By Shalini Bhardwaj
Chennai (Tamil Nadu) [India], July 9 : More than half of all tuberculosis (TB) deaths occur within the first two months of treatment. In response, the Indian Council of Medical Research-National Institute of Epidemiology (ICMR-NIE) has introduced a new alert feature designed to immediately notify frontline healthcare workers when a patient is identified as severely ill following a TB diagnosis.
The predictive model is expected to reduce the average time from diagnosis to hospital admission for severely ill patients with tuberculosis.
The ICMR-NIE has recently launched a predictive model that helps the state reduce TB deaths.
The predictive model was developed using data from 57,803 adults diagnosed with TB from public health facilities.
"In 2023, of 57,803 adults with TB diagnosed from public facilities, 57,070 (99%) were triaged and 6864 (12%) were triage-positive (eligible for referral). Of 6864 eligible, 6105(89%) were referred, comprehensively assessed and confirmed as severely ill at nodal inpatient facilities. Of 6105 confirmed, 5926 (98%) were admitted for inpatient care and 5413 (92%) were successfully discharged for ambulatory directly observed treatment. The median admission duration was seven days," the study noted.
The new feature introduced by the ICMR-NIE would merge with the existing TB SeWA (Secere TB Web Application), which was launched in 2022 and integrated into the state's TN-KET (Tamil Nadu Kasanoi Erappila Thittam).
According to experts from ICMR-NIE, "This new feature will be useful to Alert front-line staff on how to recognise severely ill TB patients to avoid delay in treatment."
They further added, "The Majority of TB deaths are being reported early (within 2 months), India TB program's information management system (Nikshay) dependent death prediction models are not feasible for prospective use as few variables are captured at diagnosis. Utilising routinely captured triage variables for severe illness in TB SeWA that are available under TN-KET at diagnosis (body mass index, pedal oedema, respiratory rate, oxygen saturation, and ability to stand without support), robust models for prospective use were developed."