Search

Background: The COVID-19 pandemic has uncovered the potential of digital misinformation in shaping the health of nations. The deluge of unverified information that spreads faster than the epidemic itself is an unprecedented phenomenon that has put millions of lives in danger. Mitigating this Infodemic requires strong health messaging systems that are engaging, vernacular, scalable, effective and continuously learn the new patterns of misinformation. Objective: We created WashKaro, a multi-pronged intervention for mitigating misinformation through conversational AI, machine translation and natural language processing. WashKaro provides the right information matched against WHO guidelines through AI, and delivers it in the right format in local languages. Methods: We theorize (i) an NLP based AI engine that could continuously incorporate user feedback to improve relevance of information, (ii) bite sized audio in the local language to improve penetrance in a country with skewed gender literacy ratios, and (iii) conversational but interactive AI engagement with users towards an increased health awareness in the community. Results: A total of 5026 people who downloaded the app during the study window, among those 1545 were active users. Our study shows that 3.4 times more females engaged with the App in Hindi as compared to males, the relevance of AI-filtered news content doubled within 45 days of continuous machine learning, and the prudence of integrated AI chatbot Satya increased thus proving the usefulness of an mHealth platform to mitigate health misinformation. Conclusion: We conclude that a multi-pronged machine learning application delivering vernacular bite-sized audios and conversational AI is an effective approach to mitigate health misinformation., Comment: 14 pages, 7 figures

Background: Teleneurology consultations can be highly advantageous since neurological diseases and disabilities often limit patient's access to health care, particularly in a setting where they nee...

Background Sequential rituximab (RTX) administration has emerged as an important strategy to sustain remission of disease in patients with difficult-to-treat nephrotic syndrome. Methods We report the efficacy and safety of sequential therapy with two or more courses of intravenous RTX in 250 patients with difficult-to-treat steroid dependence (n = 127) and calcineurin inhibitor (CNI)-dependent or CNI-refractory steroid resistance (n = 123) managed at one center during 2015–2021. Subsets of patients were cross-sectionally tested for hypogammaglobulinemia, seroprotection against and hyporesponsiveness to vaccines for hepatitis B and tetanus, BK/JC viruria and human antichimeric antibodies (HACAs). Results Sequential RTX therapy, initiated at a median of 10 years [interquartile range (IQR) 7.3–14.4], was administered for 1.8 courses/person-year [95% confidence interval (CI) 1.7–2.0] over 2.0 years (95% CI 1.2–3.0). Therapy was associated with postponement of relapses by a median of 3 years in patients with steroid-sensitive disease and 2 years in those with steroid resistance. Relapses were reduced by a mean of 2.0 relapses/person-year (95% CI 1.8–2.2), enabling a reduction in prednisolone dose to 0.04 mg/kg/day (95% CI 0.01–0.11) and withdrawal of additional immunosuppression in 154 (62%) patients. RTX-associated adverse events, occurring at 0.20 events/person-year (95% CI 0.17–0.23), were chiefly comprised of infusion reactions (n = 108) and infections (n = 46); serious adverse events were observed in 10.8% patients, at 0.03 events/person-year (95% CI 0.02–0.05). Hypogammaglobulinemia was observed in 35% of 177 patients and was moderate to severe in 8.5% of cases. Rates of seroprotection at baseline and response following vaccination were lower for hepatitis B [1.9% and 29.4% (n = 52)] than tetanus [65.5% and 34.5% (n = 58)]. BK/JC viruria, without viremia, was observed in 7.3% of 109 cases. A total of 19 of 107 patients (17.8%) had HACAs, which were associated with B cell nondepletion and serum sickness. Age at therapy of Conclusions Sequential therapy with RTX effectively reduces relapses in patients with difficult-to-treat steroid- and/or CNI-dependent or CNI-refractory nephrotic syndrome. Therapy is associated with high rates of hypogammaglobulinemia and infusion reactions.

BACKGROUND The COVID-19 pandemic has uncovered the potential of digital misinformation in shaping the health of nations. The deluge of unverified information that spreads faster than the epidemic itself is an unprecedented phenomenon that has put millions of lives in danger. Mitigating this ‘Infodemic’ requires strong health messaging systems that are engaging, vernacular, scalable, effective and continuously learn the new patterns of misinformation. OBJECTIVE We created WashKaro, a multi-pronged intervention for mitigating misinformation through conversational AI, machine translation and natural language processing. WashKaro provides the right information matched against WHO guidelines through AI, and delivers it in the right format in local languages. METHODS We theorize (i) an NLP based AI engine that could continuously incorporate user feedback to improve relevance of information, (ii) bite sized audio in the local language to improve penetrance in a country with skewed gender literacy ratios, and (iii) conversational but interactive AI engagement with users towards an increased health awareness in the community. RESULTS A total of 5026 people who downloaded the app during the study window, among those 1545 were active users. Our study shows that 3.4 times more females engaged with the App in Hindi as compared to males, the relevance of AI-filtered news content doubled within 45 days of continuous machine learning, and the prudence of integrated AI chatbot “Satya” increased thus proving the usefulness of an mHealth platform to mitigate health misinformation. CONCLUSIONS We conclude that a multi-pronged machine learning application delivering vernacular bite-sized audios and conversational AI is an effective approach to mitigate health misinformation. CLINICALTRIAL Not Applicable