Risk Management
Singapore General Hospital needed to curb inappropriate antibiotic prescribing and antimicrobial resistance, but its antimicrobial stewardship team could manually audit only a limited subset of prescriptions and could not scale to broader, real-time review across patient records and clinical context.
Reported impact
The AI system improved stewardship efficiency by sharply narrowing the review queue, accelerating case analysis from manual minutes to sub-second assessment, and supporting more timely, targeted antibiotic interventions intended to reduce inappropriate prescribing, hospital stays, mortality, readmissions, and treatment costs.
Singapore General Hospital and DXC Technology co-created a custom AI-driven antimicrobial stewardship solution to automate review of antibiotic use for pneumonia. The implementation draws data from SGH's proprietary electronic medical records system and linked repositories including radiology images, laboratory results, histology reports, and anaesthetic charts. These inputs are transformed through data-engineering and data-completeness strategies so patient history, biomarkers, comorbidities, prior admissions, microbiology, and treatment timing can be normalized for analysis. On top of this data foundation, SGH built an operational AI model that flags prescriptions needing ASP review and a recommender AI model that suggests suitable regimens. The models apply a five-part clinical reasoning framework to support point-of-prescription decisions, prioritize complex cases, and move stewardship from retrospective manual audit toward real-time, patient-specific treatment guidance inside hospital clinical workflows.
Clinical data is pulled from SGH's proprietary EMR system and linked repositories holding radiology, lab, histology, and anaesthetic records, then processed with data-engineering and missing-data strategies into illness-specific features. The operational AI model scores pneumonia prescriptions for review priority, and the recommender AI model returns regimen guidance for ASP teams and clinicians in clinical workflows.
"DXC and SGH co-created an AI model that gives antimicrobial stewardship program (ASP) teams faster, more accurate insights into antibiotic use."
"In 2018 alone, approximately 12,000 audits performed for broad-spectrum antibiotic use at SGH showed that 20 to 30 per cent of these prescriptions were inappropriate."
"In SGH, data will need to be drawn from institution’s proprietary electronic medical records system. Information from linked data repositories, such as radiology images, all laboratory results, histology reports and anaesthetic charts, is also required"
"In a test using 2,012 pneumonia treatments unseen by the model, 624 cases were flagged as requiring additional review. Seventy-two (87%) of all intervention cases were captured within the 624 cases flagged for review."
"Singapore General Hospital is working with DXC Technology to use artificial intelligence (AI) to automate the process of auditing antibiotic usage"
"While manual processes typically take 20 minutes to review each case, AI can assess the same data in less than a second"
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
In-house Sample Jul 28, 2026 Novartis Novartis R&D needs to turn large volumes of scientific, clinical, operational, and real-world data into faster, higher-quality decisions across drug discovery and development, reducing cycle times, surfacing safety… less than 10 percent of drug candidates historically reach the market AI models · AI-enhanced analytics · Generative AI In-house Sample Feb 24, 2026 Sanofi Sanofi needed a faster, more objective way to decide which R&D programs to advance, accelerate, or stop while weighing costs, clinical trial enrollment timelines, unmet need, competition, and each program's probability… more than one billion data points across Sanofi Aily Labs · Plai In-house Sample May 22, 2024 Sanofi Drug development is long, resource-intensive, and uncertain, and Sanofi needed a better way to assess safety, efficacy, and competitive differentiation of drug candidates before advancing them into later clinical phases. 90% failure rate of new drug candidates during clinical development 