Analyzing patient experiences using natural language processing: development and validation of the artificial intelligence patient reported experience measure (AI-PREM).

BACKGROUND: Evaluating patients' experiences is essential when incorporating the patients' perspective in improving healthcare. Experiences are mainly collected using closed-ended questions, although the value of open-ended questions is widely recognized. Natural language processing (NLP) can automate the analysis of open-ended questions for an efficient approach to patient-centeredness. METHODS: We developed the Artificial Intelligence Patient-Reported Experience Measures (AI-PREM) tool, consisting of a new, open-ended questionnaire, an NLP pipeline to analyze the answers using sentiment analysis and topic modeling, and a visualization to guide physicians through the results. The questionnaire and NLP pipeline were iteratively developed and validated in a clinical context. RESULTS: The final AI-PREM consisted of five open-ended questions about the provided information, personal approach, collaboration between healthcare professionals, organization of care, and other experiences. The AI-PREM was sent to 867 vestibular schwannoma patients, 534 of which responded. The sentiment analysis model attained an F1 score of 0.97 for positive texts and 0.63 for negative texts. There was a 90% overlap between automatically and manually extracted topics. The visualization was hierarchically structured into three stages: the sentiment per question, the topics per sentiment and question, and the original patient responses per topic. CONCLUSIONS: The AI-PREM tool is a comprehensive method that combines a validated, open-ended questionnaire with a well-performing NLP pipeline and visualization. Thematically organizing and quantifying patient feedback reduces the time invested by healthcare professionals to evaluate and prioritize patient experiences without being confined to the limited answer options of closed-ended questions.

[Making a diagnosis with the aid of the internet in times of large language models]. / Diagnose stellen met online tools.

The internet is an excellent aid in making diagnoses. One can retrieve diagnostic information from a reliable source such as a continuously updated textbook or search specifically for a diagnosis in bibliographic databases such as PubMed. Entry of a patient summary in a general search engine or a large language model such as ChatGPT can suggest differential-diagnoses to the expert user,but one must be conscious of the limitations of current large language models. There seems little room left for the traditional differential-diagnosis generators. Ideally, large language models will be combined with transparent algorithms with which medical data can be retrieved, to create a new generation of diagnostic decision support systems.

Diagnosis Classification in the Emergency Room Using Natural Language Processing.

Diagnosis classification in the emergency room (ER) is a complex task. We developed several natural language processing classification models, looking both at the full classification task of 132 diagnostic categories and at several clinically applicable samples consisting of two diagnoses that are hard to distinguish.

Picture a data scientist: a call to action for increasing diversity, equity, and inclusion in the age of AI.

The lack of diversity, equity, and inclusion continues to hamper the artificial intelligence (AI) field and is especially problematic for healthcare applications. In this article, we expand on the need for diversity, equity, and inclusion, specifically focusing on the composition of AI teams. We call to action leaders at all levels to make team inclusivity and diversity the centerpieces of AI development, not the afterthought. These recommendations take into consideration mitigation at several levels, including outreach programs at the local level, diversity statements at the academic level, and regulatory steps at the federal level.

The digital scribe in clinical practice: a scoping review and research agenda.

The number of clinician burnouts is increasing and has been linked to a high administrative burden. Automatic speech recognition (ASR) and natural language processing (NLP) techniques may address this issue by creating the possibility of automating clinical documentation with a "digital scribe". We reviewed the current status of the digital scribe in development towards clinical practice and present a scope for future research. We performed a literature search of four scientific databases (Medline, Web of Science, ACL, and Arxiv) and requested several companies that offer digital scribes to provide performance data. We included articles that described the use of models on clinical conversational data, either automatically or manually transcribed, to automate clinical documentation. Of 20 included articles, three described ASR models for clinical conversations. The other 17 articles presented models for entity extraction, classification, or summarization of clinical conversations. Two studies examined the system's clinical validity and usability, while the other 18 studies only assessed their model's technical validity on the specific NLP task. One company provided performance data. The most promising models use context-sensitive word embeddings in combination with attention-based neural networks. However, the studies on digital scribes only focus on technical validity, while companies offering digital scribes do not publish information on any of the research phases. Future research should focus on more extensive reporting, iteratively studying technical validity and clinical validity and usability, and investigating the clinical utility of digital scribes.

Development and Usability of ADappt: Web-Based Tool to Support Clinicians, Patients, and Caregivers in the Diagnosis of Mild Cognitive Impairment and Alzheimer Disease.

BACKGROUND: As a result of advances in diagnostic testing in the field of Alzheimer disease (AD), patients are diagnosed in earlier stages of the disease, for example, in the stage of mild cognitive impairment (MCI). This poses novel challenges for a clinician during the diagnostic workup with regard to diagnostic testing itself, namely, which tests are to be performed, but also on how to engage patients in this decision and how to communicate test results. As a result, tools to support decision making and improve risk communication could be valuable for clinicians and patients. OBJECTIVE: The aim of this study was to present the design, development, and testing of a Web-based tool for clinicians in a memory clinic setting and to ascertain whether this tool can (1) facilitate the interpretation of biomarker results in individual patients with MCI regarding their risk of progression to dementia, (2) support clinicians in communicating biomarker test results and risks to MCI patients and their caregivers, and (3) support clinicians in a process of shared decision making regarding the diagnostic workup of AD. METHODS: A multiphase mixed-methods approach was used. Phase 1 consisted of a qualitative needs assessment among professionals, patients, and caregivers; phase 2, consisted of an iterative process of development and the design of the tool (ADappt); and phase 3 consisted of a quantitative and qualitative assessment of usability and acceptability of ADappt. Across these phases, co-creation was realized via a user-centered qualitative approach with clinicians, patients, and caregivers. RESULTS: In phase 1, clinicians indicated the need for risk calculation tools and visual aids to communicate test results to patients. Patients and caregivers expressed their needs for more specific information on their risk for developing AD and related consequences. In phase 2, we developed the content and graphical design of ADappt encompassing 3 modules: a risk calculation tool, a risk communication tool including a summary sheet for patients and caregivers, and a conversation starter to support shared decision making regarding the diagnostic workup. In phase 3, ADappt was considered to be clear and user-friendly. CONCLUSIONS: Clinicians in a memory clinic setting can use ADappt, a Web-based tool, developed using multiphase design and co-creation, for support that includes an individually tailored interpretation of biomarker test results, communication of test results and risks to patients and their caregivers, and shared decision making on diagnostic testing.

Disclosure of amyloid positron emission tomography results to individuals without dementia: a systematic review.

BACKGROUND: Disclosure of amyloid positron emission tomography (PET) results to individuals without dementia has become standard practice in secondary prevention trials and also increasingly occurs in clinical practice. However, this is controversial given the current lack of understanding of the predictive value of a PET result at the individual level and absence of disease-modifying treatments. In this study, we systematically reviewed the literature on the disclosure of amyloid PET in cognitively normal (CN) individuals and patients with mild cognitive impairment (MCI) in both research and clinical settings. METHODS: We performed a systematic literature search of four scientific databases. Two independent reviewers screened the identified records and selected relevant articles. Included articles presented either empirical data or theoretical data (i.e. arguments in favor or against amyloid status disclosure). Results from the theoretical data were aggregated and presented per theme. RESULTS: Of the seventeen included studies, eleven reported empirical data and six provided theoretical arguments. There was a large variation in the design of the empirical studies, which were almost exclusively in the context of cognitively normal trial participants, comprising only two prospective cohort studies quantitatively assessing the psychological impact of PET result disclosure which showed a low risk of psychological harm after disclosure. Four studies showed that both professionals and cognitively normal individuals support amyloid PET result disclosure and underlined the need for clear disclosure protocols. From the articles presenting theoretical data, we identified 51 'pro' and 'contra' arguments. Theoretical arguments in favor or against disclosure were quite consistent across population groups and settings. Arguments against disclosure focused on the principle of non-maleficence, whereas its psychological impact and predictive value is unknown. Important arguments in favor of amyloid disclosure are the patients right to know (patient autonomy) and that it enables early future decision making. DISCUSSION: Before amyloid PET result disclosure in individuals without dementia in a research or clinical setting is ready for widespread application, more research is needed about its psychological impact, and its predictive value at an individual level. Finally, communication materials and strategies to support disclosure of amyloid PET results should be further developed and prospectively evaluated.

Association of Amyloid Positron Emission Tomography With Changes in Diagnosis and Patient Treatment in an Unselected Memory Clinic Cohort: The ABIDE Project.

Importance: Previous studies have evaluated the diagnostic effect of amyloid positron emission tomography (PET) in selected research cohorts. However, these research populations do not reflect daily practice, thus hampering clinical implementation of amyloid imaging. Objective: To evaluate the association of amyloid PET with changes in diagnosis, diagnostic confidence, treatment, and patients' experiences in an unselected memory clinic cohort. Design, Setting, and Participants: Amyloid PET using fluoride-18 florbetaben was offered to 866 patients who visited the tertiary memory clinic at the VU University Medical Center between January 2015 and December 2016 as part of their routine diagnostic dementia workup. Of these patients, 476 (55%) were included, 32 (4%) were excluded, and 358 (41%) did not participate. To enrich this sample, 31 patients with mild cognitive impairment from the University Medical Center Utrecht memory clinic were included. For each patient, neurologists determined a preamyloid and postamyloid PET diagnosis that existed of both a clinical syndrome (dementia, mild cognitive impairment, or subjective cognitive decline) and a suspected etiology (Alzheimer disease [AD] or non-AD), with a confidence level ranging from 0% to 100%. In addition, the neurologist determined patient treatment in terms of ancillary investigations, medication, and care. Each patient received a clinical follow-up 1 year after being scanned. Main Outcomes and Measures: Primary outcome measures were post-PET changes in diagnosis, diagnostic confidence, and patient treatment. Results: Of the 507 patients (mean [SD] age, 65 (8) years; 201 women [39%]; mean [SD] Mini-Mental State Examination score, 25 [4]), 164 (32%) had AD dementia, 70 (14%) non-AD dementia, 114 (23%) mild cognitive impairment, and 159 (31%) subjective cognitive decline. Amyloid PET results were positive for 242 patients (48%). The suspected etiology changed for 125 patients (25%) after undergoing amyloid PET, more often due to a negative (82 of 265 [31%]) than a positive (43 of 242 [18%]) PET result (P < .01). Post-PET changes in suspected etiology occurred more frequently in patients older (>65 years) than younger (<65 years) than the typical age at onset of 65 years (74 of 257 [29%] vs 51 of 250 [20%]; P < .05). Mean diagnostic confidence (SD) increased from 80 (13) to 89 (13%) (P < .001). In 123 patients (24%), there was a change in patient treatment post-PET, mostly related to additional investigations and therapy. Conclusions and Relevance: This prospective diagnostic study provides a bridge between validating amyloid PET in a research setting and implementing this diagnostic tool in daily clinical practice. Both amyloid-positive and amyloid-negative results had substantial associations with changes in diagnosis and treatment, both in patients with and without dementia.