Discuss how AI-enabled screening and rapid molecular diagnostics can transform active case finding in communicable disease control in India.

Active case finding (ACF) means going out to search for disease among at-risk groups instead of waiting for sick people to reach a clinic. India carries about one-fourth of the world's TB cases [3]. Combining AI-assisted screening with rapid molecular tests can help disease control act early instead of only reacting.

How they transform active case finding

• Screening at the doorstep: AI-supported portable X-ray machines screen people in villages, slums and crowded places such as prisons and mines. They flag who needs a confirmatory test [1][2].
• Finding hidden cases: The 100-day TB campaign X-rayed over 38 lakh people, including many without typical symptoms [2]. Symptom-based (passive) case finding misses these people, and they keep spreading infection.
• Fast confirmation: NAAT (molecular tests) confirms TB close to the patient [2] and detects drug resistance [1], so the right treatment starts sooner.
• Closing the resistance gap: India accounts for 33% of the global gap between estimated drug-resistant TB cases and those put on treatment [4].
• Making up for scarce specialists: AI reading reduces the need for radiologists, who are scarce in rural districts. The same platforms can be adapted for other infectious diseases.

Limitations

• Private-sector blind spot: In 2016, about 1 million TB cases went unreported, mostly people treated by private providers [5]. Technology placed only in public facilities cannot capture them.
• More demand than capacity: Community mobilisation such as JOSH Teams [1] sends more people for testing. Without enough machines, test cartridges and staff, they wait and lose trust.
• AI governance: AI tools may be less accurate for some groups of patients. Data privacy and responsibility for missed diagnoses still need clear rules.
• Care after detection: Finding a case helps only if the patient continues to diagnosis, treatment and completion [1].

Way forward

• Plan testing capacity before running campaigns, starting with high-burden districts.
• Link private clinics and laboratories to Ni-kshay, the government's online TB reporting system.
• Test AI tools on Indian patient data before scaling them, and protect patient data.
• Use community volunteers for referral and follow-up.

AI-enabled screening and rapid molecular tests can make case finding faster, wider and more accurate. Their value depends on enough testing capacity, links with private providers and support until cure. Built into a Jan Bhagidari (people's participation) approach, they can move India closer to SDG 3.3: ending the epidemics of TB and other communicable diseases by 2030.