At the time this photo was taken in 2021, Covid-19 ICU beds in the Klang Valley were being 113% utilised with field ICUs having to be erected to help cope with the demand. — Tan Sri Dr NOOR HISHAM ABDULLAH/ Facebook
AT the height of the Covid-19 pandemic, hospitals frequently ran short of beds in intensive care units (ICUs).
But before that, ICUs faced challenges in keeping beds available.
Artificial intelligence (AI) offers a possible solution, says The University of Texas at Austin (UT) McCombs School of Business professor of information, risk and operations management Dr Indranil Bardhan, based in the United States.
AI models can predict the lengths of time patients will spend in the ICU, helping hospitals better manage their beds, and ideally, cut costs.
But although AI is good at predicting length of stay, it’s not so good at describing the reasons, the Charles and Elizabeth Prothro Regents Chair in Health Care Management says.
That makes doctors less likely to trust and adopt it.
“People were mostly focused on the accuracy of prediction, and that’s an important thing,” Prof Bardhan says.
“The prediction is good, but can you explain your prediction?”
In new research, he makes AI’s outputs more understandable and useful to ICU doctors – an approach called explainable artificial intelligence (XAI).
With McCombs doctoral student Guo Tianjian, School of Information Bill and Lewis Suit Professor Dr Ding Ying, and Harvard University postdoctoral fellow Dr Zhang Shichang, Prof Bardhan designed a model and trained it on a dataset of 22,243 medical records from 2001 to 2012.
The model processes 47 different attributes of patients at the time they’re admitted, including age, gender, vital signs, medications and diagnosis.
It constructs graphs that show a patient’s probability of being discharged within seven days.
The graphs also depict which attributes most influence the outcome and how they interact.
In one example, the model calculates an 8.5% likelihood of discharge within seven days.
It points to a respiratory system diagnosis as the main reason, and to age and medications as secondary factors.
Running their model against other XAI models, the researchers found that its predictions were just as accurate, while its explanations were more comprehensive than the others.
To test how useful their model might be in practice, the team surveyed six physicians at Austin-area ICUs, asking them to read and evaluate samples of the model’s explanations.
Four of the six said the model could improve their staffing and resource management, helping them better plan patient scheduling.
The model has one major limitation though, Prof Bardhan notes: the age of the data.
In 2014, the industry’s medical coding system changed from ICD-9-CM to ICD-10-CM, adding much more detail in diagnosis coding and classification.
“If we were able to get access to more recent data, we would have loved to extend our models using that data,” he says.
His model also need not be limited to adult ICUs.
“You could extend it to paediatric ICUs and neonatal ICUs,” he says.
“You could use this model for emergency room settings.
“Even if you’re talking about a regular hospital unit, if you want to know how much or how long a patient is likely to need a hospital bed, we can easily extend our model to that setting.”
Details on the AI model were published in the journal Information Systems Research.
