Doxper: Digitising disease surveillance from doctors’ handwritten Rx

During disease outbreaks, rapid, anonymized and aggregated insights based on real world data is crucial. Doxper digitises doctors’ case sheets without behaviour change, with an AI assisted, digital pen and paper solution.

Randeep Singh, Co-Founder & Chief Scientific Officer

Updating electronic health records (EHRs) is often the responsibility of doctors and care providers, but very few like the burden and inconvenience of typing. This is especially true in countries where the doctor-patient ratio is poor and the average consultation time is a handful of minutes. Patients in 18 countries representing about 50% of the global population spend 5 minutes or less with their primary care physician as per a 2017 British Medical Journal survey.

EHR systems globally are also the source of real world and longitudinal patient data. However, providers in 124 countries* are still using pen and paper and are looking for a cost effective digitisation solution that does not force behaviour change.

During disease outbreaks, rapid, anonymized and aggregated insights based on real world data is pivotal to direct the outbreak control efforts in the right direction. However, health systems that rely on paper based workflows that are not digitised at the point of care are unable to respond quickly enough without accurate, representative signals of changes happening on the ground.

*Internal estimate if a country has doctor-patient ratio of < 1:1000, or if no data is available, as a proxy for digitisation gaps. Source W.H.O, 2015-2018.

For the digitisation of paper based workflows, our customers and end users include physicians, nurses, receptionists, health workers and clinical researchers.

For the analytics generated from the digitised records, our customers include Hospital administrators, Pharma companies, NGOs, Government and Clinical research organisations.

Today, we believe the most optimal input technology in the outpatient setting is pen and paper, especially in countries where there is high patient load and limited consultation time. While we continue on this path and expand our market leadership in India, we are also developing a suite of multi-modal input technologies to cover requirements across the user behaviour spectrum - from hybrid models (part of the data is captured on paper, and the rest, such as Rx advice on tablet/phone/app) to developing best in class AI, NLP engines for handwriting recognition. We are also innovating around unique paper surfaces that can be reused so that the consumable cost is significantly reduced, without compromising the user experience.

On the analytics front, we have started working with pharma companies on use cases such as prescription audits, brand launch tracking and patient journeys. This experience is helping us build capabilities for population health level surveillance and insights.

In India, we have the largest longitudinal patient dataset in the outpatient setting which continues to grow rapidly. We have plans to publish aggregated and anonymised insights that could be useful for general public consumption and for academic research. Eventually, the datasets behind these published insights could be made searchable and also be connected via public APIs for entrepreneurs and new applications. This is useful once we have national level scale, and representation in most of the country’s districts. We are inspired by the Singapore government’s Open Data initiative: www.data.gov.sg  

We are also keen on partnering with stakeholders in India and other countries to build an alliance (and eventually a culture/mindset) for Open Data to start publishing aggregated, anonymised datasets available with us and other stakeholders. In line with India’s recently launched National Digital Health Mission which is completely voluntary to participate, we believe taking an alliance approach would credibly demonstrate the benefits of Open Data, and will also accelerate the digitisation of the country’s providers across the socioeconomic spectrum.

There have been various approaches to track the start and spread of epidemics using data. With technological and IT advances scientists have added information channels such as social media, tweets, Google query searchers,  etc. specifically for flu trends tracking. The results have been of mixed quality due to self reporting by individuals and hard to model social media data. 

In India, apart from governmental hospitals, healthcare services also depend on private health providers in most States, especially in urban centers. In the event of an emerging outbreak, the private sector units may detect warning signs earlier than the public sector. It becomes crucial to engage private hospitals in making all out efforts for their participation in the surveillance of outbreak prone diseases.

Since Doxper can be deployed as a plug and play solution seamlessly across both public/private care settings, a true integrated disease surveillance programme can be sustainably scaled up for lasting impact. The programme can be managed by States with the guidance of the Central government. Incentives can also be aligned with the National Digital Health Mission. Demonstrating proof of concept/impact is also relatively straightforward and can be piloted in several districts of a State.

In Phase 1 (in 1st year), we propose inputs to the integrated disease surveillance programme from general physicians using our technology or independent data collation and analysis to the government as a service. The surveillance activities that are well developed in one area may act as driving forces for strengthening other surveillance activities, offering possible synergies and common resources. 

Data requested may differ from disease to disease, requiring specialized templates to collect the data. In our uploaded deck, we show sample prescriptions with raw captured data. 
 
In Phase 2 (over 3 years), we would expand the scope of specialties to include other qualifications such as BAMS, BUMS (Unani), MD/DNB and Paed/ DCH so that user acceptance is further validated. We can also expand coverage to districts in very different socioeconomic and cultural settings to test user acceptance.
 
The final link in the surveillance chain is the application of these data to prevention and control. Over 95% of doctors' provisional diagnosis turn out to be correct after lab and radiology tests are conducted. Hence primary care needs to be strengthened and digitised to catch potential disease outbreaks early; this alone could save millions of lives from infectious disease and death.

1. Doctor Digitisation Compliance %:  Proportion of doctors actively digitising their case sheets and prescriptions using Doxper in the first 90 days and in the first 180 days.

2. Template Digitisation Compliance: For all the patients that doctors consult, what % of patients do they use Doxper for.

3. Data Transfer Frequency: What % of data points are coming in real-time vs those getting delayed due to offline use (data is automatically transferred when the Internet is available again or stable). For offline use, what is the average frequency of data transfer, in terms of days.

4. Handwritten Strokes to Text Accuracy: For the target data points and fields, what is our algorithm’s accuracy compared to human transcription? After establishing a baseline for 90 days, what is the % improvement in accuracy for the same set of doctors in the next 180 days?

Digitisation in healthcare is currently not mandatory in India. Even the National Digital Health Mission (NDHM) is voluntary. However, with our success so far in the private sector (mainly tier 1/2 towns) and we are about to also graduate from the NDHM Sandbox, we are confident that gradually more providers will come on board. In terms of our go to market strategy, we are focused on demonstrating clear ROI and business related analytics to our customers before pitching clinical analytics, and positioning Doxper as an investment rather than a cost centre. For example, in hospitals, we have cracked the outpatient revenue leakage problem, and enabled our customers to recover the cost of Doxper within the first year itself.

For public health use cases, to convince potentially risk averse or cost-sensitive decision makers, we are pursuing grants from philanthropic and social impact institutions to help cover at least the first year of operations and capital expenditure, to demonstrate proof of impact. We strongly believe the technology to solve local problems will come from domestic entrepreneurs who understand the ecosystem and context. Anything that works in India can be scaled to similar markets and LMIC countries still on pen and paper.

1. Swasth - Swasth is a Not-for-Profit initiative and alliance of India’s top digital health companies

2. NDHM - India’s National Digital Health Mission

3. Global Linkages Programme, USAID  - Selected as one of handful innovators from India to pilot in Nigeria

4. MIT Solve - Chronic Disease winner, 2017

Disease surveillance is tough. According to Klaucke et al in their 1988 publication “Guidelines for evaluating surveillance systems”, quality is measured in terms of seven dimensions: sensitivity, representativeness, timeliness, simplicity, flexibility, acceptability, and positive-negative predictive values.

In modern times, we should be blessed with more tools and data at our disposal to address the 7 factors above. However, the pervasive lack of digitisation in primary care excludes the most critical and accurate real world data: Insights from doctor’s prescriptions and case histories, and the speed at which these insights are relayed back.

Doxper has been successful at digitising outpatient records in the private sector. We are confident of our abilities to significantly contribute to disease surveillance. However, grant funding and support from larger organisations is needed to convince the State/Central governments to partner with a small, albeit fast growing startup for a pilot, and eventually a pan-India rollout. In short, pooling risk capital with the right expertise to energise the space.

We were referred to the Trinity Challenge, as a proud alumnus and past winner at MIT Solve. We believe Trinity Challenge can also give us a platform to make an impact beyond India in LMIC markets with similar challenges.

1. Erstwhile Google Flu trends team: Experience/lessons in disease surveillance

 2. Google Research team in India: AI/ML expertise, to further enhance our handwriting recognition engine
 
3. Bill & Melinda Gates Foundation: Experience funding/executing with State and Central governments in India; Memorandum of Cooperation (MoC) with India's Ministry of Health and Family Welfare under which they provide technical, management, and program design support for key health initiatives; Strong data driven track record.
 
4. GSK: Disease surveillance is a form of real world data (RWD), and the quality of RWD is the highest when it comes directly from the doctors' prescriptions and case histories. GSK is one of the first pharma companies to fully embrace RWD, and their expertise could be invaluable.
 
5. Dr Evidence: They have worked with the top pharma companies globally in the RWD space, and have a specialised medical search engine that could be potentially integrated with Doxper.
 
6. Infosys: Deploying IT solutions at scale globally