APBN New Site

APBN Developing Site

Artificial Intelligence Tool to Predict Severity of Pneumonia

New predictive engine powered by artificial intelligence developed by Changi General Hospital (CGH) and the Integrated Health Information System (IHiS) to determine severity of pneumonia in patients.

Pneumonia is a serious inflammatory condition that accounts for 20.7 percent of deaths in Singapore in 2019. It is one of the leading causes of death in Singapore and across the world and is the main cause of deterioration and complications in COVID-19. The ability to quickly predict the severity of pneumonia in patients would enable clinicians and healthcare professionals to efficiently allocate healthcare resources and treat patients, particularly during disease outbreaks, where there may be an increased need for inpatient care and critical care support.

As pneumonia severity correlates to the degree of Chest X-Ray (CXR) lung image abnormality, CGH’s Respiratory and Critical Care Medicine and Radiology teams recognised the potential in leveraging artificial intelligence to predict the severity of pneumonia from CXR images, and worked with the IHiS Health Insights team to develop CAPE (Community Acquired Pneumonia and COVID-19 Artificial Intelligence Predictive Engine).

Dr Charlene Liew, Project Lead and Deputy Chief Medical Informatics Officer, CGH, and Director of Innovation, SingHealth Radiological Sciences Academic Clinical Programme (RADSC ACP) said, “One main advantage of using artificial intelligence as a predictive tool is that the risk of patients requiring critical care can be calculated almost instantaneously. Emergency Department and ward doctors can receive an early warning for possible clinical deterioration and prescribe the appropriate interim measures to improve patient outcomes.”

“Driven by the clinical care needs and resource demands of the pandemic, the CGH and IHiS teams saw the potential of AI to combat the critical needs of COVID-19,” said Professor Ng Wai Hoe, Chief Executive Officer of CGH, “CAPE shows the value of interdisciplinary collaboration and that research and innovation can occur even in difficult times to provide practical solutions to improve patient care.”

CAPE works by generating a score for three things; low-risk pneumonia with anticipated short inpatient hospitalisation, the risk of death, and the risk of requiring critical care support. Calculation of the score is done by training the CAPE system with more than 3,000 CXR images and 200,000 datapoints which include lab results and clinical history. The score would then serve as a support for clinicians in decision-making and allocation of required critical care for patients who need it more urgently.

Initial validation tests at CGH showed that CAPE has an approximate accuracy of 80 percent in predicting severe pneumonia. This result was comparable to traditional pneumonia severity tools that are scored manually.

This new predictive engine has the potential to be calibrated to support other healthcare settings for identifying and predicting severity of respiratory infections. Given the current pandemic climate, there is an increased demand for inpatient and critical care support. Particularly in areas where healthcare resources are limited, CAPE could potentially provide better allocations of resources to more severe patients to receive appropriate and timely care.

“Technology has been a crucial enabler in every stage of our fight against COVID-19 – prevention, detection, containment and patient care. CAPE is one of over 50 HealthTech solutions IHiS has engineered and we are happy to partner CGH in the use of AI to better predict the severity of pneumonia for better patient care. The accelerated launch and quick refinements were possible with an agile delivery approach and excellent partnership between the IHiS tech and CGH clinical teams,” said Bruce Liang, Chief Executive Officer of IHiS.

Validated with prospective clinical data at CGH since May 2020, the team is looking to integrate data from electronic medical records, and further improve the accuracy of CAPE with clinical data from the SingHealth cluster including Singapore General Hospital and Sengkang General Hospital. The team is also exploring collaborative models, including hosting it as a “freeware” collaborative tool on a research platform for interested researchers, so that CAPE can be generalised and eventually used internationally.

A study published on CAPE was accepted as poster paper in “Knowledge Discovery and Data Mining”, a leading publication in data mining and analysis, and also presented at the Knowledge Discovery and Data Mining (KDD) conference on (24 August 2020). [APBN]