BACKGROUND: Medical documentation plays a crucial role in clinical practice, facilitating accurate patient management and communication among health care professionals. However, inaccuracies in medical notes can lead to miscommunication and diagnostic errors. Additionally, the demands of documentation contribute to physician burnout. Although intermediaries like medical scribes and speech recognition software have been used to ease this burden, they have limitations in terms of accuracy and addressing provider-specific metrics. The integration of ambient artificial intelligence (AI)-powered solutions offers a promising way to improve documentation while fitting seamlessly into existing workflows.
OBJECTIVE: This study aims to assess the accuracy and quality of Subjective, Objective, Assessment, and Plan (SOAP) notes generated by ChatGPT-4, an AI model, using established transcripts of History and Physical Examination as the gold standard. We seek to identify potential errors and evaluate the model\'s performance across different categories.
METHODS: We conducted simulated patient-provider encounters representing various ambulatory specialties and transcribed the audio files. Key reportable elements were identified, and ChatGPT-4 was used to generate SOAP notes based on these transcripts. Three versions of each note were created and compared to the gold standard via chart review; errors generated from the comparison were categorized as omissions, incorrect information, or additions. We compared the accuracy of data elements across versions, transcript length, and data categories. Additionally, we assessed note quality using the Physician Documentation Quality Instrument (PDQI) scoring system.
RESULTS: Although ChatGPT-4 consistently generated SOAP-style notes, there were, on average, 23.6 errors per clinical case, with errors of omission (86%) being the most common, followed by addition errors (10.5%) and inclusion of incorrect facts (3.2%). There was significant variance between replicates of the same case, with only 52.9% of data elements reported correctly across all 3 replicates. The accuracy of data elements varied across cases, with the highest accuracy observed in the \"Objective\" section. Consequently, the measure of note quality, assessed by PDQI, demonstrated intra- and intercase variance. Finally, the accuracy of ChatGPT-4 was inversely correlated to both the transcript length (P=.05) and the number of scorable data elements (P=.05).
CONCLUSIONS: Our study reveals substantial variability in errors, accuracy, and note quality generated by ChatGPT-4. Errors were not limited to specific sections, and the inconsistency in error types across replicates complicated predictability. Transcript length and data complexity were inversely correlated with note accuracy, raising concerns about the model\'s effectiveness in handling complex medical cases. The quality and reliability of clinical notes produced by ChatGPT-4 do not meet the standards required for clinical use. Although AI holds promise in health care, caution should be exercised before widespread adoption. Further research is needed to address accuracy, variability, and potential errors. ChatGPT-4, while valuable in various applications, should not be considered a safe alternative to human-generated clinical documentation at this time.

UNASSIGNED: New legislation allows patients (with permitted exceptions) to read their clinical notes, leading to both benefits and ethical dilemmas. Medical students need a robust curriculum to learn documentation skills within this challenging context. We aimed to teach note-writing skills through a patient-centered lens with special consideration for the impact on patients and providers. We developed this session for first-year medical students within their foundational clinical skills course to place bias-free language at the forefront of how they learn to construct a medical note.
UNASSIGNED: One hundred seventy-three first-year medical and dental students participated in this curriculum. They completed an asynchronous presession module first, followed by a 2-hour synchronous workshop including a didactic, student-led discussion and sample patient note exercise. Students were subsequently responsible throughout the year for constructing patient-centered notes, graded by faculty with a newly developed rubric and checklist of best practices.
UNASSIGNED: On postworkshop surveys, learners reported increased preparedness in their ability to document in a patient-centered manner (presession M = 2.2, midyear M = 3.9, p < .001), as rated on a 5-point Likert scale (1 = not prepared at all, 5 = very prepared), and also found this topic valuable to learn early in their training.
UNASSIGNED: This curriculum utilizes a multipart approach to prepare learners to employ clinical notes to communicate with patients and providers, with special attention to how patients and their care partners receive a note. Future directions include expanding the curriculum to higher levels of learning and validating the developed materials.

UNASSIGNED: Medical notes are narratives that describe the health of the patient in free text format. These notes can be more informative than structured data such as the history of medications or disease conditions. They are routinely collected and can be used to evaluate the patient\'s risk for developing chronic diseases such as dementia. This study investigates different methodologies for transforming routine care notes into dementia risk classifiers and evaluates the generalizability of these classifiers to new patients and new health care institutions.
UNASSIGNED: The notes collected over the relevant history of the patient are lengthy. In this study, TF-ICF is used to select keywords with the highest discriminative ability between at risk dementia patients and healthy controls. The medical notes are then summarized in the form of occurrences of the selected keywords. Two different encodings of the summary are compared. The first encoding consists of the average of the vector embedding of each keyword occurrence as produced by the BERT or Clinical BERT pre-trained language models. The second encoding aggregates the keywords according to UMLS concepts and uses each concept as an exposure variable. For both encodings, misspellings of the selected keywords are also considered in an effort to improve the predictive performance of the classifiers. A neural network is developed over the first encoding and a gradient boosted trees model is applied to the second encoding. Patients from a single health care institution are used to develop all the classifiers which are then evaluated on held-out patients from the same health care institution as well as test patients from two other health care institutions.
UNASSIGNED: The results indicate that it is possible to identify patients at risk for dementia one year ahead of the onset of the disease using medical notes with an AUC of 75% when a gradient boosted trees model is used in conjunction with exposure variables derived from UMLS concepts. However, this performance is not maintained with an embedded feature space and when the classifier is applied to patients from other health care institutions. Moreover, an analysis of the top predictors of the gradient boosted trees model indicates that different features inform the classification depending on whether or not spelling variants of the keywords are included.
UNASSIGNED: The present study demonstrates that medical notes can enable risk prediction models for complex chronic diseases such as dementia. However, additional research efforts are needed to improve the generalizability of these models. These efforts should take into consideration the length and localization of the medical notes; the availability of sufficient training data for each disease condition; and the variabilities resulting from different feature engineering techniques.

BACKGROUND: Identifying caregiver availability, particularly for patients with dementia or those with a disability, is critical to informing the appropriate care planning by the health systems, hospitals, and providers. This information is not readily available, and there is a paucity of pragmatic approaches to automatically identifying caregiver availability and type.
OBJECTIVE: Our main objective was to use medical notes to assess caregiver availability and type for hospitalized patients with dementia. Our second objective was to identify whether the patient lived at home or resided at an institution.
METHODS: In this retrospective cohort study, we used 2016-2019 telephone-encounter medical notes from a single institution to develop a rule-based natural language processing (NLP) algorithm to identify the patient\'s caregiver availability and place of residence. Using note-level data, we compared the results of the NLP algorithm with human-conducted chart abstraction for both training (749/976, 77%) and test sets (227/976, 23%) for a total of 223 adults aged 65 years and older diagnosed with dementia. Our outcomes included determining whether the patients (1) reside at home or in an institution, (2) have a formal caregiver, and (3) have an informal caregiver.
RESULTS: Test set results indicated that our NLP algorithm had high level of accuracy and reliability for identifying whether patients had an informal caregiver (F1=0.94, accuracy=0.95, sensitivity=0.97, and specificity=0.93), but was relatively less able to identify whether the patient lived at an institution (F1=0.64, accuracy=0.90, sensitivity=0.51, and specificity=0.98). The most common explanations for NLP misclassifications across all categories were (1) incomplete or misspelled facility names; (2) past, uncertain, or undecided status; (3) uncommon abbreviations; and (4) irregular use of templates.
CONCLUSIONS: This innovative work was the first to use medical notes to pragmatically determine caregiver availability. Our NLP algorithm identified whether hospitalized patients with dementia have a formal or informal caregiver and, to a lesser extent, whether they lived at home or in an institutional setting. There is merit in using NLP to identify caregivers. This study serves as a proof of concept. Future work can use other approaches and further identify caregivers and the extent of their availability.

Discharge medical notes written by physicians contain important information about the health condition of patients. Many deep learning algorithms have been successfully applied to extract important information from unstructured medical notes data that can entail subsequent actionable results in the medical domain. This study aims to explore the model performance of various deep learning algorithms in text classification tasks on medical notes with respect to different disease class imbalance scenarios.
In this study, we employed seven artificial intelligence models, a CNN (Convolutional Neural Network), a Transformer encoder, a pretrained BERT (Bidirectional Encoder Representations from Transformers), and four typical sequence neural networks models, namely, RNN (Recurrent Neural Network), GRU (Gated Recurrent Unit), LSTM (Long Short-Term Memory), and Bi-LSTM (Bi-directional Long Short-Term Memory) to classify the presence or absence of 16 disease conditions from patients\' discharge summary notes. We analyzed this question as a composition of 16 binary separate classification problems. The model performance of the seven models on each of the 16 datasets with various levels of imbalance between classes were compared in terms of AUC-ROC (Area Under the Curve of the Receiver Operating Characteristic), AUC-PR (Area Under the Curve of Precision and Recall), F1 Score, and Balanced Accuracy as well as the training time. The model performances were also compared in combination with different word embedding approaches (GloVe, BioWordVec, and no pre-trained word embeddings).
The analyses of these 16 binary classification problems showed that the Transformer encoder model performs the best in nearly all scenarios. In addition, when the disease prevalence is close to or greater than 50%, the Convolutional Neural Network model achieved a comparable performance to the Transformer encoder, and its training time was 17.6% shorter than the second fastest model, 91.3% shorter than the Transformer encoder, and 94.7% shorter than the pre-trained BERT-Base model. The BioWordVec embeddings slightly improved the performance of the Bi-LSTM model in most disease prevalence scenarios, while the CNN model performed better without pre-trained word embeddings. In addition, the training time was significantly reduced with the GloVe embeddings for all models.
For classification tasks on medical notes, Transformer encoders are the best choice if the computation resource is not an issue. Otherwise, when the classes are relatively balanced, CNNs are a leading candidate because of their competitive performance and computational efficiency.

The aim of this work is to uncover the preferences and perspectives of college educators as they interpret medical documentation outlining medically requested return-to-learn (RTL) instructions. Participants were recruited from five colleges across campus at a large Midwest public university. They each engaged in a private, one-on-one, audio-recorded interview. All recordings were transcribed and inductively analyzed using a grounded theory approach and two-coder system. All codes and themes were finalized once agreement was reached by both coders. Resultant themes from axial coding had to represent the voices of at least 80% of participants. Three characteristics emerged as being desired by college educators: brevity, clarity, and direction. Educators also expressed considerably less utility with medical documentation designed for pediatric students with concussion. College educators desire medical notes that are brief, clear, and provide straightforward direction, in addition to documentation that is tailored for the college setting.

OBJECTIVE: We wanted to characterize the acceptability of and women\'s satisfaction with the eMutterPass application. Particular attention was placed on concerns about data confidentiality and on willingness to use the app in an interactive way to share information about medication consumption.
METHODS: The present analysis is based on self-reported data from obstetric patients participating in an anonymous online survey between April 6th 2021 and April 20th 2021.
RESULTS: During the 2-week timeframe, 1123 questionnaires were completed. The eMutterPass application was widely appreciated by our survey population and almost all participants would recommend the application to other pregnant women. A subpopulation analysis indicates that concerns about data confidentiality were higher among younger, multigravid and non-German-speaking pregnant women. The majority of women would be willing to report their medication use by taking pictures, filling in medication dosages or submitting assessments of perceived drug effectiveness.
CONCLUSIONS: The development of our eMutterPass application meets the spirit of the times and gives pregnant women uncomplicated access to their own data. Concerns about data confidentiality can be adequately countered with additional information about the system structure. The largely positive adherence to the idea of reporting medication use on the app lays the groundwork for potential use of the eMutterPass for documentation of non-prescribed drugs.

Clinicians spend a substantial part of their workday reviewing and writing electronic medical notes. Here we describe how the current, widely accepted paradigm for electronic medical notes represents a poor organizational framework for both the individual clinician and the broader medical team. As described in this viewpoint, the medical chart-including notes, labs, and imaging results-can be reconceptualized as a dynamic, fully collaborative workspace organized by topic rather than time, writer, or data type. This revised framework enables a more accurate and complete assessment of the current state of the patient and easy historical review, saving clinicians substantial time on both data input and retrieval. Collectively, this approach has the potential to improve health care delivery effectiveness and efficiency.

OBJECTIVE: Older patients who are at risk of poor healthcare outcomes should be recognised early during hospital admission to allow appropriate interventions. It is unclear whether routinely collected data can identify high-risk patients. The aim of this study was to define current practice with regard to the identification of older patients at high risk of poor healthcare outcomes on admission to hospital.
RESULTS: Interviews/focus groups were conducted to establish the views of 22 healthcare staff across five acute medicine for older people wards in one hospital including seven nurses, four dieticians, seven doctors, and four therapists. In addition, a random sample of 60 patients\' clinical records were reviewed to characterise the older patients, identify risk assessments performed routinely on admission, and describe usual care. We found that staff relied on their clinical judgment to identify high risk patients which was influenced by a number of factors such as reasons for admission, staff familiarity with patients, patients\' general condition, visible frailty, and patients\' ability to manage at home. \"Therapy assessment\" and patients\' engagement with therapy were also reported to be important in recognising high-risk patients. However, staff recognised that making clinical judgments was often difficult and that it might occur several days after admission potentially delaying specific interventions. Routine risk assessments carried out on admission to identify single healthcare needs included risk of malnutrition (completed for 85% patients), falls risk (95%), moving and handling assessments (85%), and pressure ulcer risk assessments (88%). These were not used collectively to highlight patients at risk of poor healthcare outcomes. Thus, patients at risk of poor healthcare outcomes were not explicitly identified on admission using routinely collected data. There is a need for an early identification of these patients using a valid measure alongside staff clinical judgment to allow timely interventions to improve healthcare outcomes.

OBJECTIVE: Patients are increasingly provided facilitated access to their medical notes. Physicians have reported concerns that patients will find notes confusing and offensive, and that typographical errors will appear unprofessional. This exploratory study quantifies the prevalence of potentially confusing or offensive medical language and typographic errors within notes.
METHODS: The authors performed a retrospective, cross-sectional review of 400 inpatient History and Physical notes from a tertiary care center. All notes were from admissions to general internal medicine services. Words and phrases of interest were codified into five pre-established categories and subdivisions.
RESULTS: Of 400 notes, 337 notes written by residents and hospitalists were analyzed. The most prevalent characteristics identified per note were General Medical Acronyms (99.1%), Medical Jargon (96.7%), and Typographical Errors (49%). Residents used a greater number of acronyms and abbreviations (p<0.01). All subdivisions within Subjective Descriptors and Mental and Personal Health appeared in less than 20% of notes.
CONCLUSIONS: While the place of medical shorthand, jargon, and sensitive history in the note is unlikely to change in the near future, this study identifies typographical errors as a modifiable area for improvement. The examination of medical note language may prove beneficial to the patient-physician relationship in the digital era.