AI system achieves 95pc accuracy in early cervical cancer detection

DAR ES SALAAM: A NEW (AI) system developed in Tanzania for the early detection of cervical cancer has demonstrated an impressive 95 per cent accuracy rate, surpassing the performance of human specialists.

Statistics indicate that doctors examining patients with the naked eye achieve, on average, a 79 per cent accuracy rate in interpreting the disease.

The system, currently undergoing clinical validation, was developed by a local innovator at the Muhimbili University of Health and Allied Sciences (MUHAS), marking a significant milestone for homegrown innovation in the country’s healthcare sector.

Speaking to journalists in Dar es Salaam on Tuesday during the reception of three Lambda Vector supercomputers donated to MUHAS, Co-Founder of Saratani AI, Dr Sang’udi Sang’udi, said the system is currently in pilot testing.

The AI uses machinelearning algorithms to analyse medical images and identify early signs of cervical cancer with remarkable precision.

“The technology could revolutionise care for women in remote areas, where access to qualified doctors and diagnostic services remains limited,” he said, noting that cervical cancer remains one of the leading causes of cancer-related deaths among women in low- and middle-income countries, largely due to late diagnosis.

Dr Sang’udi expressed optimism that AI innovation will reduce the burden on healthcare workers and allow doctors to focus more on treatment.

ALSO READ: Women encouraged to go for cervical cancer screening

Explaining the donation of three high-performance computers worth 40 million/- from Global Health Labs (GHL), under the Bill & Melinda Gates Foundation and Gates Ventures, Dr Sang’udi said the machines will accelerate the training of the Saratani AI system.

“This will enable the system, currently undergoing clinical validation, to efficiently process and analyse incoming data in a much shorter period. Previously, it took us two to three weeks to train the system to interpret disease data. With the support of these computers, we can obtain results far more quickly,” he added.

The Head of the Biomedical Engineering Department at MUHAS, Dr Deogratius Mzurikwao, said the addition of the three new computers brings the department’s total to 11 machines, which have the capacity to develop AI systems aimed at improving healthcare service delivery.

“Already, we have a technology for the early detection of breast cancer, developed using these computers and local data and another system for heart disease, which is currently in trials,” he said.

MUHAS Vice-Chancellor Prof Appolinary Kamuhabwa pledged continued support for the university’s innovation unit to ensure that locally developed technologies contribute to transformative changes in the country’s healthcare sector.

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button