Intron Health, a pioneering health tech company specialising in clinical speech recognition for over 200 accents spoken in developing countries, particularly in Africa, has raised $1.6M in pre-seed funding. The funding round was led by Microtraction, with contributions from Plug and Play Ventures, Jaza Rift Ventures, Octopus Ventures, Africa Health Ventures, OpenseedVC, Pi Campus, Alumni Angel, and Baker Bridge Capital. Angel investors from global companies such as Google, CLEAR Global, NYU, and Optum also participated.
This investment will enable Intron Health to deepen its research, enhance cloud-native and on-premise capabilities, and expand its distribution network. Additionally, the company plans to grow its team by hiring tech talent to support product development and market expansion, driving further technological advancements.
Voice technology has advanced rapidly globally and now plays a pivotal role in various industries– automating call centre operations, generating social media content, biometric verification, voice bots for mental health and patient education, and eliminating several hours of clinical documentation through ambient listening. Productivity tools such as clinical automatic speech recognition (ASR) are ubiquitous in developed markets. However, with over 3,000 of the world’s estimated 7,000 languages and dialects in Africa, many African and minority languages and accents remain excluded from global speech advancements. Intron Health’s advanced speech recognition platform is bridging this gap by supporting a diverse range of African languages, accents, recognising local names and accurately transcribing medical terminologies online and offline.
Launched in 2020 to digitise healthcare, Intron Founder, Tobi Olatunji, quickly recognised data entry was a massive bottleneck to electronic medical record adoption. Heavy patient traffic meant thousands of keystrokes per day, increasing documentation time and patient wait time, with doctors sometimes spending over six hours a day on paperwork. The significant additional workload made digitization impractical for already overworked clinicians. To combat these inefficiencies, Intron developed Africa’s first clinical speech recognition platform, which boasts up to 92% accuracy rate on medical terminology with heavy accents. This platform helps doctors across Nigeria, Ghana, Kenya, South Africa and most recently Uganda complete documentation seven times faster, significantly accelerating the adoption of Electronic Health Records (EHR) and reducing the administrative burden.
Speaking on the round, Tobi Olatunji, Founder and CEO of Intron Health stated, ‘Having worked as a doctor in Nigeria, I have experienced first-hand the pain points with trying to deliver quality healthcare amidst increasing patient numbers. We are excited about the adoption and growth we've seen over the past year, which shows we are addressing a significant need and providing a well overdue solution to a critical problem in the global south. We are not only improving efficiency but also enhancing health outcomes and positively impacting hospital finances. With the backing of prominent global investors who bring deep knowledge and expertise, we are looking forward to our next phase of growth.’
At West Africa’s largest Hospital, the University of College Hospital, Ibadan, the company significantly alleviated the workload of healthcare practitioners, reducing radiology reporting turnaround time from 48 hours to just 20 minutes. Speaking on the impact on operational efficiency and patient care, the Chief Resident at the Radiology Department, Dr Oluwatosin Fatade, commended the technology’s ability to reduce back-and-forth from multiple report reviews, ultimately cutting patient wait time. “We confirmed it was much better for us than voice-to-text available on Android and iPhones. It is refreshing to finally see great technology that helps doctors amidst several challenges facing healthcare in Nigeria”. Intron Health now serves over 30 public and private hospitals including Aminu Kano Teaching Hospital (AKTH) Kano, Asiwaju Bola Ahmed Tinubu Hospital (ABATH) Lagos, Babcock Teaching Hospital Ogun, and Meridian Health Group Nairobi, providing care to more than 56,000 patients.
Dayo Koleowo, Partner at Microtraction, shared, "We value companies and entrepreneurs who push boundaries with innovative solutions. Intron Health exemplifies this spirit. Tobi and Olakunle have effectively combined their domain expertise, unique insights, and proven execution skills to achieve impressive traction. We are excited to support Intron Health further and confident in their ability to deliver significant value to the healthcare sector and its stakeholders."
To solve the massive problem with various accents and languages, Intron Health created Africa’s largest clinical speech dataset, a proprietary war chest of over 3.5 million audio clips across multiple specialities and domains, covering 288 accents from over 18,000 contributors from 29 countries. This vast dataset has enabled the company to train its algorithms for deployment in any hospital with minimal additional model fine-tuning. Accessible via any device through a browser, Intron Health’s speech-to-text real-time AI transcription converts spoken information into text allowing healthcare providers to easily enter data into electronic medical records, saving time and improving productivity.
Leveraging its humongous African data contributor base, Intron Health recently partnered with Google Research, the Bill & Melinda Gates Foundation, and Digital Square at PATH on the largest study on LLMs in Global health evaluating 20+ LLMS (like OpenAI’s GPT-4o, Google’s Gemini, and Anthropic’s Claude) on 32 medical specialties across 15 countries. The project, tagged AfriMed-QA, creates a pan-African multispecialty benchmark dataset of 20,000 Multiple Choice Questions (MCQs), Short Answer Questions (SAQs) and Consumer Questions for Medical Question-Answering (QA).
Contributed by over 1,000 clinicians across 15 countries, this initiative will identify strengths, weaknesses, and risks of bias or harm in LLMs, and fine-tune culturally attuned models for use in African clinics. The company has also partnered with industry leaders such as NVIDIA and Huggingface to enhance its technology. As a member of the Commonwealth Artificial Intelligence Consortium (CAIC) initiated by the Commonwealth Secretary General, Rt Hon Patricia Scotland KC, Intron will help extend cutting-edge AI technologies to Commonwealth Small States.
No comments:
Post a Comment