VOCs and supplies training labels for both models. Task A1 (MSA ↔ GC-MS regression, the breath-transduction exit gate) · Task A3 (EC per-lot calibration).
ElyCia Lifesciences

Unit economics

How TBot reaches a sub-₹150 test, a fraction of a ₹930 Xpert

Most diagnostics are costly because sensing uses antibodies or DNA. We detect small breath molecules, so the recognition chemistry is bulk, printable and cheap. The cost sits in plastic and packaging, not biology.

Cartridge bill of materials · ₹ per test at scale (>10 M units / yr)

Total COGS at scale≈ ₹37–69 / test

Price per test

The reader

Reusable handheld: BOM target <₹50,000, sale ~₹1,00,000. Priced near cost to drive placements; profit compounds on the cartridge annuity.

ElyCia Lifesciences

Indicative modelled costs at scale, not quoted prices. Biodegradable mouthpiece and reduced-foil packaging are committed design goals.

Market · one platform, many indications

TB is the beachhead. The same reader unlocks the markets our patents already claim

Near-term focus: TB

US$2.3–3.2BTAM · global TB diagnostics US$120MSAM · India triage $18–35MSOM · 5-yr
Horizon 1 · now

Tuberculosis triage

beachhead

Horizon 2 · next
  • Pneumonia & respiratory infections
  • COPD & asthma: phenotype stratification

Global respiratory dx & monitoring: multi-billion-USD, chronic + recurring

Horizon 3 · later
  • Lung-cancer risk triage
  • Diabetes & metabolic (acetone-class)
  • Hepatic / renal · GI markers

Large global screening markets: early detection & monitoring

The expansion engine

Each new disease = a new disease-specific cartridge + tuned classifier on the same reader. Both filed specifications claim extension to other diseases by substituting the marker panel. No new hardware.

>US$10B

combined breath-diagnostics opportunity globally, addressable on one reader with disease-specific cartridges

ElyCia Lifesciences

Adjacent-market figures are indicative global estimates; TBot enters each indication only after TB validation. Extensions are per the filed provisional specifications.

Business model & revenue

Razor-and-blade: a low-cost reader, recurring cartridge revenue

Reader (device)~₹1,00,000one-time

Reusable handheld: sensor platform, capnography, display, UV-C, software

Test cartridge · consumable₹135 / testrecurring

Single-use TB-marker cartridge: the recurring margin engine

Analytics & integrationAnnual licenceper year

NTEP / Nikshay-ready dashboards and fleet management

Consumable margin

>70%

COGSmargin

at scale (₹135 vs ~₹40 COGS)

Revenue driver
×

Installed base

× tests per device / yr

Channel CAC

Low

institutional / government sales

Commercial revenue ramp · ₹ crore / yr (India base case, from procurement entry)

≈ ₹293 Cr (US$35M) revenue by the 5th commercial year (base case)

ElyCia Lifesciences

Development roadmap · click a track or phase

Three tracks from month 1, then gated phases to market

A 60-person breath study answers the biggest question by month 6, without waiting for a prototype, and sets the targets for the EC strip and the reader. Fusion and the pivotal trial stay gated on results.

Clean division
of work
CSIR-NIISTTrack B · EC TB biomarker strip
Engineering partnerTrack C · MSA reader, firmware
ElyCiaTrack A · breath study; integration, clinical, regulatory
AMTZprototyping, testing, DFM

Go-to-market

Into the NTEP public procurement chain, the way Truenat and Xpert went

Decides & buys

Central TB Division, MoHFW (with ICMR)

Sets the national testing algorithm and procures at scale, as it did for Truenat & Xpert.

→

Deploys

State TB Cells (STO) · District TB Centres (DTO)

Roll out community active case-finding once a technology is adopted nationally.

→

Operates

ASHA & frontline health workers

Run TBot at the point of care, designed for minimal training.

Strategy

BeachheadPull-throughExpansion NTEP active case-findingPrivate diagnostic chains (cartridges)Other respiratory diseases ElyCia Lifesciences

Competitive landscape

An open white space: PHC-deployable and pathogen-specific

SegmentPlayersWhy it isn't TBot
Molecular confirmatory
India, NTEP
Xpert MTB/RIF, Truenat, AG ChitraSputum + lab; confirmatory. TBot feeds them, never replaces
Imaging / acoustic triageqXR, Genki (CAD-CXR); Swaasa (cough AI)Needs an X-ray unit, or reads only a cough pattern; not pathogen-specific
International breath platformsOwlstone (FAIMS); Breathomix (SpiroNose)Built for oncology / asthma-COPD, not TB; centralised or MOX-only
Breath-VOC TB & patent-stageTSI-3000 (IMS); VIT, G. Rani, CVR filingsNon-specific total-volatilome, or applications; none a cleared product
The open white space

No player holds TBot's full combination: a TB-marker-specific EC channel + MOX array + capnography-gated alveolar sampling + disposable cartridge. No breath-based TB test is cleared anywhere; FTO cleared across 9 jurisdictions.

OPEN WHITE SPACE MolecularXpert, Truenat AI-CXRqXR Cough-AISwaasa E-noseOwlstone, Breathomix TBot PHC-deployable & affordable → Pathogen / molecular specificity →
ElyCia Lifesciences

Competitive benchmark · the test TBot must match

AI chest X-ray sets the bar: TBot aims to match it where X-ray cannot go

30%40%50%60%70%80%90%WHO minimum 70%optimal 80%AI X-ray · 7 countries5 products65–74%AI X-ray · Indiacountry cut-offs64–68%AI X-ray · previous TBold scars≤ 58%AI X-ray · people with HIVcut-off for 90% sens.≈ 46%TBot · simulatedbefore breath data51–72%Specificity at 90% sensitivity →

AI X-ray: multi-country head-to-head of 5 CAD products (medRxiv 2024). TBot: Monte Carlo of 2,400 trials from literature-anchored priors, not clinical data. Median 54–61%, 80% range 37–87%, driven mainly by how many TB patients emit the markers, which Track A measures.

Where TBot can win
  • Previous TB: X-ray cannot tell old scars from active disease; the markers come from living bacteria (hypothesis)
  • Reach: no X-ray unit, radiation, power or network. At PHC level the real comparator is symptom screening (~71% sens / ~64% spec)
  • Together: TBot alongside X-ray raises specificity, so programmes can use both
Where X-ray stays stronger
  • People with HIV and low-bacteria disease: breath markers likely weak too
  • TB without symptoms: X-ray sees abnormal films in people who feel well
How we will prove it

Phase 2 study (n ≈ 270): every participant also gets an AI X-ray read, so the first accuracy result is a direct comparison. The previous-TB subgroup is pre-registered. To clearly beat X-ray, the marker cartridge alone must reach AUC ≈ 0.88–0.90.

ElyCia Lifesciences

IP & regulatory pathway

Protected, and mapped to a clear route to market

Intellectual property

1Sep 2025 2Feb 2026 3Jul 2026 PCT · Sep 2026
1App 202541084151 · 4 Sep 2025Multi-sensor Array System for TB Detection using Breath Analysis & ML
2App 202641013600 · 7 Feb 2026Bio-Safe Hybrid Breath-Analysis Platform for respiratory diseases
3App 202641092414 · 30 Jul 2026Analyte-Specific Electrochemical Sensing Module
PCT/IB2026/059348 · 3 Sep 2026International phase secured

Trademark
"TBot", App 7219027, Class 10, filed

Freedom to operate cleared, 9 jurisdictions (TIPS@SCTIMST-TIMed)

IndiaEUUKUSAChinaAustraliaIndonesiaPhilippinesSouth Africa

Regulatory · CDSCO / MDR 2017

BUILD TOClass CSEEKClass B

A new IVD with no CDSCO predicate device, reviewed by ICMR MedTech Mitra (51st TAC). Building to the conservative Class C standard, seeking Class B where risk justifies.

MD-12

Test Licence: manufacture the device for evaluation

MD-24

Clinical Performance Evaluation: permission for human-subject testing

MD-28

Manufacture permission for a no-predicate device

MD-9

Manufacturing Licence: Central Licensing Authority; ISO 13485

ElyCia Lifesciences

Team

The people accountable for delivery

Dr. Ruwise E. A.

Dr. Ruwise E. A.

Founder, Exec. Director & PI

Orthopaedic surgeon & device innovator. Owns architecture, IP & coordination; sole inventor on all patents.

Dr. Aswathy Menon

Dr. Aswathy Menon

Co-founder · Regulatory & Quality

Pharmacologist. Leads regulatory affairs, QMS, risk documentation and the CDSCO interface.

Dr. Jishnu V. J.

Dr. Jishnu V. J.

Co-founder · Analytical Science

MD Forensic Medicine, DM Toxicology. Analytical toxicology & breath-biomarker interpretation.

Institutional delivery partners · contracted, non-overlapping scope

CSIR–NIIST

Sensing chemistry (Dr Rakhi R.B)

C-DAC Trivandrum

MSA engineering (MeitY)

AMTZ Vizag

Prototyping, EMI/safety, DFM

The ask · 24 months · three tracks, then the exploratory study

₹2.1 Cr seed to reach TBot's first hard clinical evidence

Use of funds · 24 months (₹3.3 Cr)

Raising ₹2.1 crore seed equity; the remaining ₹1.2 Cr of the ₹3.3 Cr plan is targeted from non-dilutive grants (ICMR, BIRAC, PRIP). The first ₹31 L answers the biggest question by month 6.

A · M6 · TB biomarkers measured in the breath of 60 patients and controls by GC-MS, before any prototype is built

B · M15 · A TB biomarker EC strip validated for gas-phase reading at the breath levels Track A measured

C → Ph 2 · M24 · An interface-frozen MSA reader and a locked triage model from the ~270-participant exploratory study

Funding relay

~₹1.2 Cr ₹2.1 CrTHIS ASK ~₹3 Cr ~₹8–12 Cr GRANTSSEED · NOWPRE-SERIES ASERIES A

Alongside the seed · co-fund M1–24

This ask · 3 tracks + exploratory study

Equity + DoP/ICMR · fusion MVP + pilot

Equity + clinical · pivotal, MD-9, launch

Milestones bought: breath-marker readout (M6) · interface freeze (M12) · EC gas-phase (M15) · MD-12/24 (M15) · study locked + first sens/spec (M24)

Thank you

TBot

A sub-₹150, sputum-free TB triage test in every primary health centre.

Dr. Ruwise E. A. · Elycia Lifesciences Pvt. Ltd.
ruwiseea@elycialifesciences.com · +91 70127 49565

Appendix A1 · AI / ML · validation & calibration

Built for regulatory review, calibrated on the device

Validation · built for regulatory review

subjects → 5 folds sites red = held out for testing

Subject-level nested CV · leave-one-site-out; metric = specificity @ 90% sensitivity (WHO TPP-3)

confound-only TBot model

Beats a confound-only benchmark (age · sex · BMI · fever · HIV · diabetes · site); algorithm locked for v1 (IEC 62304)

270study 3–6 ~1,000–1,200

n ≈ 270 → feature discovery + model locking (3–6 features) · pivotal validation ~1,000–1,200

Calibration · traceable, onboard

ZERO · clean airSPAN · ref gas

MSA: onboard zero/span cartridge (carbon scrub + permeation) · reference-gas drift span

EC: internal-redox standard + per-lot carrier (EEPROM/NFC) · strip authentication

0.1 – 110 µM LOD??

EC working range 0.1–110 µM (LOD ≈ 0.1 µM); out-of-range flagged indeterminate

ElyCia Lifesciences

Appendix A2 · How much breath is enough

About 2–4 litres of deep-lung air: one to two minutes of normal breathing

Three things run in parallel; the slowest sets the test time

Deep-lung air captureonly the CO₂ plateau is kept · ~250 mL per adult breath
Multi-sensor arraychamber flush + heater cycles · ~30–60 s, <1 L
TB-marker cartridgeenough marker must build up in the gel to read clearly above its 0.1 µM detection limit

1–2 min

adult · ~15 normal breaths

2–3 min

small child · smaller breaths

Breath needed vs TB-marker level in breath

1 ppb0.1 ppb10 ppt1 ppt feasible: ≤ 4 L (~1–2 min) 37 mL 0.37 L 3.7 L 37 L too long

Log-scale design calculation: 1 µL gel, ~20% capture, read at 3× the detection limit. Not yet measured.

Phase 1 gate: GC-MS measures the real marker level in TB patients' deep-lung air; the cartridge must read within ≤ 4 L at that level.
ElyCia Lifesciences

Appendix A3 · EC sensor · layer architecture

Inside the single-use cartridge: how a breath molecule becomes a signal

Cross-section · working-electrode stack (bottom → top)

M1M2M3M4 TB marker markers (four)partition into the gel Electrolyte filmelectrolyte + gas→liquid capture in one step Selectivity layeroptional · generic marker selectivity Recognition layerproprietary · binds the markers Screen-printed electrodes4 working + control · counter · Ag ref Flexible substrate (PET)+ edge connector

The electrolyte film supplies the electrolyte and captures gas-phase markers in one step: no trapping, no condensation. recognition film binds the TB biomarkers (validated in solution for the lead marker); DPV/SWV resolves each marker against an internal redox reference.

Disposable strip · semi-selective array · top view

W1W2W3W4 C edgeconnector W1–W4 · recognition film, one per markerC · control counterAg reference (redox std)

Detection · voltammetry (DPV / SWV)

M1M2M3M4 Current (µA)Potential (V) → PER-ESTERpeak pattern→ classifier → fusion

Single-use cartridge, reusable reader. The strip carries a per-lot calibration and authentication.

ElyCia Lifesciences

Appendix A4 · Q&A · evidence

"Breath TB tests have looked promising for years. Why will yours work?"

What the evidence says

E-nose vs healthy controls
meta-analysis, 14 studies, 1,715 subjects (2019)
sens 92% · spec 93%
E-nose in symptomatic patients
blinded, Paraguay, n=107 (2023)
accuracy 50%
Electrochemical the lead marker breath test
Uganda, n=57, preprint (2024)
sens 71% · spec 100%

Lesson: pattern-only devices lose specificity when controls are sick. Targeted chemistry is promising but small and unreplicated.

How TBot is built for the hard case

Sick controls by design. ~165 of ~270 participants are symptomatic and TB-negative, not healthy volunteers.

Two independent channels. A broad breath pattern plus a TB biomarker mycobacterial panel, so they fail in different ways.

Deep-lung air only, with a Repeat zone instead of a forced call.

Pre-registered go / no-go against GC-MS and Xpert / culture; results reported per subgroup.

ElyCia Lifesciences

Saktiawati et al., EBioMedicine 2019 · Coronel Teixeira et al., PLOS ONE 2023 · Jeppson et al., medRxiv 2024 (not peer-reviewed). WHO triage TPP 2014 (≥90% / ≥70%); WHO screening TPPs updated Aug 2025.

Appendix A5 · Q&A · confounders

"What about smoking, food, cosmetics and other lung disease?"

ConfounderWhat it can doHow TBot handles it
Lip products, rubs, food, mouthwashMostly in mouth and dead-space airCapnography-gated deep-lung sampling · alveolar-gradient check · pre-test rinse protocol
Smoking, biomass and room airVolatiles reach the lungs or the inletInhaled-air reference · smoking recorded for every test · results reported for smokers and non-smokers
Single-source markersOne marker raised without infectionTB biomarker array reads a pattern, not one number · control electrode removes non-specific signal
Pneumonia, COPD, diabetes, alcoholShift the broad breath patternThe marker channel stays flat → channels disagree → Repeat or No refer
Antibiotics, low bacterial load (HIV, children)Can hide a true TB signalRepeat zone · lower refer threshold for high-risk groups · no paediatric claim at launch
Phase 1 bench gate: single-source challenges (smoke, rubs, flavourings, supplements) and non-TB mycobacteria cultures, before any patient is enrolled.
ElyCia Lifesciences

Appendix A6 · Q&A · competition and adoption

"AI X-ray, cough apps and tongue swabs exist. Why would NTEP buy TBot?"

Non-sputum tools today

ToolStatusWhat it needs
AI chest X-rayWHO-recommended; qXR screened >7 M for TB in FY24–25X-ray unit, power, radiation safety
Cough-sound AI (Swaasa)CDSCO Class B SaMD; 90% / 85% in validationPhone; pattern only
Tongue swab NAATWHO-recommended sample (Mar 2026)Molecular instrument, cartridge
Breath-aerosol PCR (Avelo)Late-stage; 71% / 92%Molecular lab step
TBotPre-clinical (TRL 3)Nothing but the reader: no radiation, sample or lab
~13 Cr

people screened in the 2024–25 100-day TB Mukt Bharat campaign; ~500 AI handheld X-ray units deployed, 1,000 more planned

Where TBot fits

The pre-filter before X-ray and NAAT in camps, homes and PHCs without imaging. It complements X-ray rather than replacing it.

Adoption path

ICMR multicentric validation→Central TB Division policy→GeM / state procurement

The route Truenat took (validated at NIRT, AIIMS, NITRD, JALMA).

ElyCia Lifesciences

WHO TB guidelines Module 3 (2025, Mar 2026 update) · Qure.ai FY24–25 impact report · Yellapu et al., Sci Rep 2023 · TAG Pipeline Report 2025 · MoHFW / PIB 2025.

Appendix A7 · Q&A · risk and de-risking

"What could go wrong, and what does this seed actually de-risk?"

RiskMitigationGate / when
Markers not readable from breathElectrolyte film capture · sorbent micro-trap · liquid-condensate fallback (all in our filing)EC gas-phase gate · M15
Accuracy collapses in sick patientsSymptomatic controls · two channels · pre-registered analysisStudy locked · M24
Humidity, heat, sensor driftHeated path · internal redox reference · zero / span cartridgeInterface freeze · M12
Biosafety of a breath deviceSingle-use filter mouthpiece · UV-C inner path · IEC 62471 / 60601 testingPre-compliance · M12
RegulatoryNew IVD, likely CDSCO Class C · ICMR MedTech Mitra reviewed · test licence firstMD-12 / MD-24 · M15
Team gap: hardwareEmbedded hardware hire first · contracted partners with clear IP termsHire · M3

The exit exists

Molbio (Truenat) became India's first medtech unicorn in 2022; Qure.ai raised a US$65 M Series D in 2024. Both scaled after validation and programme adoption.

Capital-efficient

Seed is matched by non-dilutive money: BIRAC, ICMR, PRIP and India Health Fund–type grants.

ElyCia Lifesciences

Appendix A8 · Development plan · overview

Three tracks from month 1, then four gated phases

Stage · led byQuestion it answersOutputDirect costGo / no-go
M0 · now
TRL 3 · ElyCia + CSIR-NIIST
Does the chemistry work?Lead marker on recognition film in solution (LOD ≈ 0.1 µM, 0.1–110 µM); IP filed₹4.5 L spent—
A · M1–6
Clinical validation · ElyCia
Are the markers in TB breath, and at what level?n = 60 at a Delhi TB centre, GC-MS lab: emitter share, breath levels, AUC against symptomatic controls; no prototype needed₹0.31 Cr≥ 80% emit ≥ 2 markers and AUC ≥ 0.80 → go; 50–80% → re-scope; < 50% → stop the cartridge
B · M1–15
EC TB biomarker strip · CSIR-NIIST
Can the strip read them from humid breath?Per-marker vapour detection at Track A levels; cross-reaction grid; confounder challenges₹0.32 Cr≥ 3 markers read at breath levels; tobacco does not raise the anchor markers
C · M1–12
MSA reader · engineering partner
Does the reader deliver deep-lung air reliably?Gated reader with trap, heated path and UV-C; breath volume set from Track A₹0.60 CrInterface frozen; study units built
Ph 2 · M13–24
Exploratory study · ElyCia
Does it work in sick patients?n ≈ 270 at 2 NTEP-linked sites, both channels + GC-MS reference · expected AUC 0.80–0.91, specificity 50–72% at 90% sensitivity (±7 points)₹0.85 CrMarker AUC ≥ 0.85 and fused specificity ≥ 60% → proceed; < 50% → change course
Ph 3 · M25–36
Fused beta · ElyCia + partners
Does the whole device hold up?Locked model and confounder logic in an integrated pilot₹1.6 Cr≥ 70% specificity at 90% sensitivity; ≤ 10% first-attempt Repeat → design freeze
Ph 4–5 · M37–60
Pivotal + licence · ElyCia + AMTZ
Does it meet WHO targets at scale?CDSCO evaluation at 4–6 sites, n ≈ 1,000–1,200; results usually drop 5–10 points, so Phase 2 should show ≥ 75–80% specificity₹5.8 CrEndpoints met → MD-9 licence, NTEP entry

Months 1–24 · ₹3.3 Cr

₹2.08 Cr direct (Tracks A–C and Phase 2) + ₹1.23 Cr team, regulatory, IP and contingency. Seed ₹2.1 Cr + grants ₹1.2 Cr. Running the tracks together saves about six months; B and C carry a month-6 checkpoint, so about ₹1.0 Cr is committed before the first gate.

Value inflection

Month 6: first real breath data on the four markers. Month 15: the strip reads them from breath. Month 24: first accuracy in symptomatic patients, the step before a Series A.

Stop rule, fixed in advance

If Track A shows few emitters, the cartridge pauses and B and C are re-scoped: condensate mode, a narrower intended use, or the reader as a platform for other markers. The filed IP and the gated breath interface keep their value either way.

ElyCia Lifesciences

Appendix A9 · Track A · initial clinical validation (M1–6)

TB biomarkers in real breath, measured before any prototype exists

GroupnDefinition
Confirmed TB25Xpert Ultra or culture positive; sampled before or within 24 h of starting treatment
Symptomatic, TB-negative25Presumptive TB; Xpert and culture negative
Healthy controls10No symptoms, non-smokers

At least 6 smokers in each of the first two groups, analysed separately. Observational: ethics approval and CTRI registration, no device licence.

Sampling

Deep-lung breath only, verified by CO₂ (≥ 90% of end-tidal); 1 L on a Tenax TA tube; paired room-air tube

Analysis

Thermal-desorption GC-MS with authentic standards; detection limits set before the first sample; analyst blinded

Timeline

M1 method + ethics · M2–4 recruitment · M5–6 analysis and decision

Decision (M6): ≥ 80% of TB patients with ≥ 2 markers and AUC ≥ 0.80 → full build · 50–80% or AUC 0.70–0.80 → re-scope · below that → stop the cartridge

What the month-6 readout predicts

Share of TB patients emitting ≥ 2 markers → expected fused specificity at 90% sensitivity (80% range below)

Below 60%
~44%
32–56%
60–70%
~55%
42–67%
70–80%
~66%
51–80%
80% or more
~83%
64–96%

Monte Carlo, 2,400 trials from literature-anchored priors: a simulation, not data.

Cost · ₹31 L · full study

TD-GC-MS analysis · 238 runs₹11.90 L
Tubes, sampling kit, capnometer, CO monitor₹5.95 L
Research coordinator · 6 months₹3.00 L
Marker standards, second-source check₹1.40 L
Untargeted workup (exploratory)₹1.00 L
Ethics, reimbursement, culture₹1.50 L
Statistics, report, manuscript₹1.50 L
Shipping and sundries₹0.50 L
Contingency (15%)₹4.01 L
Total₹30.76 L

About ₹21 L if the GC-MS lab joins as co-investigator and charges consumables only.

What it hands to the other tracks

  • Track B: breath concentrations set the strip's detection limit and which markers to prioritise
  • Track C: breath volume and sampling time, before the interface is frozen
  • Phase 2: effect sizes for the sample size
ElyCia Lifesciences

Appendix A13 · Phase 2 exploratory study (M13–24)

A study built to fail honestly if the signal is not there

Population

  • n ≈ 270: ~70 confirmed TB, ~165 symptomatic TB-negative, margin for indeterminates; confirmed from Track A effect sizes
  • 2+ sites linked to NTEP
  • Deliberately enrols post-TB lung disease, COPD, pneumonia and NTM
  • Adults at launch; children in a separate later protocol

Reference standards

  • Xpert / culture for TB status
  • GC-MS on a parallel Tenax breath tube for chemistry
  • Urine cotinine strip for tobacco
  • Result screen hidden during the study

Recorded for every participant

  • Tobacco form and time since last use · exhaled CO
  • Antibiotics in last 14 days · prior TB
  • Diabetes · HIV · alcohol · food, coffee, niacin
  • Cosmetics and topical rubs

Analysis, fixed in advance

  • Pre-registered (CTRI) go / no-go thresholds
  • Subject-level nested CV · leave-one-site-out
  • Must beat a confound-only model
  • Specificity at 90% sensitivity; ±7-point precision

Reported separately

  • Non-users · smokers · smokeless users
  • HIV · diabetes · other lung disease
  • Marker score alone · array alone · fused

Approvals

  • CDSCO MD-12 test licence for study devices
  • MD-24 clinical performance evaluation
  • Ethics at each site · CTRI registration
ElyCia Lifesciences

Appendix A14 · Phases 3–5 · fused beta to market

From fused beta to a licensed, procurable device

Standards file built from M1

ISO 13485QMS, design controls, DHF / DMR
ISO 14971Risk file; confounder controls as risk controls
IEC 60601-1 / -1-2Electrical safety, EMC
IEC 62304Software lifecycle; algorithm locked for v1
IEC 62366Usability; pre-test protocol, Repeat messages
IEC 62471UV-C photobiological safety
ISO 10993Biocompatibility of mouthpiece and strip
ISO 14155Clinical investigation practice

M3 · fused beta (M25–36)

Cartridge docks without changing the frozen airflow · locked combiner · integrated pilot · target ≥ 70% specificity at 90% sensitivity · design freeze

M4 · pivotal + licence (M37–60)

CDSCO evaluation, n ≈ 1,000–1,200 at 4–6 sites · likely Class C IVD · MD-28 (no-predicate) → MD-9 manufacturing licence · ISO 13485 line at AMTZ

Adoption

ICMR multicentric validation→Central TB Division policy→GeM / state procurement→WHO policy / PQ
ElyCia Lifesciences

Appendix A15 · Programme value

What TBot is worth per 1,000 people screened

ApproachReferred to NAATCostTB missed (of 150)
NAAT for everyone1,000~₹10.0 L0
TBot at 90% / 51%~550~₹6.9 L (−31%)15
TBot at 90% / 72%~370~₹5.1 L (−49%)15

Assumes 15% TB among symptomatic people screened, NAAT ≈ ₹1,000 and TBot ₹135 per test.

In camps and PHCs the real comparison is usually no test at all. There, TBot finds ~135 of every 150 TB cases per 1,000 people, without X-ray, sputum or lab.

For NTEP

Up to half the NAAT spend saved per 1,000 screened, and cartridges directed to the people most likely to have TB.

For the business

Every screened person is a ₹135 cartridge: the recurring revenue engine behind the ~₹293 Cr year-5 base case.

ElyCia Lifesciences

Appendix A16 · Risk register · click a tab

Complete risk register and mitigation

H high M medium L low · L = likelihood, I = impact

ElyCia Lifesciences