Artificial Intelligence in business is still a fantasy for many of us. For some, Artificial Intelligence frees humans from dull tasks; for others, it would alienate us and destroy jobs. But what few of us know is that AI and Machine Learning are already very present in our companies, and that we use them every day!
NLP (Natural Language Processing) is one of the most prolific fields of application of AI. It is the branch of Artificial Intelligence which involves understanding and processing human language.
Its uses in business are very numerous: NLP offers a wealth of opportunities to increase productivity, reliability, and make better decisions.
Having explored the use cases of NLP in Marketing and Customer Relations, then in the HR industry and in the Legal field, we now turn to the applications of language processing in the Healthcare industry.
A sector with profound specificities (regulatory, organizational, financial, State importance), where the notions of patients and practitioners replace those of consumers and employees, health brings together a large part of human tasks with high added value, and therefore difficult to automate. The highly confidential nature of health data must also be taken into account. This sector is nevertheless an important playground for the NLP.
1- NLP to improve the Patient Experience
Just like the Voice of the Customer and the Voice of the Collaborator, the Voice of the Patient requires being listened to understand how they perceive their experience, and to improve it.
“The patient experience can be defined as the set of interactions and situations experienced by a person, likely to influence their perception during their health journey”, explains Amah Kouevi, founder of the Institut français de l’expérience patient (French Institute of the Patient Experience).
Feedback: automated analysis of home health anomaly reports
One of the leading French home health companies works with Semantic Analysis solutions to improve the state of health of patients.
This company sells medical and surgical equipment to equip the patient for his stay in the place of residence. To ensure the quality of its service, the company asks its home technicians to write anomaly reports in the event of equipment malfunction or patient complaints. In seven years, 20,000 improvement reports have been filed, containing 100,000 responses to open-ended questions asked. The Semantic Analysis made it possible to study, sort and annotate the reasons for patient satisfaction and dissatisfaction contained in these reports in record time.
This device can very well be used to analyze the comments received via a post-stay satisfaction survey in a health establishment, or as part of a care path.
Feedback: Orkyn’ adopts a chatbot to facilitate the relationship with patients and their caregivers
Orkyn’, a home health care provider, has set up a chatbot on its site to advise people with loss of dependence and their caregivers. The chatbot understands the questions asked in Natural Language and is constantly improving with the questions asked.
Read the Orkyn’ case study: A chatbot to advise people with lower mobility and their caregivers.
2- NLP to speed up R&D work
Applied to large databases, Semantic Analysis technologies help to accelerate the acquisition of information and the constitution of knowledge. They also allow us to go further by identifying unnoticed relationships between certain concepts.
Thus, Semantic Analysis makes it possible to process large volumes of scientific publications, summaries of clinical trials or even internal research documents.
NLP projects have thus made it possible to identify new biomarkers and phenotypes, or to detect antibiotic resistance relationships.
In addition to the processing time saved, NLP allows access to knowledge embedded in large quantities of texts, difficult to analyze by humans on such a volume. Significant bonus, the semantic annotations produced (entities and relations) can be added to the original PDF document, using the layer mechanisms, which greatly facilitates the rapid reading of documents.
