Taiwan and U.S. researchers announced the results of a new joint study into the international transferability of machine learning (ML) models to detect medication errors. ML can help doctors to make better decisions and improve patient safety and quality of care. The results were recently published in the Journal of Medical Internet Research – Medical Informatics.
Medication errors are a growing financial and healthcare burden that results in economic costs. Medication errors can occur during any stage of the medication process, including prescribing, dispensing, administration, and monitoring, with errors in prescribing accounting for 50% of the total.
When medicating patients, physicians go through complex decision-making processes to accurately write a prescription. First, they must clearly define the patient’s problem and list the therapeutic objective before selecting an appropriate drug therapy based on age, gender, and possible allergies. They must also consider dosing, drug-drug interaction, potential discontinuation of the drug, drug cost, and other therapies — and all of these need to be done instantly and simultaneously.
Reducing medication errors at the source is crucial. However, to help physicians be better informed and make better decisions, they need more accurate suggestions and alerts. Hence, ML can provide insights on patterns and predictions to help doctors make data-driven decisions. For technology to assist in solving these problems, ML learning must understand these variables. For this to be successful, data must be properly collected, organized, and maintained.
Data-driven medicine demands huge and diverse medical data sets. The biggest challenge is successfully implementing data-driven applications in clinical practice, from local to global, without compromising patient safety and privacy.
The AI model for medication safety has been trained by one of the world’s largest prescription databases, 1.5 billion well-coded prescriptions from the U.S. and Taiwan, to learn the association between diagnosis, medication, and complex prescribing behaviour of doctors from different countries. The study has shown the model trained by federated learning (FL) achieves remarkable performance comparable to the other two models trained by individual data sets.
The system can immediately provide adaptive suggestions to help the doctor better complete the prescription whenever physicians prescribe diagnoses or medications that cannot be explained. The new model has been deployed in several hospitals and has since been expanded to the eastern and western United States to catch medication errors before they make an impact.
The result is a breakthrough in the international transferability of medical AI. It demonstrates a way to provide practical data-driven prescribing support to improve patient safety even though it could be challenging to obtain data to develop these systems locally.
Taiwan has been utilising technology to improve its health sector such as developing artificial intelligence (AI) that can identify brain tumour more quickly and accurately. As reported by OpenGov Asia, National Taiwan University Hospital (NTUH) is collaborating with the U.S.- based Artificial Intelligence (AI) solution provider to develop the first-ever AI-powered tumour auto-contouring solution. To treat brain cancer, doctors must first precisely map out where the tumours are in the brain, in a process called contouring.
Using traditional manual contouring takes several hours, while the AI device can shorten the process to just a few minutes. It ensures precision mapping of brain tumours with closer cuts and the ability to identify additional lesions that may be missed by the human eye.
NTUH has been used the AI device for the past 18 months as part of clinical trials and helped doctors treat more than 100 patients with brain tumours, including a terminally ill woman whose lung cancer metastasised to her brain.
The director of the NTUH Department of Oncology said with the AI device, even tiny tumours can be treated precisely thereby ensuring patients experience fewer side effects. In addition, it also means doctors have time to help additional patients or engage in more discussions with existing patients
According to a page, The AI device has received clearance from the U.S. Food and Drug Administration (FDA). This is the first time the FDA has cleared an AI device for tumour auto-contouring in radiation therapy. Devices to receive FDA clearance before are specific to normal organ auto-contouring.
