Clinical analytics

Froedtert & the MCW Health Network, through its Inception Health innovation arm, built a digital platform on AWS to reimagine the patient experience and support personalized digital engagement.The organization wanted a lean, secure, HIPAA-compliant cloud foundation that could connect disparate parts of the patient journey, support telehealth and asynchronous care at scale, and enable data-driven patient communications.

Froedtert & the MCW Health NetworkHealthcare

Seqrite, the enterprise arm of Quick Heal Technologies, offers cybersecurity software that secures endpoints, data, networks, and users globally.The company built an XDR Event Correlation Engine on AWS to analyze security events and log data in near real time, detect zero-day threats, and automate threat detection and response with minimal human effort.The solution uses Amazon Kinesis Data Streams, Amazon Data Firehose, Amazon OpenSearch Service, and Amazon EMR.

SeqriteTech & Comms

The NFL uses the Digital Athlete as an injury prediction tool that leverages data and artificial intelligence to help clubs keep players healthy and performing at their best.All 32 clubs have access to the Digital Athlete team portal, which provides daily training volume and injury risk information, as well as league-wide trends and benchmarks.The system has also been used to inform rule changes, including the Dynamic Kickoff, by simulating 10,000 seasons' worth of games under the new rule.

National Football LeagueOther

Mount Sinai Health System partnered with Microsoft Azure to develop artificial intelligence solutions aimed at improving patient outcomes and streamlining healthcare operations. This collaboration introduced 14 AI models that address significant challenges like predicting patient falls and malnutrition rates. By combining Microsoft Azure’s scalability and Mount Sinai’s expertise, this partnership pushes the boundaries of healthcare innovation through big data and data science.

Mount Sinai Health SystemHealthcare

Small to medium-sized US home healthcare providers struggled with operational inefficiency, employee retention challenges, and meeting patient care and regulatory requirements. Microsoft Copilot, in combination with Microsoft Teams and Microsoft Fabric, was implemented to address these pain points. Copilot automated repetitive and administrative tasks, including scheduling and coordination between caregivers and administrative staff, reducing delays and missed appointments. AI-powered insights from Dynamics 365 enabled proactive engagement and improved retention through better understanding of staff needs. Predictive analytics, using Azure Health Insights and Fabric, allowed providers to identify early warning signs of patient complications for preventive care. Microsoft’s compliance integration ensured all patient documentation and data handling met healthcare regulation standards. Results included significant improvement to scheduling efficiency and patient satisfaction, reduced risk of staff turnover, and streamlined regulatory compliance processes.

US Home Healthcare ProviderHealthcare

Microsoft Fabric is a SaaS analytics platform that unifies data engineering, data science, and real-time analytics for complex organizations across manufacturing, finance, healthcare, and retail.The platform integrates AI and automation, eliminating data silos and delivering real-time insights for business-critical operations.Fabric’s OneLake centralizes data storage and access, ensuring secure, scalable, and collaborative data management.Manufacturers use Fabric for predictive maintenance, real-time monitoring, and streamlining production.Banks and financial services use case examples include fraud prevention, compliance, and improved risk models.Healthcare organizations leverage Fabric for advanced patient care analytics, collaborative research, and secure data sharing.Retailers utilize unified analytics for demand forecasting, customer behavior analysis, and marketing optimization.The technology is deployed globally on Azure, supported by Microsoft partners such as Saxon AI for integration and analytics expertise.

Humana, a leading US healthcare insurer, partnered with Microsoft Research to leverage AI and the Microsoft Cloud for Healthcare to proactively identify members at high risk for emergency hospital admissions. Traditionally focused on in-patient care and remote monitoring, Humana shifted toward integrating clinical data and key patient event triggers to develop advanced predictive models. These models use neural networks, tree-based models, and deep learning, unified on the Microsoft Cloud, to capture nuanced patient health dynamics. By combining existing single-focus predictive models with structured patient data, the collaboration resulted in over 20% improvement in model precision. Importantly, this was accomplished with strict adherence to data privacy using de-identified information. Enhanced model accuracy allows care teams to act earlier with personalized care plans, helping reduce readmissions and optimize care delivery. The project highlights the impact of precise AI deployment in transforming patient outcomes and reducing healthcare system costs.Humana partnered with Microsoft Research to develop a multivariable AI model integrating data from Humana’s 4.9 million Medicare Advantage members. The research addressed sample imbalance and precision issues through novel deep learning techniques. Resulting improvements in model precision directly enable earlier care team interventions. The effort positions Humana for further analytics-driven care enhancements as models continue to evolve.

HumanaHealthcare

Unnamed AWS healthcare customers developed a deep learning model to predict patient outcomes such as mortality within 90 days after ICU discharge by utilizing both structured and unstructured healthcare data.The solution used Amazon HealthLake to normalize and extract clinical data, combining embedding techniques for richer unstructured data representation.A custom convolutional neural network model was trained on Amazon SageMaker using TensorFlow containers. Visualization of results was provided using SHAP values for interpretability through a custom UI and API Gateway.This approach enabled improved healthcare provider decision-making and early patient intervention based on predictive insights.

Unnamed AWS healthcare customersHealthcare

Munich Leukemia Lab (MLL) partnered with the Amazon Machine Learning Solutions Lab to build a machine learning pipeline leveraging Amazon SageMaker to classify 30 leukemia subtypes using next generation sequencing (NGS) data.Manually classifying leukemia subtypes is complex, slow, and requires expensive specialized equipment and highly skilled experts, leading to turnaround times up to ten days.MLL and AWS developed a feature extraction process transforming varied NGS data into tabular form with over 70,000 features, followed by training a LightGBM model with SageMaker Hyperparameter Optimization achieving 82% accuracy in 5-fold cross-validation.The interpretable model uses SHAP to explain feature impacts per patient, aiding clinical decision making.The solution accelerates diagnosis with high accuracy, reducing time and cost while supporting precision treatment strategies for 30 leukemia subtypes.

Munich Leukemia LabHealthcare

Change Healthcare, a leading independent healthcare technology company in the US, sought to improve clinical, financial, and patient engagement outcomes by reducing overpayment and claim waste.They faced challenges in getting machine learning model predictions into business intelligence tools quickly and cost-effectively.The solution involved leveraging Amazon SageMaker for machine learning training and inference and integrating it with Amazon QuickSight to automate the data ingestion, inference pipeline, and reporting process.This integration allowed business analysts and data scientists to create predictive dashboards without specialized ML expertise, streamlining workflows and reducing the time to deliver insights to decision-makers.The approach eliminated heavy manual ETL tasks, enabled scheduled and programmatic predictions, and reduced costs by using SageMaker batch transform jobs without running costly inference endpoints continuously.

Change HealthcareHealthcare