Developing an AI framework to automatically detect shared decision-making in patient-doctor conversations
🤖 AI Summary
Current evaluation and improvement of patient-centered care are hindered by the lack of scalable, automated methods for quantifying Shared Decision Making (SDM) in clinical dialogues. To address this, we propose the first BERT-based language modeling framework that integrates Dialogue Alignment (CA) scoring with interpretability design for large-scale, automated SDM detection. Our method innovatively combines sentence segmentation, context-aware response pair construction, negative sampling, and Next Sentence Prediction (NSP) fine-tuning to generate multidimensional CA scores. Evaluated on real-world clinician–patient dialogue data, the BERT-base model achieves a recall@1 of 0.640. All CA scores demonstrate significant correlation (p < 0.01) with established clinical instruments—OPTION12 and the Decisional Conflict Scale (DCS)—validating efficacy, interpretability, and clinical applicability. This work overcomes the bottleneck of manual SDM assessment and establishes a novel paradigm for real-time SDM monitoring and quality improvement.
Application Category
📝 Abstract
Shared decision-making (SDM) is necessary to achieve patient-centred care. Currently no methodology exists to automatically measure SDM at scale. This study aimed to develop an automated approach to measure SDM by using language modelling and the conversational alignment (CA) score. A total of 157 video-recorded patient-doctor conversations from a randomized multi-centre trial evaluating SDM decision aids for anticoagulation in atrial fibrillations were transcribed and segmented into 42,559 sentences. Context-response pairs and negative sampling were employed to train deep learning (DL) models and fine-tuned BERT models via the next sentence prediction (NSP) task. Each top-performing model was used to calculate four types of CA scores. A random-effects analysis by clinician, adjusting for age, sex, race, and trial arm, assessed the association between CA scores and SDM outcomes: the Decisional Conflict Scale (DCS) and the Observing Patient Involvement in Decision-Making 12 (OPTION12) scores. p-values were corrected for multiple comparisons with the Benjamini-Hochberg method. Among 157 patients (34% female, mean age 70 SD 10.8), clinicians on average spoke more words than patients (1911 vs 773). The DL model without the stylebook strategy achieved a recall@1 of 0.227, while the fine-tuned BERTbase (110M) achieved the highest recall@1 with 0.640. The AbsMax (18.36 SE7.74 p=0.025) and Max CA (21.02 SE7.63 p=0.012) scores generated with the DL without stylebook were associated with OPTION12. The Max CA score generated with the fine-tuned BERTbase (110M) was associated with the DCS score (-27.61 SE12.63 p=0.037). BERT model sizes did not have an impact the association between CA scores and SDM. This study introduces an automated, scalable methodology to measure SDM in patient-doctor conversations through explainable CA scores, with potential to evaluate SDM strategies at scale.
Problem
Research questions and friction points this paper is trying to address.
Automatically detecting shared decision-making in patient-doctor conversations
Developing scalable methodology to measure SDM using language modeling
Associating conversational alignment scores with SDM clinical outcomes
Innovation
Methods, ideas, or system contributions that make the work stand out.
Used language modeling and conversational alignment scores
Employed deep learning and fine-tuned BERT models
Applied next sentence prediction with context-response pairs
🔎 Similar Papers
No similar papers found.
