Challenges of developing a digital scribe to reduce clinical documentation burden

Impact of a Digital Scribe System on Clinical Documentation Time and Quality: Usability Study

BACKGROUND

Physicians spend approximately half of their time on administrative tasks, which is one of the leading causes of physician burnout and decreased work satisfaction. The implementation of natural language processing-assisted clinical documentation tools may provide a solution.

OBJECTIVE

This study investigates the impact of a commercially available Dutch digital scribe system on clinical documentation efficiency and quality.

METHODS

Medical students with experience in clinical practice and documentation (n=22) created a total of 430 summaries of mock consultations and recorded the time they spent on this task. The consultations were summarized using 3 methods: manual summaries, fully automated summaries, and automated summaries with manual editing. We then randomly reassigned the summaries and evaluated their quality using a modified version of the Physician Documentation Quality Instrument (PDQI-9). We compared the differences between the 3 methods in descriptive statistics, quantitative text metrics (word count and lexical diversity), the PDQI-9, Recall-Oriented Understudy for Gisting Evaluation scores, and BERTScore.

RESULTS

The median time for manual summarization was 202 seconds against 186 seconds for editing an automatic summary. Without editing, the automatic summaries attained a poorer PDQI-9 score than manual summaries (median PDQI-9 score 25 vs 31, P<.001, ANOVA test). Automatic summaries were found to have higher word counts but lower lexical diversity than manual summaries (P<.001, independent t test). The study revealed variable impacts on PDQI-9 scores and summarization time across individuals. Generally, students viewed the digital scribe system as a potentially useful tool, noting its ease of use and time-saving potential, though some criticized the summaries for their greater length and rigid structure.

CONCLUSIONS

This study highlights the potential of digital scribes in improving clinical documentation processes by offering a first summary draft for physicians to edit, thereby reducing documentation time without compromising the quality of patient records. Furthermore, digital scribes may be more beneficial to some physicians than to others and could play a role in improving the reusability of clinical documentation. Future studies should focus on the impact and quality of such a system when used by physicians in clinical practice.

Balancing act: the complex role of artificial intelligence in addressing burnout and healthcare workforce dynamics

Burnout and workforce attrition present pressing global challenges in healthcare, severely impacting the quality of patient care and the sustainability of health systems worldwide. Artificial intelligence (AI) has immense potential to reduce the administrative and cognitive burdens that contribute to burnout through innovative solutions such as digital scribes, automated billing and advanced data management systems. However, these innovations also carry significant risks, including potential job displacement, increased complexity of medical information and cases, and the danger of diminishing clinical skills. To fully leverage AI's potential in healthcare, it is essential to prioritise AI technologies that align with stakeholder values and emphasise efforts to re-humanise medical practice. By doing so, AI can contribute to restoring a sense of purpose, fulfilment and efficacy among healthcare workers, reinforcing their essential role as caregivers, rather than distancing them from these core professional attributes.

Assessing the Effectiveness of Automatic Speech Recognition Technology in Emergency Medicine Settings: A Comparative Study of Four AI-powered Engines

Purpose Cutting-edge automatic speech recognition (ASR) technology holds significant promise in transcribing and recognizing medical information during patient encounters, thereby enabling automatic and real-time clinical documentation, which could significantly alleviate care clinicians' burdens. Nevertheless, the performance of current-generation ASR technology in analyzing conversations in noisy and dynamic medical settings, such as prehospital or Emergency Medical Services (EMS), lacks sufficient validation. This study explores the current technological limitations and future potential of deploying ASR technology for clinical documentation in fast-paced and noisy medical settings such as EMS. Methods In this study, we evaluated four ASR engines, including Google Speech-to-Text Clinical Conversation, OpenAI Speech-to-Text, Amazon Transcribe Medical, and Azure Speech-to-Text engine. The empirical data used for evaluation were 40 EMS simulation recordings. The transcribed texts were analyzed for accuracy against 23 Electronic Health Records (EHR) categories of EMS. The common types of errors in transcription were also analyzed. Results Among all four ASR engines, Google Speech-to-Text Clinical Conversation performed the best. Among all EHR categories, better performance was observed in categories "mental state" (F1 = 1.0), "allergies" (F1 = 0.917), "past medical history" (F1 = 0.804), "electrolytes" (F1 = 1.0), and "blood glucose level" (F1 = 0.813). However, all four ASR engines demonstrated low performance in transcribing certain critical categories, such as "treatment" (F1 = 0.650) and "medication" (F1 = 0.577). Conclusion Current ASR solutions fall short in fully automating the clinical documentation in EMS setting. Our findings highlight the need for further improvement and development of automated clinical documentation technology to improve recognition accuracy in time-critical and dynamic medical settings.

Natural Language Processing in medicine and ophthalmology: A review for the 21st-century clinician

Natural Language Processing (NLP) is a subfield of artificial intelligence that focuses on the interaction between computers and human language, enabling computers to understand, generate, and derive meaning from human language. NLP's potential applications in the medical field are extensive and vary from extracting data from Electronic Health Records -one of its most well-known and frequently exploited uses- to investigating relationships among genetics, biomarkers, drugs, and diseases for the proposal of new medications. NLP can be useful for clinical decision support, patient monitoring, or medical image analysis. Despite its vast potential, the real-world application of NLP is still limited due to various challenges and constraints, meaning that its evolution predominantly continues within the research domain. However, with the increasingly widespread use of NLP, particularly with the availability of large language models, such as ChatGPT, it is crucial for medical professionals to be aware of the status, uses, and limitations of these technologies.

Evaluation of a Digital Scribe: Conversation Summarization for Emergency Department Consultation Calls

OBJECTIVE

We present a proof-of-concept digital scribe system as an Emergency Department (ED) consultation call-based clinical conversation summarization pipeline to support clinical documentation, and report its performance.

MATERIALS AND METHODS

We use four pre-trained large language models to establish the digital scribe system: T5-small, T5-base, PEGASUS-PubMed, and BART-Large-CNN via zero-shot and fine-tuning approaches. Our dataset includes 100 referral conversations among ED clinicians and medical records. We report the ROUGE-1, ROUGE-2, and ROUGE-L to compare model performance. In addition, we annotated transcriptions to assess the quality of generated summaries.

RESULTS

The fine-tuned BART-Large-CNN model demonstrates greater performance in summarization tasks with the highest ROUGE scores (F1ROUGE-1=0.49, F1ROUGE-2=0.23, F1ROUGE-L=0.35) scores. In contrast, PEGASUS-PubMed lags notably (F1ROUGE-1=0.28, F1ROUGE-2=0.11, F1ROUGE-L=0.22). BART-Large-CNN's performance decreases by more than 50% with the zero-shot approach. Annotations show that BART-Large-CNN performs 71.4% recall in identifying key information and a 67.7% accuracy rate.

DISCUSSION

The BART-Large-CNN model demonstrates a high level of understanding of clinical dialogue structure, indicated by its performance with and without fine-tuning. Despite some instances of high recall, there is variability in the model's performance, particularly in achieving consistent correctness, suggesting room for refinement. The model's recall ability varies across different information categories.

CONCLUSION

The study provides evidence towards the potential of AI-assisted tools in assisting clinical documentation. Future work is suggested on expanding the research scope with additional language models and hybrid approaches, and comparative analysis to measure documentation burden and human factors.

Transforming Healthcare with AI: Promises, Pitfalls, and Pathways Forward

This perspective paper provides a comprehensive examination of artificial intelligence (AI) in healthcare, focusing on its transformative impact on clinical practices, decision-making, and physician-patient relationships. By integrating insights from evidence, research, and real-world examples, it offers a balanced analysis of AI's capabilities and limitations, emphasizing its role in streamlining administrative processes, enhancing patient care, and reducing physician burnout while maintaining a human-centric approach in medicine. The research underscores AI's capacity to augment clinical decision-making and improve patient interactions, but it also highlights the variable impact of AI in different healthcare settings. The need for context-specific adaptations and careful integration of AI technologies into existing healthcare workflows is emphasized to maximize benefits and minimize unintended consequences. Significant attention is given to the implications of AI on the roles and competencies of healthcare professionals. The emergence of AI necessitates new skills in data literacy and technology use, prompting a shift in educational curricula towards digital health and AI training. Ethical considerations are a pivotal aspect of the discussion. The paper explores the challenges posed by data privacy concerns, algorithmic biases, and ensuring equitable access to AI-driven healthcare. It advocates for the development of comprehensive ethical frameworks and ongoing research to guide the responsible use of AI in healthcare. Conclusively, the paper advocates for a balanced approach to AI adoption in healthcare, highlighting the importance of ongoing research, strategic implementation, and the synergistic combination of human expertise with AI technologies for optimal patient care.

The impact of nuance DAX ambient listening AI documentation: a cohort study

OBJECTIVE

To assess the impact of the use of an ambient listening/digital scribing solution (Nuance Dragon Ambient eXperience (DAX)) on caregiver engagement, time spent on Electronic Health Record (EHR) including time after hours, productivity, attributed panel size for value-based care providers, documentation timeliness, and Current Procedural Terminology (CPT) submissions.

MATERIALS AND METHODS

We performed a peer-matched controlled cohort study from March to September 2022 to evaluate the impact of DAX in outpatient clinics in an integrated healthcare system. Primary outcome measurements included provider engagement survey results, reported patient safety events related to DAX use, patients' Likelihood to Recommend score, number of patients opting out of ambient listening, change in work relative values units, attributed value-based primary care panel size, documentation completion and CPT code submission deficiency rates, and note turnaround time.

RESULTS

A total of 99 providers representing 12 specialties enrolled in the study; 76 matched control group providers were included for analysis. Median utilization of DAX was 47% among active participants. We found positive trends in provider engagement, while non-participants saw worsening engagement and no practical change in productivity. There was a statistically significant worsening of after-hours EHR. There was no quantifiable effect on patient safety.

DISCUSSION

Nuance DAX use showed positive trends in provider engagement at no risk to patient safety, experience, or clinical documentation. There were no significant benefits to patient experience, documentation, or measures of provider productivity.

CONCLUSION

Our results highlight the potential of ambient dictation as a tool for improving the provider experience. Head-to-head comparisons of EHR documentation efficiency training are needed.

Charting Tomorrow's Healthcare: A Traditional Literature Review for an Artificial Intelligence-Driven Future

Electronic health record (EHR) systems have developed over time in parallel with general advancements in mainstream technology. As artificially intelligent (AI) systems rapidly impact multiple societal sectors, it has become apparent that medicine is not immune from the influences of this powerful technology. Particularly appealing is how AI may aid in improving healthcare efficiency with note-writing automation. This literature review explores the current state of EHR technologies in healthcare, specifically focusing on possibilities for addressing EHR challenges through the automation of dictation and note-writing processes with AI integration. This review offers a broad understanding of existing capabilities and potential advancements, emphasizing innovations such as voice-to-text dictation, wearable devices, and AI-assisted procedure note dictation. The primary objective is to provide researchers with valuable insights, enabling them to generate new technologies and advancements within the healthcare landscape. By exploring the benefits, challenges, and future of AI integration, this review encourages the development of innovative solutions, with the goal of enhancing patient care and healthcare delivery efficiency.

Development and Evaluation of a Digital Scribe: Conversation Summarization Pipeline for Emergency Department Counseling Sessions towards Reducing Documentation Burden

Objective

We present a proof-of-concept digital scribe system as an ED clinical conversation summarization pipeline and report its performance.

Materials and Methods

We use four pre-trained large language models to establish the digital scribe system: T5-small, T5-base, PEGASUS-PubMed, and BART-Large-CNN via zero-shot and fine-tuning approaches. Our dataset includes 100 referral conversations among ED clinicians and medical records. We report the ROUGE-1, ROUGE-2, and ROUGE-L to compare model performance. In addition, we annotated transcriptions to assess the quality of generated summaries.

Results

The fine-tuned BART-Large-CNN model demonstrates greater performance in summarization tasks with the highest ROUGE scores (F1ROUGE-1=0.49, F1ROUGE-2=0.23, F1ROUGE-L=0.35) scores. In contrast, PEGASUS-PubMed lags notably (F1ROUGE-1=0.28, F1ROUGE-2=0.11, F1ROUGE-L=0.22). BART-Large-CNN's performance decreases by more than 50% with the zero-shot approach. Annotations show that BART-Large-CNN performs 71.4% recall in identifying key information and a 67.7% accuracy rate.

Discussion

The BART-Large-CNN model demonstrates a high level of understanding of clinical dialogue structure, indicated by its performance with and without fine-tuning. Despite some instances of high recall, there is variability in the model's performance, particularly in achieving consistent correctness, suggesting room for refinement. The model's recall ability varies across different information categories.

Conclusion

The study provides evidence towards the potential of AI-assisted tools in reducing clinical documentation burden. Future work is suggested on expanding the research scope with larger language models, and comparative analysis to measure documentation efforts and time.

I'm not burned out. This is how I write notes

Objectives

We describe an automated transcription system that addresses many documentation problems and fits within scheduled clinical hours.

Materials and methods

During visits, the provider listens to the patient while maintaining eye contact and making brief notes on paper. Immediately after the visit conclusion and before the next, the provider makes a short voice recording on a smartphone which is transmitted to the system. The system uses a public domain general language model, and a hypertuned provider-specific language model that is iteratively refined as each produced note is edited by the physician, followed by final automated processing steps to add any templated text to the note.

Results

The provider leaves the clinic having completed all voice files, median duration 3.4 minutes. Created notes are formatted as preferred and are a median of 363 words (range 125-1175).

Discussion

This approach permits documentation to occur almost entirely within scheduled clinic hours, without copy-forward errors, and without interference with patient-provider interaction.

Conclusion

Though no documentation method is likely to appeal to all, this approach may appeal to many physicians and avoid many current problems with documentation.

A method to automate the discharge summary hospital course for neurology patients

OBJECTIVE

Generation of automated clinical notes has been posited as a strategy to mitigate physician burnout. In particular, an automated narrative summary of a patient's hospital stay could supplement the hospital course section of the discharge summary that inpatient physicians document in electronic health record (EHR) systems. In the current study, we developed and evaluated an automated method for summarizing the hospital course section using encoder-decoder sequence-to-sequence transformer models.

MATERIALS AND METHODS

We fine-tuned BERT and BART models and optimized for factuality through constraining beam search, which we trained and tested using EHR data from patients admitted to the neurology unit of an academic medical center.

RESULTS

The approach demonstrated good ROUGE scores with an R-2 of 13.76. In a blind evaluation, 2 board-certified physicians rated 62% of the automated summaries as meeting the standard of care, which suggests the method may be useful clinically.

DISCUSSION AND CONCLUSION

To our knowledge, this study is among the first to demonstrate an automated method for generating a discharge summary hospital course that approaches a quality level of what a physician would write.

Creating work-life balance among physicians in the age of digitalization: the role of self-consciousness and communication - a qualitative study

BACKGROUND

Besides the positive effects of using digital health solutions, digitalization can affect the healthcare worker burnout. The ability to coordinate different aspects of life (WLB) also plays a significant role in the development of burnout among medical workers. The aim of our study is to show, through qualitative interviews, the impact of digitalization on work-life balance in Hungarian physicians.

METHODS

62 semi-structured interviews were conducted between October 2021 and June 2022, of which, a total of 31 interviews were used for the analysis, which were all related to the theme of work-life balance. Purposive sampling and inductive thematic approach were used to collect and analyse the data and identify patterns of the themes.

RESULTS

Based on this analysis, 5 main themes emerged: (1) the use of digital health tools, (2) Impact of digital tools on everyday work, (3) Work-life balance, (4) Setting and maintaining work-life boundaries, (5) Potential solutions. With the spread of digital communication, most of the respondents feel that their working hours increased even at the expense of their private life. The majority considers constant availability as a serious problem, however, several physicians indicated that as a result of a learning curve, they are able to change and set the necessary boundaries. Respondents were divided on whether or not they were successful in setting and maintaining boundaries. The 2 most important factors of establishing WLB in a digital age are self-consciousness and communication. However, these skills are not self-evident: the responses also show that in many cases there is a need for external support, but also for health professionals to actively reflect from time to time on their role as healers and their relationship with technology.

CONCLUSION

Basic principles and tools for establishing successful digital work-life balance in healthcare should be involved in the training curriculum of future physicians and healthcare professionals, while institutions should elaborate specific policies to include digital work-life balance in the institutional setting, as part of the preventive measures against burnout.

Machine learning-based speech recognition system for nursing documentation - A pilot study

PURPOSE

Considering the significant workload of nursing tasks, enhancing the efficiency of nursing documentation is imperative. This study aimed to evaluate the effectiveness of a machine learning-based speech recognition (SR) system in reducing the clinical workload associated with typing nursing records, implemented in a psychiatry ward.

METHODS

The study was conducted between July 15, 2020, and June 30, 2021, at Cheng Hsin General Hospital in Taiwan. The language corpus was based on the existing records from the hospital nursing information system. The participating ward's nursing activities, clinical conversation, and accent data were also collected for deep learning-based SR-engine training. A total of 21 nurses participated in the evaluation of the SR system. Documentation time and recognition error rate were evaluated in parallel between SR-generated records and keyboard entry over 4 sessions. Any differences between SR and keyboard transcriptions were regarded as SR errors.

FINDINGS

A total of 200 data were obtained from four evaluation sessions, 10 participants were asked to use SR and keyboard entry in parallel at each session and 5 entries were collected from each participant. Overall, the SR system processed 30,112 words in 32,456 s (0.928 words per second). The mean accuracy of the SR system improved after each session, from 87.06% in 1st session to 95.07% in 4th session.

CONCLUSION

This pilot study demonstrated our machine learning-based SR system has an acceptable recognition accuracy and may reduce the burden of documentation for nurses. However, the potential error with the SR transcription should continually be recognized and improved. Further studies are needed to improve the integration of SR in digital documentation of nursing records, in terms of both productivity and accuracy across different clinical specialties.

Aci-bench: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation

Recent immense breakthroughs in generative models such as in GPT4 have precipitated re-imagined ubiquitous usage of these models in all applications. One area that can benefit by improvements in artificial intelligence (AI) is healthcare. The note generation task from doctor-patient encounters, and its associated electronic medical record documentation, is one of the most arduous time-consuming tasks for physicians. It is also a natural prime potential beneficiary to advances in generative models. However with such advances, benchmarking is more critical than ever. Whether studying model weaknesses or developing new evaluation metrics, shared open datasets are an imperative part of understanding the current state-of-the-art. Unfortunately as clinic encounter conversations are not routinely recorded and are difficult to ethically share due to patient confidentiality, there are no sufficiently large clinic dialogue-note datasets to benchmark this task. Here we present the Ambient Clinical Intelligence Benchmark (ACI-BENCH) corpus, the largest dataset to date tackling the problem of AI-assisted note generation from visit dialogue. We also present the benchmark performances of several common state-of-the-art approaches.

Transitioning Cognitive Aids into Decision Support Platforms: Requirements and Design Guidelines

Digital cognitive aids have the potential to serve as clinical decision support platforms, triggering alerts about process delays and recommending interventions. In this mixed-methods study, we examined how a digital checklist for pediatric trauma resuscitation could trigger decision support alerts and recommendations. We identified two criteria that cognitive aids must satisfy to support these alerts: (1) context information must be entered in a timely, accurate, and standardized manner, and (2) task status must be accurately documented. Using co-design sessions and near-live simulations, we created two checklist features to satisfy these criteria: a form for entering the pre-hospital information and a progress slider for documenting the progression of a multi-step task. We evaluated these two features in the wild, contributing guidelines for designing these features on cognitive aids to support alerts and recommendations in time- and safety-critical scenarios.

"Mm-hm," "Uh-uh": are non-lexical conversational sounds deal breakers for the ambient clinical documentation technology?

OBJECTIVES

Ambient clinical documentation technology uses automatic speech recognition (ASR) and natural language processing (NLP) to turn patient-clinician conversations into clinical documentation. It is a promising approach to reducing clinician burden and improving documentation quality. However, the performance of current-generation ASR remains inadequately validated. In this study, we investigated the impact of non-lexical conversational sounds (NLCS) on ASR performance. NLCS, such as Mm-hm and Uh-uh, are commonly used to convey important information in clinical conversations, for example, Mm-hm as a "yes" response from the patient to the clinician question "are you allergic to antibiotics?"

MATERIALS AND METHODS

In this study, we evaluated 2 contemporary ASR engines, Google Speech-to-Text Clinical Conversation ("Google ASR"), and Amazon Transcribe Medical ("Amazon ASR"), both of which have their language models specifically tailored to clinical conversations. The empirical data used were from 36 primary care encounters. We conducted a series of quantitative and qualitative analyses to examine the word error rate (WER) and the potential impact of misrecognized NLCS on the quality of clinical documentation.

RESULTS

Out of a total of 135 647 spoken words contained in the evaluation data, 3284 (2.4%) were NLCS. Among these NLCS, 76 (0.06% of total words, 2.3% of all NLCS) were used to convey clinically relevant information. The overall WER, of all spoken words, was 11.8% for Google ASR and 12.8% for Amazon ASR. However, both ASR engines demonstrated poor performance in recognizing NLCS: the WERs across frequently used NLCS were 40.8% (Google) and 57.2% (Amazon), respectively; and among the NLCS that conveyed clinically relevant information, 94.7% and 98.7%, respectively.

DISCUSSION AND CONCLUSION

Current ASR solutions are not capable of properly recognizing NLCS, particularly those that convey clinically relevant information. Although the volume of NLCS in our evaluation data was very small (2.4% of the total corpus; and for NLCS that conveyed clinically relevant information: 0.06%), incorrect recognition of them could result in inaccuracies in clinical documentation and introduce new patient safety risks.

Automatic documentation of professional health interactions: A systematic review

Electronic systems are increasingly present in the healthcare system and are often related to improved medical care. However, the widespread use of these technologies ended up building a relationship of dependence that can disrupt the doctor-patient relationship. In this context, digital scribes are automated clinical documentation systems that capture the physician-patient conversation and then generate the documentation for the appointment, enabling the physician to engage with the patient entirely. We have performed a systematic literature review on intelligent solutions for automatic speech recognition (ASR) with automatic documentation during a medical interview. The scope included only original research on systems that could detect speech and transcribe it in a natural and structured fashion simultaneously with the doctor-patient interaction, excluding speech-to-text-only technologies. The search resulted in a total of 1995 titles, with eight articles remaining after filtering for the inclusion and exclusion criteria. The intelligent models mainly consisted of an ASR system with natural language processing capability, a medical lexicon, and structured text output. None of the articles had a commercially available product at the time of the publication and reported limited real-life experience. So far, none of the applications has been prospectively validated and tested in large-scale clinical studies. Nonetheless, these first reports suggest that automatic speech recognition may be a valuable tool in the future to facilitate medical registration in a faster and more reliable manner. Improving transparency, accuracy, and empathy could drastically change how patients and doctors experience a medical visit. Unfortunately, clinical data on the usability and benefits of such applications is almost non-existent. We believe that future work in this area is necessary and needed.

Adaptation of Autoencoder for Sparsity Reduction From Clinical Notes Representation Learning

When dealing with clinical text classification on a small dataset, recent studies have confirmed that a well-tuned multilayer perceptron outperforms other generative classifiers, including deep learning ones. To increase the performance of the neural network classifier, feature selection for the learning representation can effectively be used. However, most feature selection methods only estimate the degree of linear dependency between variables and select the best features based on univariate statistical tests. Furthermore, the sparsity of the feature space involved in the learning representation is ignored.

GOAL

Our aim is, therefore, to access an alternative approach to tackle the sparsity by compressing the clinical representation feature space, where limited French clinical notes can also be dealt with effectively.

METHODS

This study proposed an autoencoder learning algorithm to take advantage of sparsity reduction in clinical note representation. The motivation was to determine how to compress sparse, high-dimensional data by reducing the dimension of the clinical note representation feature space. The classification performance of the classifiers was then evaluated in the trained and compressed feature space.

RESULTS

The proposed approach provided overall performance gains of up to 3% for each test set evaluation. Finally, the classifier achieved 92% accuracy, 91% recall, 91% precision, and 91% f1-score in detecting the patient's condition. Furthermore, the compression working mechanism and the autoencoder prediction process were demonstrated by applying the theoretic information bottleneck framework. Clinical and Translational Impact Statement- An autoencoder learning algorithm effectively tackles the problem of sparsity in the representation feature space from a small clinical narrative dataset. Significantly, it can learn the best representation of the training data because of its lossless compression capacity compared to other approaches. Consequently, its downstream classification ability can be significantly improved, which cannot be done using deep learning models.

Using less keystrokes to achieve high top-1 accuracy in Chinese clinical text entry

Background

As a routine task, physicians spend substantial time and keystrokes on text entry. Documentation burden is increasingly associated with physician burnout. Predicting at top-1 with less keystrokes (TLKs) is a hot topic for smart text entry. In Western countries, contextual autocomplete is deployed to alleviate the burden. Chinese text entry is intercepted by input method engines (IMEs), which cut off suggestions from electronic health records (EHRs).

Objective

To explore a user-friendly approach to make text entry easier and faster for Chinese physicians.

Methods

Physicians were shadowed to uncover the real-word input behaviors. System logs were collected for behavior validation and then used for context-based learning. An in-line web-based popup layer was proposed to hold the best suggestion from EHRs. Keystrokes per character and TLK rate were evaluated quantitatively. Questionnaires were used for qualitative assessment. Nine hundred fifty-two physicians were enrolled in a field testing.

Results

14 facilitators and 17 barriers related to IMEs were identified after shadowing. With system logs, physicians tended to split long words into short units, which were 1-4 in length. 81.7% of these units were disyllables. Compared to the control group, the intervention group improved TLK rate by 40.3% (p < .0001), and reduced keystrokes per character by 48.3% (p < .0001). Survey results also promised positive feedback from physicians.

Conclusions

Keystroke burden and frequent choice reaction time challenge Chinese physicians for text entry. The proposed system demonstrates an approach to alleviate the burden. Contextual information is easily retrieved and it further helps improve the top-1 accuracy, with a smaller number of keystrokes. While positive feedback is received, it promises a benefit to protect patient privacy.

Comparison of clinical note quality between an automated digital intake tool and the standard note in the emergency department

BACKGROUND

Medical encounters require an efficient and focused history of present illness (HPI) to create differential diagnoses and guide diagnostic testing and treatment. Our aim was to compare the HPI of notes created by an automated digital intake tool versus standard medical notes created by clinicians.

METHODS

Prospective trial in a quaternary academic Emergency Department (ED). Notes were compared using the 5-point Physician Documentation Quality Instrument (PDQI-9) scale and the Centers for Medicare & Medicaid Services (CMS) level of complexity index. Reviewers were board certified emergency medicine physicians blinded to note origin. Reviewers received training and calibration prior to note assessments. A difference of 1 point was considered clinically significant. Analysis included McNemar's (binary), Wilcoxon-rank (Likert), and agreement with Cohen's Kappa.

RESULTS

A total of 148 ED medical encounters were charted by both digital note and standard clinical note. The ability to capture patient information was assessed through comparison of note content across paired charts (digital-standard note on the same patient), as well as scores given by the reviewers. Reviewer agreement was kappa 0.56 (CI 0.49-0.64), indicating moderate level of agreement between reviewers scoring the same patient chart. Considering all 18 questions across PDQI-9 and CMS scales, the average agreement between standard clinical note and digital note was 54.3% (IQR 44.4-66.7%). There was a moderate level of agreement between content of standard and digital notes (kappa 0.54, 95%CI 0.49-0.60). The quality of the digital note was within the 1 point clinically significant difference for all of the attributes, except for conciseness. Digital notes had a higher frequency of CMS severity elements identified.

CONCLUSION

Digitally generated clinical notes had moderate agreement compared to standard clinical notes and within the one point clinically significant difference except for the conciseness attribute. Digital notes more reliably documented billing components of severity. The use of automated notes should be further explored to evaluate its utility in facilitating documentation of patient encounters.

Management Opportunities and Challenges After Achieving Widespread Health System Digitization

The adoption of electronic health records (EHRs) and digitization of health data over the past decade is ushering in the next generation of digital health tools that leverage artificial intelligence (AI) to improve varied aspects of health system performance. The decade ahead is therefore shaping up to be one in which digital health becomes even more at the forefront of health care delivery - demanding the time, attention, and resources of health care leaders and frontline staff, and becoming inextricably linked with all dimensions of health care delivery. In this chapter, we look back and look ahead. There are substantive lessons learned from the first era of large-scale adoption of enterprise EHRs and ongoing challenges that organizations are wrestling with - particularly related to the tension between standardization and flexibility/customization of EHR systems and the processes they support. Managing this tension during efforts to implement and optimize enterprise systems is perhaps the core challenge of the past decade, and one that has impeded consistent realization of value from initial EHR investments. We describe these challenges, how they manifest, and organizational strategies to address them, with a specific focus on alignment with broader value-based care transformation. We then look ahead to the AI wave - the massive number of applications of AI to health care delivery, the expected benefits, the risks and challenges, and approaches that health systems can consider to realize the benefits while avoiding the risks.

Keyword-augmented and semi-automatic generation of FESS reports: a proof-of-concept study

Introduction

Surgical reports are usually written after a procedure and must often be reproduced from memory. Thus, this is an error-prone, and time-consuming task which increases the workload of physicians. In this proof-of-concept study, we developed and evaluated a software tool using Artificial Intelligence (AI) for semi-automatic intraoperative generation of surgical reports for functional endoscopic sinus surgery (FESS).

Materials and methods

A vocabulary of keywords for developing a neural language model was created. With an encoder-decoder-architecture, artificially coherent sentence structures, as they would be expected in general operation reports, were generated. A first set of 48 conventional operation reports were used for model training. After training, the reports were generated again and compared to those before training. Established metrics were used to measure optimization of the model objectively. A cohort of 16 physicians corrected and evaluated three randomly selected, generated reports in four categories: “quality of the generated operation reports,” “time-saving,” “clinical benefits” and “comparison with the conventional reports.” The corrections of the generated reports were counted and categorized.

Results

Objective parameters showed improvement in performance after training the language model (p < 0.001). 27.78% estimated a timesaving of 1–15 and 61.11% of 16–30 min per day. 66.66% claimed to see a clinical benefit and 61.11% a relevant workload reduction. Similarity in content between generated and conventional reports was seen by 33.33%, similarity in form by 27.78%. 66.67% would use this tool in the future. An average of 23.25 ± 12.5 corrections was needed for a subjectively appropriate surgery report.

Conclusion

The results indicate existing limitations of applying deep learning to text generation of operation reports and show a high acceptance by the physicians. By taking over this time-consuming task, the tool could reduce workload, optimize clinical workflows and improve the quality of patient care. Further training of the language model is needed.

Expectations for Artificial Intelligence (AI) in Psychiatry

PURPOSE OF REVIEW

Artificial intelligence (AI) is often presented as a transformative technology for clinical medicine even though the current technology maturity of AI is low. The purpose of this narrative review is to describe the complex reasons for the low technology maturity and set realistic expectations for the safe, routine use of AI in clinical medicine.

RECENT FINDINGS

For AI to be productive in clinical medicine, many diverse factors that contribute to the low maturity level need to be addressed. These include technical problems such as data quality, dataset shift, black-box opacity, validation and regulatory challenges, and human factors such as a lack of education in AI, workflow changes, automation bias, and deskilling. There will also be new and unanticipated safety risks with the introduction of AI. The solutions to these issues are complex and will take time to discover, develop, validate, and implement. However, addressing the many problems in a methodical manner will expedite the safe and beneficial use of AI to augment medical decision making in psychiatry.

Capturing Essentials in Wound Photography Past, Present, and Future: A Proposed Algorithm for Standardization

GENERAL PURPOSE

To discuss a standardized methodology for wound photography with a focus on aiding clinicians in capturing high-fidelity images.

TARGET AUDIENCE

This continuing education activity is intended for physicians, physician assistants, nurse practitioners, and nurses with an interest in skin and wound care.

LEARNING OBJECTIVES/OUTCOMES

After participating in this educational activity, the participant will be able to:1. Discriminate the components of high-quality wound photography.2. Identify the technological innovations that can augment clinical decision-making capacity.3. Choose strategies that can help clinicians avoid adverse medicolegal outcomes.

Applications of natural language processing in ophthalmology: present and future

Advances in technology, including novel ophthalmic imaging devices and adoption of the electronic health record (EHR), have resulted in significantly increased data available for both clinical use and research in ophthalmology. While artificial intelligence (AI) algorithms have the potential to utilize these data to transform clinical care, current applications of AI in ophthalmology have focused mostly on image-based deep learning. Unstructured free-text in the EHR represents a tremendous amount of underutilized data in big data analyses and predictive AI. Natural language processing (NLP) is a type of AI involved in processing human language that can be used to develop automated algorithms using these vast quantities of available text data. The purpose of this review was to introduce ophthalmologists to NLP by (1) reviewing current applications of NLP in ophthalmology and (2) exploring potential applications of NLP. We reviewed current literature published in Pubmed and Google Scholar for articles related to NLP and ophthalmology, and used ancestor search to expand our references. Overall, we found 19 published studies of NLP in ophthalmology. The majority of these publications (16) focused on extracting specific text such as visual acuity from free-text notes for the purposes of quantitative analysis. Other applications included: domain embedding, predictive modeling, and topic modeling. Future ophthalmic applications of NLP may also focus on developing search engines for data within free-text notes, cleaning notes, automated question-answering, and translating ophthalmology notes for other specialties or for patients, especially with a growing interest in open notes. As medicine becomes more data-oriented, NLP offers increasing opportunities to augment our ability to harness free-text data and drive innovations in healthcare delivery and treatment of ophthalmic conditions.

Interfacing With the Electronic Health Record (EHR): A Comparative Review of Modes of Documentation

Electronic health records (EHRs) have provided physicians with a systematic framework for collecting patient data, organizing notes from the healthcare team, and managing the daily workflow in the modern era of healthcare. Despite these advantages, EHRs have proven to be problematic for clinicians. The burdensome regulations requiring increased documentation with the EHR paradigm have led to inefficiencies from data-entry requirements forcing physicians to spend an inordinate amount of time on it, affecting the time available for direct patient care as well as leading to professional burnout. As a result, new modalities such as speech recognition, medical scribes, pre-made EHR templates, and digital scribes [a form of artificial intelligence (AI) based on ambient speech recognition] are increasingly being used to reduce charting time and increase the time available for patient care. The purpose of our review is to provide an up-to-date review of the literature on these modalities including their benefits and shortcomings, to help physicians and other medical professionals choose the best methods to document their patient-care encounters efficiently and effectively.

A dataset of simulated patient-physician medical interviews with a focus on respiratory cases

Artificial Intelligence (AI) is playing a major role in medical education, diagnosis, and outbreak detection through Natural Language Processing (NLP), machine learning models and deep learning tools. However, in order to train AI to facilitate these medical fields, well-documented and accurate medical conversations are needed. The dataset presented covers a series of medical conversations in the format of Objective Structured Clinical Examinations (OSCE), with a focus on respiratory cases in audio format and corresponding text documents. These cases were simulated, recorded, transcribed, and manually corrected with the underlying aim of providing a comprehensive set of medical conversation data to the academic and industry community. Potential applications include speech recognition detection for speech-to-text errors, training NLP models to extract symptoms, detecting diseases, or for educational purposes, including training an avatar to converse with healthcare professional students as a standardized patient during clinical examinations. The application opportunities for the presented dataset are vast, given that this calibre of data is difficult to access and costly to develop.

Do nurses document all discussions of patient problems and nursing interventions in the electronic health record? A pilot study in home healthcare

Objective

To assess the overlap of information between electronic health record (EHR) and patient–nurse verbal communication in home healthcare (HHC).

Methods

Patient–nurse verbal communications during home visits were recorded between February 16, 2021 and September 2, 2021 with patients being served in an organization located in the Northeast United States. Twenty-two audio recordings for 15 patients were transcribed. To compare overlap of information, manual annotations of problems and interventions were made on transcriptions as well as information from EHR including structured data and clinical notes corresponding to HHC visits.

Results

About 30% (1534/5118) of utterances (ie, spoken language preceding/following silence or a change of speaker) were identified as including problems or interventions. A total of 216 problems and 492 interventions were identified through verbal communication among all the patients in the study. Approximately 50.5% of the problems and 20.8% of the interventions discussed during the verbal communication were not documented in the EHR. Preliminary results showed that statistical differences between racial groups were observed in a comparison of problems and interventions.

Discussion

This study was the first to investigate the extent that problems and interventions were mentioned in patient–nurse verbal communication during HHC visits and whether this information was documented in EHR. Our analysis identified gaps in information overlap and possible racial disparities.

Conclusion

Our results highlight the value of analyzing communications between HHC patients and nurses. Future studies should explore ways to capture information in verbal communication using automated speech recognition.

Artificial Intelligence Education for the Health Workforce: Expert Survey of Approaches and Needs

BACKGROUND

The preparation of the current and future health workforce for the possibility of using artificial intelligence (AI) in health care is a growing concern as AI applications emerge in various care settings and specializations. At present, there is no obvious consensus among educators about what needs to be learned or how this learning may be supported or assessed.

OBJECTIVE

Our study aims to explore health care education experts' ideas and plans for preparing the health workforce to work with AI and identify critical gaps in curriculum and educational resources across a national health care system.

METHODS

A survey canvassed expert views on AI education for the health workforce in terms of educational strategies, subject matter priorities, meaningful learning activities, desired attitudes, and skills. A total of 39 senior people from different health workforce subgroups across Australia provided ratings and free-text responses in late 2020.

RESULTS

The responses highlighted the importance of education on ethical implications, suitability of large data sets for use in AI clinical applications, principles of machine learning, and specific diagnosis and treatment applications of AI as well as alterations to cognitive load during clinical work and the interaction between humans and machines in clinical settings. Respondents also outlined barriers to implementation, such as lack of governance structures and processes, resource constraints, and cultural adjustment.

CONCLUSIONS

Further work around the world of the kind reported in this survey can assist educators and education authorities who are responsible for preparing the health workforce to minimize the risks and realize the benefits of implementing AI in health care.

Automated evaluation of psychotherapy skills using speech and language technologies

With the growing prevalence of psychological interventions, it is vital to have measures which rate the effectiveness of psychological care to assist in training, supervision, and quality assurance of services. Traditionally, quality assessment is addressed by human raters who evaluate recorded sessions along specific dimensions, often codified through constructs relevant to the approach and domain. This is, however, a cost-prohibitive and time-consuming method that leads to poor feasibility and limited use in real-world settings. To facilitate this process, we have developed an automated competency rating tool able to process the raw recorded audio of a session, analyzing who spoke when, what they said, and how the health professional used language to provide therapy. Focusing on a use case of a specific type of psychotherapy called "motivational interviewing", our system gives comprehensive feedback to the therapist, including information about the dynamics of the session (e.g., therapist's vs. client's talking time), low-level psychological language descriptors (e.g., type of questions asked), as well as other high-level behavioral constructs (e.g., the extent to which the therapist understands the clients' perspective). We describe our platform and its performance using a dataset of more than 5000 recordings drawn from its deployment in a real-world clinical setting used to assist training of new therapists. Widespread use of automated psychotherapy rating tools may augment experts' capabilities by providing an avenue for more effective training and skill improvement, eventually leading to more positive clinical outcomes.

Perceptions and Needs of Artificial Intelligence in Health Care to Increase Adoption: Scoping Review

BACKGROUND

Artificial intelligence (AI) has the potential to improve the efficiency and effectiveness of health care service delivery. However, the perceptions and needs of such systems remain elusive, hindering efforts to promote AI adoption in health care.

OBJECTIVE

This study aims to provide an overview of the perceptions and needs of AI to increase its adoption in health care.

METHODS

A systematic scoping review was conducted according to the 5-stage framework by Arksey and O'Malley. Articles that described the perceptions and needs of AI in health care were searched across nine databases: ACM Library, CINAHL, Cochrane Central, Embase, IEEE Xplore, PsycINFO, PubMed, Scopus, and Web of Science for studies that were published from inception until June 21, 2021. Articles that were not specific to AI, not research studies, and not written in English were omitted.

RESULTS

Of the 3666 articles retrieved, 26 (0.71%) were eligible and included in this review. The mean age of the participants ranged from 30 to 72.6 years, the proportion of men ranged from 0% to 73.4%, and the sample sizes for primary studies ranged from 11 to 2780. The perceptions and needs of various populations in the use of AI were identified for general, primary, and community health care; chronic diseases self-management and self-diagnosis; mental health; and diagnostic procedures. The use of AI was perceived to be positive because of its availability, ease of use, and potential to improve efficiency and reduce the cost of health care service delivery. However, concerns were raised regarding the lack of trust in data privacy, patient safety, technological maturity, and the possibility of full automation. Suggestions for improving the adoption of AI in health care were highlighted: enhancing personalization and customizability; enhancing empathy and personification of AI-enabled chatbots and avatars; enhancing user experience, design, and interconnectedness with other devices; and educating the public on AI capabilities. Several corresponding mitigation strategies were also identified in this study.

CONCLUSIONS

The perceptions and needs of AI in its use in health care are crucial in improving its adoption by various stakeholders. Future studies and implementations should consider the points highlighted in this study to enhance the acceptability and adoption of AI in health care. This would facilitate an increase in the effectiveness and efficiency of health care service delivery to improve patient outcomes and satisfaction.

Clinician Preimplementation Perspectives of a Decision-Support Tool for the Prediction of Cardiac Arrhythmia Based on Machine Learning: Near-Live Feasibility and Qualitative Study

BACKGROUND

Artificial intelligence (AI), such as machine learning (ML), shows great promise for improving clinical decision-making in cardiac diseases by outperforming statistical-based models. However, few AI-based tools have been implemented in cardiology clinics because of the sociotechnical challenges during transitioning from algorithm development to real-world implementation.

OBJECTIVE

This study explored how an ML-based tool for predicting ventricular tachycardia and ventricular fibrillation (VT/VF) could support clinical decision-making in the remote monitoring of patients with an implantable cardioverter defibrillator (ICD).

METHODS

Seven experienced electrophysiologists participated in a near-live feasibility and qualitative study, which included walkthroughs of 5 blinded retrospective patient cases, use of the prediction tool, and questionnaires and interview questions. All sessions were video recorded, and sessions evaluating the prediction tool were transcribed verbatim. Data were analyzed through an inductive qualitative approach based on grounded theory.

RESULTS

The prediction tool was found to have potential for supporting decision-making in ICD remote monitoring by providing reassurance, increasing confidence, acting as a second opinion, reducing information search time, and enabling delegation of decisions to nurses and technicians. However, the prediction tool did not lead to changes in clinical action and was found less useful in cases where the quality of data was poor or when VT/VF predictions were found to be irrelevant for evaluating the patient.

CONCLUSIONS

When transitioning from AI development to testing its feasibility for clinical implementation, we need to consider the following: expectations must be aligned with the intended use of AI; trust in the prediction tool is likely to emerge from real-world use; and AI accuracy is relational and dependent on available information and local workflows. Addressing the sociotechnical gap between the development and implementation of clinical decision-support tools based on ML in cardiac care is essential for succeeding with adoption. It is suggested to include clinical end-users, clinical contexts, and workflows throughout the overall iterative approach to design, development, and implementation.

Pay attention to doctor-patient dialogues: Multi-modal knowledge graph attention image-text embedding for COVID-19 diagnosis

The sudden increase in coronavirus disease 2019 (COVID-19) cases puts high pressure on healthcare services worldwide. At this stage, fast, accurate, and early clinical assessment of the disease severity is vital. In general, there are two issues to overcome: (1) Current deep learning-based works suffer from multimodal data adequacy issues; (2) In this scenario, multimodal (e.g., text, image) information should be taken into account together to make accurate inferences. To address these challenges, we propose a multi-modal knowledge graph attention embedding for COVID-19 diagnosis. Our method not only learns the relational embedding from nodes in a constituted knowledge graph but also has access to medical knowledge, aiming at improving the performance of the classifier through the mechanism of medical knowledge attention. The experimental results show that our approach significantly improves classification performance compared to other state-of-the-art techniques and possesses robustness for each modality from multi-modal data. Moreover, we construct a new COVID-19 multi-modal dataset based on text mining, consisting of 1393 doctor-patient dialogues and their 3706 images (347 X-ray + 2598 CT + 761 ultrasound) about COVID-19 patients and 607 non-COVID-19 patient dialogues and their 10754 images (9658 X-ray + 494 CT + 761 ultrasound), and the fine-grained labels of all. We hope this work can provide insights to the researchers working in this area to shift the attention from only medical images to the doctor-patient dialogue and its corresponding medical images.

The burden of the digital environment: a systematic review on organization-directed workplace interventions to mitigate physician burnout

OBJECTIVE

To conduct a systematic review identifying workplace interventions that mitigate physician burnout related to the digital environment including health information technologies (eg, electronic health records) and decision support systems) with or without the application of advanced analytics for clinical care.

MATERIALS AND METHODS

Literature published from January 1, 2007 to June 3, 2020 was systematically reviewed from multiple databases and hand searches. Subgroup analysis identified relevant physician burnout studies with interventions examining digital tool burden, related workflow inefficiencies, and measures of burnout, stress, or job satisfaction in all practice settings.

RESULTS

The search strategy identified 4806 citations of which 81 met inclusion criteria. Thirty-eight studies reported interventions to decrease digital tool burden. Sixty-eight percent of these studies reported improvement in burnout and/or its proxy measures. Burnout was decreased by interventions that optimized technologies (primarily electronic health records), provided training, reduced documentation and task time, expanded the care team, and leveraged quality improvement processes in workflows.

DISCUSSION

The contribution of digital tools to physician burnout can be mitigated by careful examination of usability, introducing technologies to save or optimize time, and applying quality improvement to workflows.

CONCLUSION

Physician burnout is not reduced by technology implementation but can be mitigated by technology and workflow optimization, training, team expansion, and careful consideration of factors affecting burnout, including specialty, practice setting, regulatory pressures, and how physicians spend their time.

Digital health and primary care: Past, pandemic and prospects

This article reflects on the breadth of digital developments seen in primary care over time, as well as the rapid and significant changes prompted by the COVID-19 crisis. Recent research and experience have shone further light on factors influencing the implementation and usefulness of these approaches, as well as unresolved challenges and unintended consequences. These are considered in relation to not only digital technology and infrastructure, but also wider aspects of health systems, the nature of primary care work and culture, patient characteristics and inequalities, and ethical issues around data privacy, inclusion, empowerment, empathy and trust. Implications for the future direction and sustainability of these approaches are discussed, taking account of novel paradigms, such as artificial intelligence, and the growing capture of primary care data for secondary uses. Decision makers are encouraged to think holistically about where value is most likely to be added, or risks being taken away, when judging which innovations to carry forward. It concludes that, while responding to this public health emergency has created something of a digital 'big bang' for primary care, an incremental, adaptive, patient-centered strategy, focused on augmenting rather than replacing existing services, is likely to prove most fruitful in the longer term.

Digital scribe utility and barriers to implementation in clinical practice: a scoping review

Electronic health records (EHRs) allow for meaningful usage of healthcare data. Their adoption provides clinicians with a central location to access and share data, write notes, order labs and prescriptions, and bill for patient visits. However, as non-clinical requirements have increased, time spent using EHRs eclipsed time spent on direct patient care. Several solutions have been proposed to minimize the time spent using EHRs, though each have limitations. Digital scribe technology uses voice-to-text software to convert ambient listening to meaningful medical notes and may eliminate the physical task of documentation, allowing physicians to spend less time on EHR engagement and more time with patients. However, adoption of digital scribe technology poses many barriers for physicians. In this study, we perform a scoping review of the literature to identify barriers to digital scribe implementation and provide solutions to address these barriers. We performed a literature review of digital scribe technology and voice-to-text conversion and information extraction as a scope for future research. Fifteen articles met inclusion criteria. Of the articles included, four were comparative studies, three were reviews, three were original investigations, two were perspective pieces, one was a cost-effectiveness study, one was a keynote address, and one was an observational study. The published articles on digital scribe technology and voice-to-text conversion highlight digital scribe technology as a solution to the inefficient interaction with EHRs. Benefits of digital scribe technologies included enhancing clinician ability to navigate charts, write notes, use decision support tools, and improve the quality of time spent with patients. Digital scribe technologies can improve clinic efficiency and increase patient access to care while simultaneously reducing physician burnout. Implementation barriers include upfront costs, integration with existing technology, and time-intensive training. Technological barriers include adaptability to linguistic differences, compatibility across different clinical encounters, and integration of medical jargon into the note. Broader risks include automation bias and risks to data privacy. Overcoming significant barriers to implementation will facilitate more widespread adoption.

Supplementary information

The online version contains supplementary material available at 10.1007/s12553-021-00568-0.

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.

Precision Assessment of COVID-19 Phenotypes Using Large-Scale Clinic Visit Audio Recordings: Harnessing the Power of Patient Voice

COVID-19 cases are exponentially increasing worldwide; however, its clinical phenotype remains unclear. Natural language processing (NLP) and machine learning approaches may yield key methods to rapidly identify individuals at a high risk of COVID-19 and to understand key symptoms upon clinical manifestation and presentation. Data on such symptoms may not be accurately synthesized into patient records owing to the pressing need to treat patients in overburdened health care settings. In this scenario, clinicians may focus on documenting widely reported symptoms that indicate a confirmed diagnosis of COVID-19, albeit at the expense of infrequently reported symptoms. While NLP solutions can play a key role in generating clinical phenotypes of COVID-19, they are limited by the resulting limitations in data from electronic health records (EHRs). A comprehensive record of clinic visits is required—audio recordings may be the answer. A recording of clinic visits represents a more comprehensive record of patient-reported symptoms. If done at scale, a combination of data from the EHR and recordings of clinic visits can be used to power NLP and machine learning models, thus rapidly generating a clinical phenotype of COVID-19. We propose the generation of a pipeline extending from audio or video recordings of clinic visits to establish a model that factors in clinical symptoms and predict COVID-19 incidence. With vast amounts of available data, we believe that a prediction model can be rapidly developed to promote the accurate screening of individuals at a high risk of COVID-19 and to identify patient characteristics that predict a greater risk of a more severe infection. If clinical encounters are recorded and our NLP model is adequately refined, benchtop virologic findings would be better informed. While clinic visit recordings are not the panacea for this pandemic, they are a low-cost option with many potential benefits, which have recently begun to be explored.

A patient-centered digital scribe for automatic medical documentation

Objective

We developed a digital scribe for automatic medical documentation by utilizing elements of patient-centered communication. Excessive time spent on medical documentation may contribute to physician burnout. Patient-centered communication may improve patient satisfaction, reduce malpractice rates, and decrease diagnostic testing expenses. We demonstrate that patient-centered communication may allow providers to simultaneously talk to patients and efficiently document relevant information.

Materials and Methods

We utilized two elements of patient-centered communication to document patient history. One element was summarizing, which involved providers recapping information to confirm an accurate understanding of the patient. Another element was signposting, which involved providers using transition questions and statements to guide the conversation. We also utilized text classification to allow providers to simultaneously perform and document the physical exam. We conducted a proof-of-concept study by simulating patient encounters with two medical students.

Results

For history sections, the digital scribe was about 2.7 times faster than both typing and dictation. For physical exam sections, the digital scribe was about 2.17 times faster than typing and about 3.12 times faster than dictation. Results also suggested that providers required minimal training to use the digital scribe, and that they improved at using the system to document history sections.

Conclusion

Compared to typing and dictation, a patient-centered digital scribe may facilitate effective patient communication. It may also be more reliable compared to previous approaches that solely use machine learning. We conclude that a patient-centered digital scribe may be an effective tool for automatic medical documentation.

Envisioning an artificial intelligence documentation assistant for future primary care consultations: A co-design study with general practitioners

OBJECTIVE

The study sought to understand the potential roles of a future artificial intelligence (AI) documentation assistant in primary care consultations and to identify implications for doctors, patients, healthcare system, and technology design from the perspective of general practitioners.

MATERIALS AND METHODS

Co-design workshops with general practitioners were conducted. The workshops focused on (1) understanding the current consultation context and identifying existing problems, (2) ideating future solutions to these problems, and (3) discussing future roles for AI in primary care. The workshop activities included affinity diagramming, brainwriting, and video prototyping methods. The workshops were audio-recorded and transcribed verbatim. Inductive thematic analysis of the transcripts of conversations was performed.

RESULTS

Two researchers facilitated 3 co-design workshops with 16 general practitioners. Three main themes emerged: professional autonomy, human-AI collaboration, and new models of care. Major implications identified within these themes included (1) concerns with medico-legal aspects arising from constant recording and accessibility of full consultation records, (2) future consultations taking place out of the exam rooms in a distributed system involving empowered patients, (3) human conversation and empathy remaining the core tasks of doctors in any future AI-enabled consultations, and (4) questioning the current focus of AI initiatives on improved efficiency as opposed to patient care.

CONCLUSIONS

AI documentation assistants will likely to be integral to the future primary care consultations. However, these technologies will still need to be supervised by a human until strong evidence for reliable autonomous performance is available. Therefore, different human-AI collaboration models will need to be designed and evaluated to ensure patient safety, quality of care, doctor safety, and doctor autonomy.

Identifying relevant information in medical conversations to summarize a clinician-patient encounter

To inform the development of automated summarization of clinical conversations, this study sought to estimate the proportion of doctor-patient communication in general practice (GP) consultations used for generating a consultation summary. Two researchers with a medical degree read the transcripts of 44 GP consultations and highlighted the phrases to be used for generating a summary of the consultation. For all consultations, less than 20% of all words in the transcripts were needed for inclusion in the summary. On average, 9.1% of all words in the transcripts, 26.6% of all medical terms, and 27.3% of all speaker turns were highlighted. The results indicate that communication content used for generating a consultation summary makes up a small portion of GP consultations, and automated summarization solutions-such as digital scribes-must focus on identifying the 20% relevant information for automatically generating consultation summaries.

Quality of care in surgical/interventional vascular medicine: what can routinely collected data from the insurance companies achieve?

The complexity and diversity of surgical/interventional vascular medicine necessitate innovative and pragmatic solutions for the valid measurement of the quality of care in the long term. The secondary utilization of routinely collected data from social insurance institutions has increasingly become the focus of interdisciplinary medicine over the years. Owing to their longitudinal linkage and pan-sector generation, routinely collected data make it possible to answer important questions and can complement quality development projects with primary registry data. Various guidelines exist for their usage, linkage, and reporting. Studies have shown good validity, especially for endpoints with major clinical relevance. The numerous advantages of routinely collected data face several challenges that require thorough plausibility and validity procedures and distinctive methodological expertise. This review presents a discussion of these advantages and challenges and provides recommendations for starting to use this increasingly important source of data.

How does medical scribes' work inform development of speech-based clinical documentation technologies? A systematic review

OBJECTIVE

Use of medical scribes reduces clinician burnout by sharing the burden of clinical documentation. However, medical scribes are cost-prohibitive for most settings, prompting a growing interest in developing ambient, speech-based technologies capable of automatically generating clinical documentation based on patient-provider conversation. Through a systematic review, we aimed to develop a thorough understanding of the work performed by medical scribes in order to inform the design of such technologies.

MATERIALS AND METHODS

Relevant articles retrieved by searching in multiple literature databases. We conducted the screening process following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) in guidelines, and then analyzed the data using qualitative methods to identify recurring themes.

RESULTS

The literature search returned 854 results, 65 of which met the inclusion criteria. We found that there is significant variation in scribe expectations and responsibilities across healthcare organizations; scribes also frequently adapt their work based on the provider's style and preferences. Further, scribes' job extends far beyond capturing conversation in the exam room; they also actively interact with patients and the care team and integrate data from other sources such as prior charts and lab test results.

DISCUSSION

The results of this study provide several implications for designing technologies that can generate clinical documentation based on naturalistic conversations taking place in the exam room. First, a one-size-fits-all solution will be unlikely to work because of the significant variation in scribe work. Second, technology designers need to be aware of the limited role that their solution can fulfill. Third, to produce comprehensive clinical documentation, such technologies will likely have to incorporate information beyond the exam room conversation. Finally, issues of patient consent and privacy have yet to be adequately addressed, which could become paramount barriers to implementing such technologies in realistic clinical settings.

CONCLUSIONS

Medical scribes perform complex and delicate work. Further research is needed to better understand their roles in a clinical setting in order to inform the development of speech-based clinical documentation technologies.