Symposium 4 – Medication Safety

The World Health Organization recognizes medication related errors as major threat, focusing at 5 particular moments. This including the time when prescribing and administrating medication, as well when there is addition, review and stopping of medication. 


To reduce medication harm, the rapid advancement of artificial intelligence (AI) shows its potential to assist clinical team with its ability to navigate and analyze vast amount of clinical, genomic, metabolomics and environmental data during the busy clinical setting. 


We have witnessed continuous enhancement of Clinical Management System (CMS), including the latest reminder to help clinician in reminding clinical intention and target INR for anticoagulant as to minimize risk incurred from inadvertent suspension of medication or erroneous dosing. This marks an important step in applying technology to reduce medication errors starting with high risk medications. 


In recognizing the rapidly advancement in applying genomic medicine for medication safety, an initial action taken locally is the preemptive alert of HLA status before initiation of medication such as carbamazepine and allopurinol. It is envisaged more general application of precision medicine in future.


The decision of treat and treatment target is followed by decision on dosing regimen. Effective communication of these important decisions to other clinical team members and patient is of utmost importance in medication safety. Standardization of complex regimen and reminder of the at finger tips of patients via HA GO greatly empower our patients. The real time tracking of relevant laboratory results will also further reduce error during medication administration. 


We believe the application of AI will help improve quality of care while the health care team to grow along with the technology. Instead of replacing health care professional, it will allow us to leave more time for human touch, and do their job better.

Medication safety has always been ranked as one of the top clinical risk in healthcare delivery. It is a common challenge to healthcare professionals around the world where unsafe medication practices could lead to errors and subsequently patient harm and increased healthcare cost. Medication Without Harm was identified by WHO as the theme for the third Global Patient Safety Challenge in 2017. 


Different strategies have been promoted as risk reduction measures to safeguard medication safety and to improve quality of services as well as to manage ever mounting healthcare cost at the same time. Closed loop medication management, automation, pharmacy informatics, IoT technologies, digitalization, etc. have been well recognized as the key building blocks of a modern medication practice taking into consideration the complexity in operational needs, complicated medication management processes, incomplete or inadequate access to complete drug use information, drug supply & logistics complications, etc. In this session, the experience of implementing Innovative solutions in a new private teaching hospital in Hong Kong for better medication management would be shared. 


CUHK Medical Centre is a newly established non-profit private teaching hospital in Hong Kong. In line with the hospital’s mission of pioneering solutions in healthcare, various smart systems have been included from the early stage of hospital design and commissioning to provide patient-centred pharmaceutical care, with focus on medication safety, efficiency and creating value for patients. Some highlights include the first implementation of all-in-one automated unit dose dispensing for inpatient as well as an automated multiple dose dispensing model directly for outpatients in Hong Kong. Building on the hospital eMR system as the common platform, the core elements within the medication management cycle including people, medications, automations/IT systems and data are connected together seamlessly.

Medication-related decision support using rule-based approaches has been demonstrated to be effective when used well, although the false positive rates of warnings are often too high, which can result in alert fatigue for providers.  Increasingly, there is interest in leveraging artificial intelligence to improve the positive predictive value of alerts and reduce false positive rates.  Dr. Bates will discuss an evaluation of decision support developed by a company called Seegnal which leverages both a better rule-based approach, patient-specific alteration of the decision support, and some artificial intelligence to improve performance.  This evaluation found in a retrospective study that it performed much better than decision support in an Epic implementation.  He will also discuss the future of medication-related decision support, which will almost certainly include artificial intelligence as well as rules.