Defining Patient-Oriented Natural Language Processing: A New Paradigm for Research and Development to Facilitate Adoption and Use by Medical Experts

Abstract

The capabilities of natural language processing (NLP) methods have expanded significantly in recent years, and progress has been particularly driven by advances in data science and machine learning. However, NLP is still largely underused in patient-oriented clinical research and care (POCRC). A key reason behind this is that clinical NLP methods are typically developed, optimized, and evaluated with narrowly focused data sets and tasks (eg, those for the detection of specific symptoms in free texts). Such research and development (R&D) approaches may be described as problem oriented, and the developed systems perform specialized tasks well. As standalone systems, however, they generally do not comprehensively meet the needs of POCRC. Thus, there is often a gap between the capabilities of clinical NLP methods and the needs of patient-facing medical experts. We believe that to increase the practical use of biomedical NLP, future R&D efforts need to be broadened to a new research paradigm—one that explicitly incorporates characteristics that are crucial for POCRC. We present our viewpoint about 4 such interrelated characteristics that can increase NLP systems’ suitability for POCRC (3 that represent NLP system properties and 1 associated with the R&D process)—(1) interpretability (the ability to explain system decisions), (2) patient centeredness (the capability to characterize diverse patients), (3) customizability (the flexibility for adapting to distinct settings, problems, and cohorts), and (4) multitask evaluation (the validation of system performance based on multiple tasks involving heterogeneous data sets). By using the NLP task of clinical concept detection as an example, we detail these characteristics and discuss how they may result in the increased uptake of NLP systems for POCRC.

Conversational Artificial Intelligence for Spinal Pain Questionnaire: Validation and User Satisfaction

“…In particular, imaging diagnosis, disease diagnosis, and prediction using clinical data and genomic Big data are medical fields of AI that currently receive the most attention [ 3 , 4 ]. AI technologies associated with natural language processing (NLU) are also being used in healthcare [ 5 ]. Conversational AI is an application of NLU and refers to AI technology that can talk to people, including chatbots or virtual agents [ 6 ].…”

Psychosocial Data

“…Such end-users may include broadly defined care teams who will be using NLP-derived psychosocial information, their patients whose care will be modified as a result, and epidemiologists and health services researchers seeking to estimate population-level statistics or draw causal inferences using such data. With early engagement of end-users to help identify and refine primary and secondary applications of NLP systems, new systems may overcome historical challenges with regards to poor interpretability, low uptake, and lack of customizability 9,10…”

“…Shortcomings of NLP systems and recommendations for improving their suitability and uptake for patient-oriented research and care have been previously described 9. Although extraction of psychosocial information from clinical notes using NLP may be accomplished with acceptable precision, NLP systems are often labor intensive to develop, difficult to interpret, and require additional effort to refine or generalize for new applications 9.…”

“…Systems risk reflecting the characteristics and perspectives of the providers documenting care and whose notes represent the input data for NLP systems. Testing and reporting on performance of NLP systems in multiple datasets from diverse organizations and populations can help address questions of robustness and aid clinicians and researchers in understanding the utility of such systems 9…”

“…Psychosocial factors that emerge from foundational research and have adequate utility for clinical and scientific purposes in a particular setting may be prioritized for integration into the EHR and research data infrastructure. The development of a robust NLP system that accomplishes this end requires substantial time and resources, primarily from the developers, although processing output from NLP systems also requires effort from providers 9. Systematic collection of structured data using validated instruments also requires time and resources, primarily from the care team and patient.…”