Automatic Adverse Drug Reaction Extraction from Electronic Health Records

Patients' electronic health records convey crucial information. The application of natural language processing techniques to these records may be an effective means of extracting information that may improve clinical decision making, clinical documentation and billing, disease prediction and the detection of adverse drug reactions. Adverse drug reactions are a major health problem, resulting in hospital re-admissions and even the death of thousands of patients. An automatic detection system can highlight said reactions in a document, summarise them and automatically report them.

In this context, the Basurto University Hospital and the Galdakao Hospital 'were interested in creating a system that would use natural language processing techniques to analyse patient health records in order to automatically identify any adverse effects' explains the engineer Sara Santiso, who also holds a PhD in Computer Science. After the hospitals contacted the IXA group at the UPV/EHU, several researchers started working to build a robust model with which to extract adverse drug reactions from electronic health records written in Spanish, based on clinical text mining.

To this end 'not only have we used techniques based on traditional machine learning algorithms, we have also explored deep learning techniques, reaching the conclusion that these are better able to detect adverse reactions' explains Santiso, one of the authors of the study. Machine learning and deep learning imitate the way the human brain learns, although they use different types of algorithms to do so.

Difficulties finding a corpus in Spanish

Santiso underscores the difficulties the team encountered when trying to find a large enough corpus with which to work: 'At first, we started with only a few health records, because they are difficult to obtain due to privacy issues; you have to sign confidentiality agreements in order to work with them' she explains. The research team has found that 'having a larger corpus helps the system learn the examples contained in it more effectively, thereby giving rise to better results'.

Through this study, which was carried out with health records written in Spanish, 'we are contributing to closing the gap between clinical text mining in English and that carried out in other languages, which accounts for less than 5% of all papers published in the field. Indeed, the extraction of clinical information is not yet fully developed due (among other things) to the potential for extracting information from other hospitals and in other languages' claims the researcher.

Although natural language processing has been of inestimable help in the computer-aided detection of adverse drug reactions, there is still room for improvement: 'To date, systems have tended to focus on detecting drug-disease pairs located in the same sentence.

However, health records contain implicit information that might reveal underlying relations (for example, information about antecedents might be relevant for determining the causes of an adverse event). In other words, future research should strive to detect both explicitly and implicitly-stated inter-sentence relationships'. Moreover, another issue that should be the subject of future research is the lack of electronic health records written in Spanish.

Sara Santiso, Alicia PĂ©rez, Arantza Casillas.
Adverse Drug Reaction extraction: Tolerance to entity recognition errors and sub-domain variants.
Computer Methods and Programs in Biomedicine, Volume 199, 2021. doi: 10.1016/j.cmpb.2020.105891

Most Popular Now

Early Warning System for Intensive Care …

Life-threatening situations occur time and again in an intensive care unit. To make sure that doctors can intervene in time, a team at the German Heart Center Berlin (DHZB) has...

Virtual Reality could Help to Reduce Pai…

We all feel physical pain in different ways, but people with nerve injuries often have a dysfunctional pain suppression system, making them particularly prone to discomfort. Now researchers have uncovered that...

Philips Partners with Orbita to Develop …

Royal Philips (NYSE: PHG, AEX: PHIA), a global leader in health technology, and Orbita Inc., an innovative provider of conversational artificial intelligence (AI) solutions for healthcare, announced a partnership agreement...

CliniSys Group Creates Single Brand for …

CliniSys Group has created a single brand for its businesses in the UK and Europe, with a refreshed logo and a new website. The move creates a unified identity for CliniSys...

East Lancashire Signs Deal for Early War…

Thousands of NHS professionals across five hospitals in East Lancashire are to benefit from early warning technology that will help them detect and swiftly respond to deteriorating patients in need...

FDA Grants Oxehealth Vital Signs De Novo…

Oxehealth has announced another world first after the US Food and Drug Administration granted a De Novo clearance for its Oxehealth Vital Signs product, which is incorporated into Oxevision, the...

Telemedicine Improves Access to High-Qua…

The American Academy of Sleep Medicine recently published an update on the use of telemedicine for the diagnosis and treatment of sleep disorders to reflect lessons learned from the transition...

DMEA 2021: Digital Health. 100 % Virtual…

7 - 11 June 2021, Berlin, Germany. An entire week dominated by digital healthcare! With that in mind, early in June DMEA 2021 will be kicking off with a wide range...

Philips and NHS Implement the First Regi…

Royal Philips (NYSE: PHG, AEX: PHIA), announced it has supported the NHS' Cheshire and Merseyside consortium [1] to become the first regional hub supplying the United Kingdom's National COVID-19 Chest...

Child Brain Tumours can be Classified by…

Diffusion weighted imaging and machine learning can successfully classify the diagnosis and characteristics of common types of paediatric brain tumours a UK-based multi-centre study, including WMG at the University of...

AI could Crack the Language of Cancer an…

Powerful algorithms used by Netflix, Amazon and Facebook can 'predict' the biological language of cancer and neurodegenerative diseases like Alzheimer's, scientists have found.