Learning objectives
Outline a digital integrative cancer care service including free-text clinical progress notes
Introduce the concept of natural language processing (NLP) and its clinical usefulness
Illustrate the basic methodology of NLP using our pilot example
Discuss the limitations and future steps of NLP in clinical medicine
Background
Our organisation runs an outpatient commercial digital integrative cancer care service that targets working-age patients who have discontinued work after cancer diagnosis and treatment. The service is multifaceted, is digitally advanced and encourages overall wellbeing and return to regular life. Participants can enrol in the service through a variety of means and partners; in this study we retrospectively analysed 365 cancer patients that commenced the service, who paused work and claimed income protection through a single life insurer on account of the burden of their...
Imaging findings OR Procedure details
Labelling text
All the notes were manually read by a trained staff member, after which patients were classified as requiring or not requiring support in each of two categories - physical and social wellbeing. These labels are used to train and then assess the NLP algorithm.
Processing text
Free-text notes need to be converted into a format that is interpretable by an algorithm - in our case this is a vectorised numerical format. Two principle techniques are applied. We used the NLTK toolkit from Python....
Conclusion
In our commercial digital integrative cancer care service, physical and social dysfunction were common in working age persons after cancer treatment. A relatively simple AI natural language processing algorithm was successfully piloted which could screen for patients needing more support using free-text progress notes. This improves our ability to care for our patients by recognising their needs earlier and providing adequate tailored digital support.
NLP should be further explored to solve other important clinical tasks, for example in retrospective audits or research that analyse large...
References
Pons E, Braun LM, Hunink MM, Kors JA. Natural language processing in radiology: a systematic review. Radiology 2016;279:329-43.
Tokunaga T, Makoto I. Text categorization based on weighted inverse document frequency. Special Interest Groups and Information Process Society of Japan (SIG-IPSJ; 1994: Citeseer.
Liu H, Christiansen T, Baumgartner WA, Verspoor K. BioLemmatizer: a lemmatization tool for morphological processing of biomedical text. Journal of biomedical semantics 2012;3:1-29.
Cammel SA, De Vos MS, van Soest D, et al. How to automatically turn patient experience free-text responses into actionable...