APSR2026-167

Yes
Late-Breaking
Submitted
Oral Presentation
AO07-002
 
 
https://storage.unitedwebnetwork.com/files/1285/1212101-46903-Abstract APSR2026-167_Vandana Garg - Copy_433748.pptx
Format: PPTX Only
 
Format: PDF Only
05. Respiratory Infections (non-tuberculous)
10

No more than 15 authors can be listed.
Please ensure the authors are listed in the right order.
If there are multiple affiliations, please use the "+" button next to "Select Country/Region" to add additional affiliation fields.

Vandana Garg * Haleon Medical & Scientific Affairs Singapore Singapore
Amber Lee - Haleon Medical & Scientific Affairs Kuala Lumpur Malaysia
Yong Qing Khoo - Haleon Medical & Scientific Affairs Singapore Singapore
Gerard Toh - Tech Observer Asia Pacific Medical Writing Singapore Singapore
Jocelyn Leong - Tech Observer Asia Pacific Medical Writing Singapore Singapore
Arya Shah - Tech Observer Asia Pacific Medical Writing Singapore Singapore
Shi Nee Tan - KPJ Healthcare University Graduate School of Medicine Nilai Malaysia
De Yun Wang - Yong Loo Lin School of Medicine, National University of Singapore Department of Otolaryngology Singapore Singapore
Baharudin Abdullah - Universiti Sains Malaysia Department of Otorhinolaryngology-Head and Neck Surgery Kubang Kerian Malaysia
Sheryl Tan - Haleon Medical & Scientific Affairs Singapore Singapore
 
 
 
 
 
Presenting Author Details
Vandana
Garg
vandana.x.garg@haleon.com
+6598578313
41-50
Singapore
Original Research
Artificial intelligence-based analysis of digital behavior in acute respiratory infections across five Asia-Pacific countries: Implications for multi-symptom management
Maximum 25 words
Abstract Content
Acute respiratory infections (ARIs) are among the most common illnesses globally, often presenting with overlapping symptoms such as fever, headache, and nasal congestion. Inadequate symptom management can lead to considerable patient discomfort and contribute to inappropriate antibiotic use. Using artificial intelligence (AI) to analyze digital behavior, this study evaluated consumer priorities and generated insights to guide patient-centered multi-symptom ARI care.
A cross-sectional study was conducted using aggregated, anonymized digital behavioral data from 5 Asia-Pacific countries (Singapore, Malaysia, Indonesia, Philippines, and India) between August and October 2025. Data were extracted via SQREEM, a cognitive AI analytics platform that captures population-level online engagement signals including web searches and content interactions. The AI algorithm identified and measured ARI-related digital activities, represented as topic/keyword data. Quantitative keyword analysis was applied to extract and compare symptom- and management-specific themes by engagement signal strength. Key outcomes included representative themes from consumer sentiments, and symptom-related topic keywords demonstrating high engagement. Engagement intensity was quantified using a normalized Engagement Score; higher scores indicate stronger interest and importance.
In total, 283,787,193 ARI-related digital activities were analyzed. Analysis of aggregated consumer sentiment highlighted three top priorities: ‘Relief to Recovery’ was the dominant theme (average Engagement Score 8.1), followed by ‘Comfort & Ease’ (5.9) and ‘Symptom-specific Relief’ (4.6). The ‘Relief to Recovery’ theme captured recovery-oriented digital activities emphasizing improvement and return to daily routines. Highest-engagement symptoms (cough, nasal congestion, sore throat, fever, headache) varied by country; this absence of a universally dominant symptom highlights a consistent need for comprehensive symptom control.
Consumer engagement consistently emphasizes recovery, comfort, and symptom relief. Even with variations in dominant symptoms, the study underscores a universal demand for effective multi-symptom management. Future work should assess how AI-powered analytics can inform personalized strategies to enhance recovery speed and daily life resumption.
 
 
 
 
 
No
No
 
JPG or JPEG or PNG format ONLY
Acute respiratory infections, digital behavior, multi-symptom management
maximum 3 keywords and no abbreviations, separated by commas
Data collection and analysis support was provided by Tech Observer Asia Pacific.
299