Deportations and departures: Undocumented Mexican immigrants' return migration during three presidential administrations.

This study examines changes in the sociodemographic patterns of deportation and voluntary return of undocumented immigrants from the United States to Mexico during three US presidential administrations (2001 to 2019) with different immigration policies. Most previous studies examining these migration flows for the United States as a whole have relied exclusively on counts of deportees and returnees, thereby ignoring changes over the past 20 y in the characteristics of the undocumented population itself, i.e., the population at risk of deportation or voluntary return. We estimate Poisson models based on two data sources that permit us to compare changes in the sex, age, education, and marital status distributions of both deportees and voluntary return migrants with the corresponding changes in the undocumented population during the Bush, Obama, and Trump administrations: the Migration Survey on the Borders of Mexico-North (Encuesta sobre Migración en las Fronteras de México-Norte) for counts of deportees and voluntary return migrants and the Current Population Survey's Annual Social and Economic Supplement for estimated counts of the undocumented population living in the United States. We find that whereas disparities by sociodemographic characteristics in the likelihood of deportation generally increased beginning in Obama's first term, sociodemographic disparities in the likelihood of voluntary return generally decreased over this period. Despite heightened antiimmigrant rhetoric during the Trump administration, the changes in deportation and voluntary return migration to Mexico among the undocumented during Trump's term were part of a trend that began early in the Obama administration.

Open-source large language models in action: A bioinformatics chatbot for PRIDE database.

We here present a chatbot assistant infrastructure (https://www.ebi.ac.uk/pride/chatbot/) that simplifies user interactions with the PRIDE database's documentation and dataset search functionality. The framework utilizes multiple Large Language Models (LLM): llama2, chatglm, mixtral (mistral), and openhermes. It also includes a web service API (Application Programming Interface), web interface, and components for indexing and managing vector databases. An Elo-ranking system-based benchmark component is included in the framework as well, which allows for evaluating the performance of each LLM and for improving PRIDE documentation. The chatbot not only allows users to interact with PRIDE documentation but can also be used to search and find PRIDE datasets using an LLM-based recommendation system, enabling dataset discoverability. Importantly, while our infrastructure is exemplified through its application in the PRIDE database context, the modular and adaptable nature of our approach positions it as a valuable tool for improving user experiences across a spectrum of bioinformatics and proteomics tools and resources, among other domains. The integration of advanced LLMs, innovative vector-based construction, the benchmarking framework, and optimized documentation collectively form a robust and transferable chatbot assistant infrastructure. The framework is open-source (https://github.com/PRIDE-Archive/pride-chatbot).

Measuring Documentation Burden in Healthcare.

BACKGROUND: The enactment of the Health Information Technology for Economic and Clinical Health Act and the wide adoption of electronic health record (EHR) systems have ushered in increasing documentation burden, frequently cited as a key factor affecting the work experience of healthcare professionals and a contributor to burnout. This systematic review aims to identify and characterize measures of documentation burden. METHODS: We integrated discussions with Key Informants and a comprehensive search of the literature, including MEDLINE, Embase, Scopus, and gray literature published between 2010 and 2023. Data were narratively and thematically synthesized. RESULTS: We identified 135 articles about measuring documentation burden. We classified measures into 11 categories: overall time spent in EHR, activities related to clinical documentation, inbox management, time spent in clinical review, time spent in orders, work outside work/after hours, administrative tasks (billing and insurance related), fragmentation of workflow, measures of efficiency, EHR activity rate, and usability. The most common source of data for most measures was EHR usage logs. Direct tracking such as through time-motion analysis was fairly uncommon. Measures were developed and applied across various settings and populations, with physicians and nurses in the USA being the most frequently represented healthcare professionals. Evidence of validity of these measures was limited and incomplete. Data on the appropriateness of measures in terms of scalability, feasibility, or equity across various contexts were limited. The physician perspective was the most robustly captured and prominently focused on increased stress and burnout. DISCUSSION: Numerous measures for documentation burden are available and have been tested in a variety of settings and contexts. However, most are one-dimensional, do not capture various domains of this construct, and lack robust validity evidence. This report serves as a call to action highlighting an urgent need for measure development that represents diverse clinical contexts and support future interventions.

Documentation and classification of hospital pharmacist interventions: A scoping review.

The practice of documenting pharmacist interventions (PIs) has been endorsed by many hospital pharmacists' societies and organizations worldwide. Current systems for recording PIs have been developed to generate data on better patient and healthcare outcomes, but harmonization and transferability are apparently minimal. The present work aims to provide a descriptive and comprehensive overview of the currently utilized PI documentation and classification tools contributing to increased evidence systematization. A systematic literature search was conducted in PubMed, Scopus, Web of Science and the Cumulative Index to Nursing and Allied Health Literature. Studies from 2008, after the release of the Basel Statements, were included if interventions were made by hospital or clinical pharmacists in a global hospital setting. Publications quality assessment was accomplished using the Mixed Methods Appraisal Tool. A total of 26 studies were included. Three studies did not refer to the documentation/classification method, 10 used an in-house developed documentation/classification method, seven used externally developed documentation/classification tools and six described method validation or translation. Evidence confirmed that most documentation/classification systems are designed in-house, but external development and validation of PI systems to be used in hospital practice is gradually increasing. Reports on validated PI documentation/classification tools that are being used in hospital clinical practice are limited, including in countries with advanced hospital pharmacy practice. Needs and gaps in practice were identified. Further research should be conducted to understand why using validated documentation/classification methods is not a disseminated practice, knowing patients' and organizational advantages.

Incidental Findings in Trauma Patients: How Big is the Challenge?

INTRODUCTION: The purpose of this study was to examine the prevalence of incidental findings (IFs) identified during workup of trauma patients and the effectiveness with which they were documented and communicated. MATERIALS AND METHODS: We performed a retrospective analysis of all trauma patients ≥15 y of age in 2018, who underwent at least one computed tomography scan. Patients' Electronic Medical Record was reviewed for the presence of IFs. IFs were classified in three categories: category 1, which includes highly significant findings requiring attention during hospitalization; category 2, which warrants attention in an outpatient basis; and category 3, which includes nonsignificant findings that require no follow-up. RESULTS: 836 patients were identified, of which 582 had at least one IF. Of the patients with IFs; 14 (2.4%) were category 1, 138 (23.7%) were category 2, and 569 (97.8%) met category 3 criteria. All category 1 patients received appropriate documentation of their IFs. Of patients with category 2 findings, only 13% had documentation of the IFs. Patients with IFs had longer length of stay (P: 0.04) and lower probability of being discharged to home (P < 0.01) compared to patients with no IFs. Only 12.5% of the patients admitted to trauma surgery service received an outpatient follow-up. CONCLUSIONS: There was timely documentation and intervention for all patients with category 1 IFs. However, 87% of patients with category 2 IFs had inadequate documentation of the IF and outpatient follow-up. Outpatient follow-up of IFs poses a challenge for trauma patients partially due to their discharge disposition.

An assessment of narrative operative reports for Wilms tumor resection using consensus component criteria.

INTRODUCTION: Precision in surgical documentation is essential to avoid miscommunication and errors in patient care. Synoptic operative reports are more precise than narrative operative reports, however they have not been widely implemented in pediatric surgical oncology. To assess the need for implementation of synoptic operative reports in pediatric surgical oncology, we examined the completeness of narrative operative reports in patients undergoing resection of Wilms tumor. METHODS: We conducted a retrospective review of narrative operative reports for resection of Wilms tumor at a single pediatric oncology center from January 2022 through July 2023. Primary outcomes were the presence or absence of 11 key operative report components. Inclusion rates were calculated as simple percentages. Unilateral and bilateral operations were considered. RESULTS: Thirty-five narrative reports for Wilms tumor resection were included. The most consistently documented operative report components were estimated blood loss, indication for surgery, intraoperative complications, and specimen naming (100% documentation rates). Documentation of lymph node sampling was present in 94.3% of reports. The least consistently documented components were assessment of intraoperative tumor spillage, completeness of resection, metastatic disease, and assessment of vascular involvement (each ≤40% documentation rate). All 11 key components were documented in three reports. CONCLUSIONS: Even at a large tertiary pediatric oncology referral center, narrative operative reports for pediatric Wilms tumor resection were found to be frequently missing important components of surgical documentation. Often, these were omissions of negative findings. Utilization of synoptic operative reports may be able to reduce these gaps.

The utility of synoptic operation reports in colorectal surgery: a systematic review.

PURPOSE: Accurate documentation is crucial in surgical patient care. Synoptic reports (SR) are structured checklist-based reports that offer a standardised alternative to traditional narrative reports (NR). This systematic review aims to assess the completeness of SR compared to NR in colorectal cancer (CRC) surgery. Secondary outcomes include the time to completion, surgeon satisfaction, educational value, research value, and barriers to implementation. METHODS: Prospective or retrospective studies that assessed SR compared to NR in colorectal cancer surgery procedures were identified through a systematic search of Ovid MEDLINE, Embase (Ovid), CIHNAL Plus with Full Text (EBSCOhost), and Cochrane. One thousand two articles were screened, and eight studies met the inclusion criteria after full-text review of 17 papers. RESULTS: Analysis included 1797 operative reports (NR, 729; SR, 1068). Across studies reporting this outcome, the completeness of documentation was significantly higher in SR (P < 0.001). Reporting of secondary outcomes was limited, with a predominant focus on research value. Several studies demonstrated significantly reduced data extraction times when utilising SR. Surgeon satisfaction with SR was high, and these reports were seen as valuable tools for research and education. Barriers to implementation included integrating SR into existing electronic medical records (EMR) and surgeon concerns regarding increased administrative burden. CONCLUSIONS: SR offer advantages in completeness, data extraction, and communication compared to NR. Surgeons perceive them as beneficial for research, quality improvement, and teaching. This review supports the necessity for development of user-friendly SR that seamlessly integrate into pre-existing EMRs, optimising patient care and enhancing the quality of CRC surgical documentation.

Validity of inpatient electronic health record-based measures of oxygen-related therapy in the United States: Lessons applicable for studying COVID-19 endpoints.

INTRODUCTION: During the COVID-19 pandemic, inpatient electronic health records (EHRs) have been used to conduct public health surveillance and assess treatments and outcomes. Invasive mechanical ventilation (MV) and supplemental oxygen (O2) use are markers of severe illness in hospitalized COVID-19 patients. In a large US system (n = 142 hospitals), we assessed documentation of MV and O2 use during COVID-19 hospitalization in administrative data versus nursing documentation. METHODS: We identified 319 553 adult hospitalizations with a COVID-19 diagnosis, February 2020-October 2022, and extracted coded, administrative data for MV or O2. Separately, we developed classification rules for MV or O2 supplementation from semi-structured nursing documentation. We assessed MV and O2 supplementation in administrative data versus nursing documentation and calculated ordinal endpoints of decreasing COVID-19 disease severity. Nursing documentation was considered the gold standard in sensitivity and positive predictive value (PPV) analyses. RESULTS: In nursing documentation, the prevalence of MV and O2 supplementation among COVID-19 hospitalizations was 14% and 75%, respectively. The sensitivity of administrative data was 83% for MV and 41% for O2, with both PPVs above 91%. Concordance between sources was 97% for MV (κ = 0.85), and 54% for O2 (κ = 0.21). For ordinal endpoints, administrative data accurately identified intensive care and MV but underestimated hospitalizations with O2 requirements (42% vs. 18%). CONCLUSIONS: In comparison to nursing documentation, administrative data under-ascertained O2 supplementation but accurately estimated severe endpoints such as MV. Nursing documentation improved ascertainment of O2 among COVID-19 hospitalizations and can capture oxygen requirements in adults hospitalized with COVID-19 or other respiratory illnesses.

Use of statewide financial incentives to improve documentation of hernia and mesh characteristics in ventral hernia repair.

BACKGROUND: Documentation of intraoperative details is critical for understanding and advancing hernia care, but is inconsistent in practice. Therefore, to improve data capture on a statewide level, we implemented a financial incentive targeting documentation of hernia defect size and mesh use. METHODS: The Abdominal Hernia Care Pathway (AHCP), a voluntary pay for performance (P4P) initiative, was introduced in 2021 within the statewide Michigan Surgical Quality Collaborative (MSQC). This consisted of an organizational-level financial incentive for achieving 80% performance on eight specific process measures for ventral hernia surgery, including complete documentation of hernia defect size and location, as well as mesh characteristics and fixation technique. Comparisons were made between AHCP and non-AHCP sites in 2021. RESULTS: Of 69 eligible sites, 47 participated in the AHCP in 2021. There were N = 5362 operations (4169 at AHCP sites; 1193 at non-AHCP sites). At AHCP sites, 69.8% of operations had complete hernia documentation, compared to 50.5% at non-AHCP sites (p < 0.0001). At AHCP sites, 91.4% of operations had complete mesh documentation, compared to 86.5% at non-AHCP sites (p < 0.0001). The site-level hernia documentation goal of 80% was reached by 14 of 47 sites (range 14-100%). The mesh documentation goal was reached by 41 of 47 sites (range 4-100%). CONCLUSIONS: Addition of an organizational-level financial incentive produced marked gains in documentation of intra-operative details across a statewide surgical collaborative. The relatively large effect size-19.3% for hernia-is remarkable among P4P initiatives. This result may have been facilitated by surgeons' direct role in documenting hernia size and mesh use. These improvements in data capture will foster understanding of current hernia practices on a large scale and may serve as a model for improvement in collaboratives nationally.

The association between use of ambient voice technology documentation during primary care patient encounters, documentation burden, and provider burnout.

BACKGROUND: The burden of documentation in the electronic medical record has been cited as a major factor in provider burnout. The aim of this study was to evaluate the association between ambient voice technology, coupled with natural language processing and artificial intelligence (DAX™), on primary care provider documentation burden and burnout. METHODS: An observational study of 110 primary care providers within a community teaching health system. The primary objectives were to determine the association between DAX™ usage and provider burnout scores on the Oldenburg Burnout Inventory (OLBI) as well as the effect on documentation time per patient encounter (minutes). RESULTS: The completion rate for the survey was 75% (83/110) and high DAX™ use (>60% of encounters) was seen in 28% of providers (23/83). High DAX™ use was associated with significantly less burnout on the OLBI disengagement sub-score (MD [Mean Difference] -2.1; 95% confidence interval [CI] -3.8 to -0.4) but not the OLBI disengagement sub-score (-1.0; 95% CI -2.9 to 1.0) or total score (MD -3.0; 95% CI -6.4 to 0.3). Nineteen providers with high implementation of DAX™ had pre and postimplementation data on documentation time per encounter. After DAX™ implementation average documentation time in notes per encounter was significantly reduced by 28.8% (1.8 min; 95% CI 1.4-2.2). CONCLUSIONS: The use of ambient voice technology during patient encounters was associated with significantly reduced documentation burden and primary care provider disengagement but not total provider burnout scores.

Hypertension evaluation and management in new young patients: are we doing our female patients a disservice?

PURPOSE: Cardiovascular disease (CVD) is one of the leading causes of death in women, largely underpinned by hypertension. Current guidelines recommend first-line therapy with a RAAS-blocking agent especially in young people. There are well documented sex disparities in CVD outcomes and management. We evaluate the management of patients with newly diagnosed hypertension in a tertiary care clinic to assess male-female differences in investigation and treatment. METHODS: Clinic letters of all new patients under the age of 51 attending the Glasgow Blood Pressure Clinic between January and December 2023 were reviewed. The primary outcomes measured were first-line treatment choices, deviations from guideline-recommended treatment, investigations for secondary hypertension, and documentation of female-specific risk factors and family planning advice. Secondary outcomes included clinical characteristics such as systolic and diastolic blood pressure at referral and at the new patient appointment, age at diagnosis, age at first appointment, and the number of antihypertensive drugs prescribed at referral. RESULTS: One hundred and five (59:46, M:F) new patient encounters were reviewed after sixteen exclusions for non-attendance and inappropriate clinic coding. Choice of first line antihypertensive agent did not vary between sexes with no deviation from guideline-recommended medical therapy. Men, however, had more biochemical investigations conducted for secondary causes across all ages. This was greatest in those under 40 years old. There was suboptimal documentation of female-specific risk factors (obstetric and gynaecological history), contraceptive drug history and family planning with 35%, 20%, and 15.6%, respectively. CONCLUSION: In 2023, women under 51 years of age seen in a tertiary care hypertension clinic received similar first-line treatment to their male peers. However, relevant female-specific histories were suboptimally documented for these patients. Whilst therapeutic approaches in men and women appear to be similar in this clinic, there are opportunities to improve CVD prevention in women, even in a specialised clinic setting.

Hypertension, or persistent high blood pressure, is a condition that can lead to serious cardiovascular diseases such as stroke and heart failure. Evidence has shown that women have cardiovascular disease more than men and it is the leading cause of death in women in Europe. To understand how male and female patients are treated for hypertension, we examined documented consultations and treatments of 105 patients under the age of 51 (46 women and 59 men) at a Glasgow hypertension clinic in 2023. We found that men had more investigations for specific causes of their hypertension across all ages (men = 88%, women = 61%). Recording of reproductive history (35%), contraceptive drug history (20%) and advice on family planning (15.6%) was not as thorough as they could be. Incorrect management of female reproductive history and contraceptive drug history can increase the risk of long-term hypertension complications, so managing this is crucial. A class of drugs commonly used to manage hypertension called RAAS blockers are dangerous to the foetus when pregnant - another factor to consider when managing young women with high blood pressure. Overall, these findings mean that there may be a need for more thorough consideration of women's health factors in hypertension treatment. By paying attention to these areas, we can enhance long-term cardiovascular health for women.

Lower comorbidity scores and severity levels in Veterans Health Administration hospitals: a cross-sectional study.

BACKGROUND: Previous studies found that documentation of comorbidities differed when Veterans received care within versus outside Veterans Health Administration (VHA). Changes to medical center funding, increased attention to performance reporting, and expansion of Clinical Documentation Improvement programs, however, may have caused coding in VHA to change. METHODS: Using repeated cross-sectional data, we compared Elixhauser-van Walraven scores and Medicare Severity Diagnosis Related Group (DRG) severity levels for Veterans' admissions across settings and payers over time, utilizing a linkage of VHA and all-payer discharge data for 2012-2017 in seven US states. To minimize selection bias, we analyzed records for Veterans admitted to both VHA and non-VHA hospitals in the same year. Using generalized linear models, we adjusted for patient and hospital characteristics. RESULTS: Following adjustment, VHA admissions consistently had the lowest predicted mean comorbidity scores (4.44 (95% CI 4.34-4.55)) and lowest probability of using the most severe DRG (22.1% (95% CI 21.4%-22.8%)). In contrast, Medicare-covered admissions had the highest predicted mean comorbidity score (5.71 (95% CI 5.56-5.85)) and highest probability of using the top DRG (35.3% (95% CI 34.2%-36.4%)). CONCLUSIONS: More effective strategies may be needed to improve VHA documentation, and current risk-adjusted comparisons should account for differences in coding intensity.

Impact of a complex health services intervention in long-term care nursing homes on 3-year overall survival: results from the CoCare study.

BACKGROUND: The Coordinated medical Care (CoCare) project aimed to improve the quality of medical care in nursing homes by optimizing collaboration between nurses and physicians. We analyze the impact of the CoCare intervention on overall survival. METHODS: The effect of time-varying treatment on 3-year overall survival was analyzed with treatment as time-varying covariate within the entire cohort. To reduce bias due to non-random assignment to treatment groups, regression adjustment was applied. Therefore, age, sex, and level of care were used as potential confounders. RESULTS: The study population consisted of 8,893 nursing home residents (NHRs), of which 1,330 participated in the CoCare intervention. The three-year overall survival was 49.8% in the entire cohort. NHRs receiving the intervention were associated with a higher survival probability compared to NHRs of the control group. In a univariable cox model with time-dependent treatment, the intervention was associated with a hazard ratio of 0.70 [95%CI 0.56-0.87, p = 0.002]. After adjustment for age, sex and level of care, the hazard ratio increased to 0.82 but was still significant [95%CI 0.71-0.96, p = 0.011]. CONCLUSION: The analysis shows that optimizing collaboration between nurses and physicians leads to better survival of NHRs in Germany. This adds to the already published favorable cost-benefit ratio of the CoCare intervention and shows that a routine implementation of optimized collaboration between nurses and physicians is highly recommended.

Use of the supportive and palliative care indicators tool (SPICT™) for end-of-life discussions: a scoping review.

BACKGROUND: In order to mitigate the distress associated with life limiting conditions it is essential for all health professionals not just palliative care specialists to identify people with deteriorating health and unmet palliative care needs and to plan care. The SPICT™ tool was designed to assist with this. AIM: The aim was to examine the impact of the SPICT™ on advance care planning conversations and the extent of its use in advance care planning for adults with chronic life-limiting illness. METHODS: In this scoping review records published between 2010 and 2024 reporting the use of the SPICT™, were included unless the study aim was to evaluate the tool for prognostication purposes. Databases searched were EBSCO Medline, PubMed, EBSCO CINAHL, APA Psych Info, ProQuest One Theses and Dissertations Global. RESULTS: From the search results 26 records were reviewed, including two systematic review, two theses and 22 primary research studies. Much of the research was derived from primary care settings. There was evidence that the SPICT™ assists conversations about advance care planning specifically discussion and documentation of advance care directives, resuscitation plans and preferred place of death. The SPICT™ is available in at least eight languages (many versions have been validated) and used in many countries. CONCLUSIONS: Use of the SPICT™ appears to assist advance care planning. It has yet to be widely used in acute care settings and has had limited use in countries beyond Europe. There is a need for further research to validate the tool in different languages.

Dementia patients in palliative care according to data from the German National Hospice and Palliative Care Register (2009-2021).

BACKGROUND: People with dementia are less in focus of palliative care research than other patient groups even though the awareness of their palliative and end-of-life care needs is rising. Empirical data analyses on people with dementia in palliative care services are lacking. AIM: To explore the prevalence of dementia diagnoses as per the ICD criteria among users of various palliative care settings and to compare use of palliative services, care pathways, and outcomes in people with and without a dementia diagnosis. DESIGN: We conducted retrospective analysis of dementia diagnoses as per ICD (F00-F03/G30) in the German National Hospice and Palliative Care Register between 2009 and 2021. The analysis used methods of descriptive and inferential statistics, including the Bonferroni correction for alpha error inflation. SETTING/PARTICIPANTS: We limited the analysis to the subsample of people aged over 64. RESULTS: The prevalence of dementia in the different settings of palliative care was lower than in the age-comparable population: Of the 69,116 data sets included in the analysis, a small minority (3.3%) was coded with dementia as the principal diagnosis. Among patients on inpatient palliative care wards, 0.8% (148 of 19,161) had a dementia diagnosis, as did 2.2% (52 of 2,380) of those under hospital palliative care support teams and 4.3% (2,014 of 46,803) of those receiving specialized palliative care at home. CONCLUSIONS: The records of the German National Hospice and Palliative Care Register suggest that the prevalence of dementia is lower than one might expect from general population data, though numbers are in line with international studies on proportion of dementia patients receiving palliative care. Future research could usefully examine whether this discrepancy stems either from omissions in coding dementia as patients' principal diagnosis respectively from lapses in documentation of a dementia diagnosis previously made, or from barriers to accessing palliative care services or even displays being excluded from palliative care when trying to access it. TRIAL REGISTRATION: No registration.

Leveraging artificial intelligence in neurosurgery-unveiling ChatGPT for neurosurgical discharge summaries and operative reports.

PURPOSE: Chat generative pre-trained transformer (GPT) is a novel large pre-trained natural language processing software that can enable scientific writing amongst a litany of other features. Given this, there is a growing interest in exploring the use of ChatGPT models as a modality to facilitate/assist in the provision of clinical care. METHODS: We investigated the time taken for the composition of neurosurgical discharge summaries and operative reports at a major University hospital. In so doing, we compared currently employed speech recognition software (i.e., SpeaKING) vs novel ChatGPT for three distinct neurosurgical diseases: chronic subdural hematoma, spinal decompression, and craniotomy. Furthermore, factual correctness was analyzed for the abovementioned diseases. RESULTS: The composition of neurosurgical discharge summaries and operative reports with the assistance of ChatGPT leads to a statistically significant time reduction across all three diseases/report types: p < 0.001 for chronic subdural hematoma, p < 0.001 for decompression of spinal stenosis, and p < 0.001 for craniotomy and tumor resection. However, despite a high degree of factual correctness, the preparation of a surgical report for craniotomy proved to be significantly lower (p = 0.002). CONCLUSION: ChatGPT assisted in the writing of discharge summaries and operative reports as evidenced by an impressive reduction in time spent as compared to standard speech recognition software. While promising, the optimal use cases and ethics of AI-generated medical writing remain to be fully elucidated and must be further explored in future studies.

Using ChatGPT-4 to Create Structured Medical Notes From Audio Recordings of Physician-Patient Encounters: Comparative Study.

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.

Experiences of Electronic Health Records' and Client Information Systems' Use on a Mobile Device and Factors Associated With Work Time Savings Among Practical Nurses: Cross-Sectional Study.

BACKGROUND: The transmission of clinical information in nursing predominantly occurs through digital solutions, such as computers and mobile devices, in today's era. Various technological systems, including electronic health records (EHRs) and client information systems (CISs), can be seamlessly integrated with mobile devices. The use of mobile devices is anticipated to rise, particularly as long-term care is increasingly delivered in environments such as clients' homes, where computers are not readily accessible. However, there is a growing need for more user-centered data to ensure that mobile devices effectively support practical nurses in their daily activities. OBJECTIVE: This study aims to analyze practical nurses' experiences of using EHRs or CISs on a mobile device in their daily practice. In addition, it aims to examine the factors associated with work time savings when using EHRs/CISs on a mobile device. METHODS: A cross-sectional study using an electronic survey was conducted in spring 2022. A total of 3866 practical nurses participated in the survey based on self-assessment. The sample was limited to practical nurses who used EHRs or CISs on a mobile device and worked in home care or service housing within the social welfare or health care sector (n=1014). Logistic regression analysis was used to explore the factors associated with work time savings. RESULTS: The likelihood of perceiving work time savings was higher among more experienced EHR/CIS users compared with those with less experience (odds ratio [OR] 1.59, 95% CI 1.30-1.94). Participants with 0-5 years of work experience were more likely to experience work time savings compared with those who had worked 21 years or more (OR 2.41, 95% CI 1.43-4.07). Practical nurses in home care were also more likely to experience work time savings compared with those working in service housing (OR 1.95, 95% CI 1.23-3.07). A lower grade given for EHRs/CISs was associated with a reduced likelihood of experiencing work time savings (OR 0.76, 95% CI 0.66-0.89). Participants who documented client data in a public area were more likely to experience work time savings compared with those who did so in the nurses' office (OR 2.33, 95% CI 1.27-4.25). Practical nurses who found documentation of client data on a mobile device easy (OR 3.05, 95% CI 2.14-4.34) were more likely to experience work time savings compared with those who did not. Similarly, participants who believed that documentation of client data on a mobile device reduced the need to memorize things (OR 4.10, 95% CI 2.80-6.00) were more likely to experience work time savings compared with those who did not. CONCLUSIONS: To enhance the proportion of practical nurses experiencing work time savings, we recommend that organizations offer comprehensive orientation and regular education sessions tailored for mobile device users who have less experience using EHRs or CISs and find mobile devices less intuitive to use.

Effect of Digital Early Warning Scores on Hospital Vital Sign Observation Protocol Adherence: Stepped-Wedge Evaluation.

BACKGROUND: Early warning scores (EWS) are routinely used in hospitals to assess a patient's risk of deterioration. EWS are traditionally recorded on paper observation charts but are increasingly recorded digitally. In either case, evidence for the clinical effectiveness of such scores is mixed, and previous studies have not considered whether EWS leads to changes in how deteriorating patients are managed. OBJECTIVE: This study aims to examine whether the introduction of a digital EWS system was associated with more frequent observation of patients with abnormal vital signs, a precursor to earlier clinical intervention. METHODS: We conducted a 2-armed stepped-wedge study from February 2015 to December 2016, over 4 hospitals in 1 UK hospital trust. In the control arm, vital signs were recorded using paper observation charts. In the intervention arm, a digital EWS system was used. The primary outcome measure was time to next observation (TTNO), defined as the time between a patient's first elevated EWS (EWS ≥3) and subsequent observations set. Secondary outcomes were time to death in the hospital, length of stay, and time to unplanned intensive care unit admission. Differences between the 2 arms were analyzed using a mixed-effects Cox model. The usability of the system was assessed using the system usability score survey. RESULTS: We included 12,802 admissions, 1084 in the paper (control) arm and 11,718 in the digital EWS (intervention) arm. The system usability score was 77.6, indicating good usability. The median TTNO in the control and intervention arms were 128 (IQR 73-218) minutes and 131 (IQR 73-223) minutes, respectively. The corresponding hazard ratio for TTNO was 0.99 (95% CI 0.91-1.07; P=.73). CONCLUSIONS: We demonstrated strong clinical engagement with the system. We found no difference in any of the predefined patient outcomes, suggesting that the introduction of a highly usable electronic system can be achieved without impacting clinical care. Our findings contrast with previous claims that digital EWS systems are associated with improvement in clinical outcomes. Future research should investigate how digital EWS systems can be integrated with new clinical pathways adjusting staff behaviors to improve patient outcomes.

Improving the Prognostic Evaluation Precision of Hospital Outcomes for Heart Failure Using Admission Notes and Clinical Tabular Data: Multimodal Deep Learning Model.

BACKGROUND: Clinical notes contain contextualized information beyond structured data related to patients' past and current health status. OBJECTIVE: This study aimed to design a multimodal deep learning approach to improve the evaluation precision of hospital outcomes for heart failure (HF) using admission clinical notes and easily collected tabular data. METHODS: Data for the development and validation of the multimodal model were retrospectively derived from 3 open-access US databases, including the Medical Information Mart for Intensive Care III v1.4 (MIMIC-III) and MIMIC-IV v1.0, collected from a teaching hospital from 2001 to 2019, and the eICU Collaborative Research Database v1.2, collected from 208 hospitals from 2014 to 2015. The study cohorts consisted of all patients with critical HF. The clinical notes, including chief complaint, history of present illness, physical examination, medical history, and admission medication, as well as clinical variables recorded in electronic health records, were analyzed. We developed a deep learning mortality prediction model for in-hospital patients, which underwent complete internal, prospective, and external evaluation. The Integrated Gradients and SHapley Additive exPlanations (SHAP) methods were used to analyze the importance of risk factors. RESULTS: The study included 9989 (16.4%) patients in the development set, 2497 (14.1%) patients in the internal validation set, 1896 (18.3%) in the prospective validation set, and 7432 (15%) patients in the external validation set. The area under the receiver operating characteristic curve of the models was 0.838 (95% CI 0.827-0.851), 0.849 (95% CI 0.841-0.856), and 0.767 (95% CI 0.762-0.772), for the internal, prospective, and external validation sets, respectively. The area under the receiver operating characteristic curve of the multimodal model outperformed that of the unimodal models in all test sets, and tabular data contributed to higher discrimination. The medical history and physical examination were more useful than other factors in early assessments. CONCLUSIONS: The multimodal deep learning model for combining admission notes and clinical tabular data showed promising efficacy as a potentially novel method in evaluating the risk of mortality in patients with HF, providing more accurate and timely decision support.