AI case studies from the real-world

Researchers from Tampere University apply machine learning to Instagram posts to predict the spread of influenza in Finland

Stanford University’s Department of Earth System Science identified the most poverty-stricken regions in parts of Africa using machine analysis of satellite imagery

CaseCrunch's AI program demonstrates greater accuracy predicting the outcomes of historic PPI cases than human lawyers

Cambridge Analytica claims to have targeted voters by modelling voter propensity to persuasion through a variety of emotional state approaches

FICO reduces bank's losses on delinquent customers by up to 25% with machine learning that predicts consumer credit risk

H&R Block improves filing acceptance rates by 10% by monitoring the performance of its online tax filing application and user experience using machine learning

Kingston Smith automates financial auditing by analysing transaction data against users and vendors and identify risk using machine learning

Schneider Electric saves €8 million by optimising its supply chain using machine learning

ARUP saves 790 engineering hours using machine learning to detect utility clash points planning a light rail system for Auckland

HealthMap analyses social media and publicly available healthcare data to detect and predict outbreaks around the globe

Imagen Tech's Osteodetect platform which uses deep learning to detect wrist fractures has acquired FDA approval

Johns Hopkins Hospital improves patient monitoring and resource allocation in ER and critical care units in real-time using machine learning

Kaiser Parmanente increases construction labour productivity by 38% and saves 11% from the initial construction budget with machine vision and analytics

Kaiser Permanente predicts probability of rapid deterioration of patient condition and alerts physicians using machine learning

Mayo Clinic researchers accurately diagnose hyperkalemia using a smartphone electrocardiogram device

Mercy Hospital Fort Smith improves patient flow and throughput in the ER to improves LWBS rates by over 30% using machine learning

NCI designated cancer centers reduces time to treatment for diagnosed patients by 5 days using machine learning and natural language processing

NHS investigates whether inflammation plays a role in mental illnesses by extracting blood test results from unstructured medical records with advanced natural language processing

Researchers develop a model to provide individualised and clinically interpretable treatment decisions to improve sepsis patients outcomes

Sheba Medical Center ensures accuracy of prescriptions and eliminates human error using machine learning

St. Michael’s Hospital predicts onset of sepsis among ICU patients with 90% accuracy using learning evolutionary algorithm framework

Suramericana optimises urgent operations scheduling with predictive analytics and machine learning

Israel Institute of Technology researchers are developing a nano-array to automatically diagnose a number of diseases from exhaled breath

WeWork predicts office meeting room usage with 40% more accuracy using neural networks

GV evaluates new and follow-on investments using machine learning

AXA used deep neural networks to increase the predictability of a customer large traffic accident from 40% to 78%

An anonymous global insurance company analysed customer contact recordings and claims data to drive sales yields using natural language processing

Orlando Health pilots platform to identify patterns in denied health insurance claims to recover payments and avoid future denials

QBE group plans to measure risk at individual level to calculate optimum premium price using machine learning

SCT Capital Management $350 Adaptive Quant Trading hedge fund is fully automated