Hybrid artificial intelligence outcome prediction using features extraction from stress perfusion cardiac magnetic resonance images and electronic health records.

Background: Prediction of clinical outcomes in coronary artery disease (CAD) has been conventionally achieved using clinical risk factors. The relationship between imaging features and outcome is still not well understood. This study aims to use artificial intelligence to link image features with mortality outcome. Methods: A retrospective study was performed on patients who had stress perfusion cardiac magnetic resonance (SP-CMR) between 2011 and 2021. The endpoint was all-cause mortality. Convolutional neural network (CNN) was used to extract features from stress perfusion images, and multilayer perceptron (MLP) to extract features from electronic health records (EHRs), both networks were concatenated in a hybrid neural network (HNN) to predict study endpoint. Image CNN was trained to predict study endpoint directly from images. HNN and image CNN were compared with a linear clinical model using area under the curve (AUC), F1 scores, and McNemar's test. Results: Total of 1,286 cases were identified, with 201 death events (16%). The clinical model had good performance (AUC =80%, F1 score =37%). Best Image CNN model showed AUC =72% and F1 score =38%. HNN outperformed the other two models (AUC =82%, F1 score =43%). McNemar's test showed statistical difference between image CNN and both clinical model (P<0.01) and HNN (P<0.01). There was no significant difference between HNN and clinical model (P=0.15). Conclusions: Death in patients with suspected or known CAD can be predicted directly from stress perfusion images without clinical knowledge. Prediction can be improved by HNN that combines clinical and SP-CMR images.

Clinical Decision Support System for Guidelines-Based Treatment of Gonococcal Infections, Screening for HIV, and Prescription of Pre-Exposure Prophylaxis: Design and Implementation Study.

BACKGROUND: The syndemic nature of gonococcal infections and HIV provides an opportunity to develop a synergistic intervention tool that could address the need for adequate treatment for gonorrhea, screen for HIV infections, and offer pre-exposure prophylaxis (PrEP) for persons who meet the criteria. By leveraging information available on electronic health records, a clinical decision support (CDS) system tool could fulfill this need and improve adherence to Centers for Disease Control and Prevention (CDC) treatment and screening guidelines for gonorrhea, HIV, and PrEP. OBJECTIVE: The goal of this study was to translate portions of CDC treatment guidelines for gonorrhea and relevant portions of HIV screening and prescribing PrEP that stem from a diagnosis of gonorrhea as an electronic health record-based CDS intervention. We also assessed whether this CDS solution worked in real-world clinic. METHODS: We developed 4 tools for this CDS intervention: a form for capturing sexual history information (SmartForm), rule-based alerts (best practice advisory), an enhanced sexually transmitted infection (STI) order set (SmartSet), and a documentation template (SmartText). A mixed methods pre-post design was used to measure the feasibility, use, and usability of the CDS solution. The study period was 12 weeks with a baseline patient sample of 12 weeks immediately prior to the intervention period for comparison. While the entire clinic had access to the CDS solution, we focused on a subset of clinicians who frequently engage in the screening and treatment of STIs within the clinical site under the name "X-Clinic." We measured the use of the CDS solution within the population of patients who had either a confirmed gonococcal infection or an STI-related chief complaint. We conducted 4 midpoint surveys and 3 key informant interviews to quantify perception and impact of the CDS solution and solicit suggestions for potential future enhancements. The findings from qualitative data were determined using a combination of explorative and comparative analysis. Statistical analysis was conducted to compare the differences between patient populations in the baseline and intervention periods. RESULTS: Within the X-Clinic, the CDS alerted clinicians (as a best practice advisory) in one-tenth (348/3451, 10.08%) of clinical encounters. These 348 encounters represented 300 patients; SmartForms were opened for half of these patients (157/300, 52.33%) and was completed for most for them (147/300, 89.81%). STI test orders (SmartSet) were initiated by clinical providers in half of those patients (162/300, 54%). HIV screening was performed during about half of those patient encounters (191/348, 54.89%). CONCLUSIONS: We successfully built and implemented multiple CDC treatment and screening guidelines into a single cohesive CDS solution. The CDS solution was integrated into the clinical workflow and had a high rate of use.

Illuminating the landscape of high-level clinical trial opportunities in the All of Us Research Program.

OBJECTIVE: With its size and diversity, the All of Us Research Program has the potential to power and improve representation in clinical trials through ancillary studies like Nutrition for Precision Health. We sought to characterize high-level trial opportunities for the diverse participants and sponsors of future trial investment. MATERIALS AND METHODS: We matched All of Us participants with available trials on ClinicalTrials.gov based on medical conditions, age, sex, and geographic location. Based on the number of matched trials, we (1) developed the Trial Opportunities Compass (TOC) to help sponsors assess trial investment portfolios, (2) characterized the landscape of trial opportunities in a phenome-wide association study (PheWAS), and (3) assessed the relationship between trial opportunities and social determinants of health (SDoH) to identify potential barriers to trial participation. RESULTS: Our study included 181 529 All of Us participants and 18 634 trials. The TOC identified opportunities for portfolio investment and gaps in currently available trials across federal, industrial, and academic sponsors. PheWAS results revealed an emphasis on mental disorder-related trials, with anxiety disorder having the highest adjusted increase in the number of matched trials (59% [95% CI, 57-62]; P < 1e-300). Participants from certain communities underrepresented in biomedical research, including self-reported racial and ethnic minorities, had more matched trials after adjusting for other factors. Living in a nonmetropolitan area was associated with up to 13.1 times fewer matched trials. DISCUSSION AND CONCLUSION: All of Us data are a valuable resource for identifying trial opportunities to inform trial portfolio planning. Characterizing these opportunities with consideration for SDoH can provide guidance on prioritizing the most pressing barriers to trial participation.

Outcomes in patients treated with loop diuretics without a diagnosis of heart failure: a retrospective cohort study.

BACKGROUND: Loop diuretics are commonly prescribed in the community, not always to patients with a recorded diagnosis of heart failure (HF). The rate of HF events in patients prescribed loop diuretics without a diagnosis of HF is unknown. METHODS: This was a propensity-matched cohort study using data from the Clinical Practice Research Datalink, Hospital Episode Statistics and Office of National Statistics in the UK. Patients prescribed a loop diuretic without a diagnosis of HF (loop diuretic group) between 1 January 2010 and 31 December 2015 were compared with patients with HF (HF group)-analysis A, and patients with risk factors for HF (either ischaemic heart disease, or diabetes and hypertension-at-risk group)-analysis B. The primary endpoint was an HF event (a composite of presentation with HF symptoms, HF hospitalisation, HF diagnosis (analysis B only) and all-cause mortality). RESULTS: From a total population of 180 384 patients (78 968 in the loop diuretic group, 28 177 in the HF group and 73 239 in the at-risk group), there were 59 694 patients, 22 352 patients and 57 219 patients in the loop diuretic, HF and at-risk groups, respectively, after exclusion criteria were applied. After propensity matching for age, sex and comorbidities, patients in the loop diuretic group had a similar rate of HF events as those in the HF group (71.9% vs 72.1%; HR=0.92 (95% CI 0.90 to 0.94); p<0.001), and twice as those in the at-risk group (59.2% vs 35.7%; HR=2.04 (95% CI 2.00 to 2.08); p<0.001). CONCLUSIONS: Patients prescribed a loop diuretic without a recorded diagnosis of HF experience HF events at a rate comparable with that of patients with a recorded diagnosis of HF; many of these patients may have undiagnosed HF.

IoT-based external attacks aware secure healthcare framework using blockchain and SB-RNN-NVS-FU techniques.

BACKGROUND: In recent times, there has been widespread deployment of Internet of Things (IoT) applications, particularly in the healthcare sector, where computations involving user-specific data are carried out on cloud servers. However, the network nodes in IoT healthcare are vulnerable to an increased level of security threats. OBJECTIVE: This paper introduces a secure Electronic Health Record (EHR) framework with a focus on IoT. METHODS: Initially, the IoT sensor nodes are designated as registered patients and undergo initialization. Subsequently, a trust evaluation is conducted, and the clustering of trusted nodes is achieved through the application of Tasmanian Devil Optimization (STD-TDO) utilizing the Student's T-Distribution. Utilizing the Transposition Cipher-Squared random number generator-based-Elliptic Curve Cryptography (TCS-ECC), the clustered nodes encrypt four types of sensed patient data. The resulting encrypted data undergoes hashing and is subsequently added to the blockchain. This configuration functions as a network, actively monitored to detect any external attacks. To accomplish this, a feature reputation score is calculated for the network's features. This score is then input into the Swish Beta activated-Recurrent Neural Network (SB-RNN) model to classify potential attacks. The latest transactions on the blockchain are scrutinized using the Neutrosophic Vague Set Fuzzy (NVS-Fu) algorithm to identify any double-spending attacks on non-compromised nodes. Finally, genuine nodes are granted permission to decrypt medical records. RESULTS: In the experimental analysis, the performance of the proposed methods was compared to existing models. The results demonstrated that the suggested approach significantly increased the security level to 98%, reduced attack detection time to 1300 ms, and maximized accuracy to 98%. Furthermore, a comprehensive comparative analysis affirmed the reliability of the proposed model across all metrics. CONCLUSION: The proposed healthcare framework's efficiency is proved by the experimental evaluation.

System-Wide Thromboprophylaxis Interventions for Hospitalized Patients at Risk of Venous Thromboembolism: Focus on Cross-Platform Clinical Decision Support.

Thromboprophylaxis of hospitalized patients at risk of venous thromboembolism (VTE) presents challenges owing to patient heterogeneity and lack of adoption of evidence-based methods. Intuitive practices for thromboprophylaxis have resulted in many patients being inappropriately prophylaxed. We conducted a narrative review summarizing system-wide thromboprophylaxis interventions in hospitalized patients. Multiple interventions for thromboprophylaxis have been tested, including multifaceted approaches such as national VTE prevention programs with audits, pre-printed order entry, passive alerts (either human or electronic), and more recently, the use of active clinical decision support (CDS) tools incorporated into electronic health records (EHRs). Multifaceted health-system and order entry interventions have shown mixed results in their ability to increase appropriate thromboprophylaxis and reduce VTE unless mandated through a national VTE prevention program, though the latter approach is potentially costly and effort- and time-dependent. Studies utilizing passive human or electronic alerts have also shown mixed results in increasing appropriate thromboprophylaxis and reducing VTE. Recently, a universal cloud-based and EHR-agnostic CDS VTE tool incorporating a validated VTE risk score revealed high adoption and effectiveness in increasing appropriate thromboprophylaxis and reducing major thromboembolism. Active CDS tools hold promise in improving appropriate thromboprophylaxis, especially with further refinement and widespread implementation within various EHRs and clinical workflows.

Risk of herpes zoster in adults with SARS-CoV-2 infection in Spain: a population-based, retrospective cohort study.

BACKGROUND: We aimed to compare the risk of herpes zoster (HZ) in adults with and without laboratory-confirmed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. METHODS: This retrospective dynamic cohort study analyzed data from a public healthcare database in Spain between November 2020 and October 2021. The main outcome was incident cases of HZ in individuals ≥ 18-year-old. Relative risk (RR) of HZ in SARS-CoV-2-confirmed versus SARS-CoV-2-free individuals was estimated by a multivariable negative binomial regression adjusted by age, sex, and comorbidities. RESULTS: Data from 4,085,590 adults were analyzed. The overall HZ incidence rate in adults was 5.76 (95% confidence interval [CI], 5.66-5.85) cases per 1,000 person-years. Individuals ≥ 18-year-old with SARS-CoV-2-confirmed infection had a 19% higher risk of developing HZ versus SARS-CoV-2-free ≥ 18-year-olds (adjusted RR = 1.19; 95% CI, 1.09-1.29); this percentage was 16% (adjusted RR = 1.16; 95% CI, 1.05-1.29) in ≥ 50-year-olds. Severe (hospitalized) cases of SARS-CoV-2 infection had a 64% (if ≥ 18 years old) or 44% (if ≥ 50 years old) higher risk of HZ versus non-hospitalized cases. CONCLUSIONS: These results support an association between SARS-CoV-2 infection and HZ, with a greater HZ risk in severe cases of SARS-CoV-2 infection.

A real-world exploration into clinical outcomes of direct oral anticoagulant therapy in people with chronic kidney disease: a large hospital-based study.

BACKGROUND: There is limited evidence to support definite clinical outcomes of direct oral anticoagulant (DOAC) therapy in chronic kidney disease (CKD). By identifying the important variables associated with clinical outcomes following DOAC administration in patients in different stages of CKD, this study aims to assess this evidence gap. METHODS: An anonymised dataset comprising 97,413 patients receiving DOAC therapy in a tertiary health setting was systematically extracted from the multidimensional electronic health records and prepared for analysis. Machine learning classifiers were applied to the prepared dataset to select the important features which informed covariate selection in multivariate logistic regression analysis. RESULTS: For both CKD and non-CKD DOAC users, features such as length of stay, treatment days, and age were ranked highest for relevance to adverse outcomes like death and stroke. Patients with Stage 3a CKD had significantly higher odds of ischaemic stroke (OR 2.45, 95% Cl: 2.10-2.86; p = 0.001) and lower odds of all-cause mortality (OR 0.87, 95% Cl: 0.79-0.95; p = 0.001) on apixaban therapy. In patients with CKD (Stage 5) receiving apixaban, the odds of death were significantly lowered (OR 0.28, 95% Cl: 0.14-0.58; p = 0.001), while the effect on ischaemic stroke was insignificant. CONCLUSIONS: A positive effect of DOAC therapy was observed in advanced CKD. Key factors influencing clinical outcomes following DOAC administration in patients in different stages of CKD were identified. These are crucial for designing more advanced studies to explore safer and more effective DOAC therapy for the population.

Open notes in psychotherapy: An exploratory mixed methods survey of psychotherapy students in Switzerland.

Background: In a growing number of countries, patients are offered access to their full online clinical records, including the narrative reports written by clinicians (the latter, referred to as "open notes"). Even in countries with mature patient online record access, access to psychotherapy notes is not mandatory. To date, no research has explored the views of psychotherapy trainees about open notes. Objective: This study aimed to explore the opinions of psychotherapy trainees in Switzerland about patients' access to psychotherapists' free-text summaries. Methods: We administered a web-based mixed methods survey to 201 psychotherapy trainees to explore their familiarity with and opinions about the impact on patients and psychotherapy practice of offering patients online access to their psychotherapy notes. Descriptive statistics were used to analyze the 42-item survey, and qualitative descriptive analysis was employed to examine written responses to four open-ended questions. Results: Seventy-two (35.8%) trainees completed the survey. Quantitative results revealed mixed views about open notes. 75% agreed that, in general open notes were a good idea, and 94.1% agreed that education about open notes should be part of psychotherapy training. When considering impact on patients and psychotherapy, four themes emerged: (a) negative impact on therapy; (b) positive impact on therapy; (c) impact on patients; and (d) documentation. Students identified concerns related to increase in workload, harm to the psychotherapeutic relationship, and compromised quality of records. They also identified many potential benefits including better patient communication and informed consent processes. In describing impact on different therapy types, students believed that open notes might have differential impact depending on the psychotherapy approaches. Conclusions: Sharing psychotherapy notes is not routine but is likely to expand. This mixed methods study provides timely insights into the views of psychotherapy trainees regarding the impact of open notes on patient care and psychotherapy practice.

Comparing the Effect of Early Versus Delayed Metformin Treatment on Glycaemic Parameters Among Australian Adults With Incident Diabetes: Evidence Using a National General Practice Database.

PURPOSE: To compare the effect of early vs delayed metformin treatment for glycaemic management among patients with incident diabetes. METHODS: Cohort study using electronic health records of regular patients (1+ visits per year in 3 consecutive years) aged 40+ years with 'incident' diabetes attending Australian general practices (MedicineInsight, 2011-2018). Patients with incident diabetes were defined as those who had a) 12+ months of medical data before the first recording of a diabetes diagnosis AND b) a diagnosis of 'diabetes' recorded at least twice in their electronic medical records or a diagnosis of 'diabetes' recorded only once combined with at least 1 abnormal glycaemic result (i.e., HbA1c ≥6.5%, fasting blood glucose [FBG] ≥7.0 mmol/L, or oral glucose tolerance test ≥11.1mmol/L) in the preceding 3 months. The effect of early (<3 months), timely (3-6 months), or delayed (6-12 months) initiation of metformin treatment vs no metformin treatment within 12 months of diagnosis on HbA1c and FBG levels 3 to 24 months after diagnosis was compared using linear regression and augmented inverse probability weighted models. Patients initially managed with other antidiabetic medications (alone or combined with metformin) were excluded. FINDINGS: Of 18,856 patients with incident diabetes, 38.8% were prescribed metformin within 3 months, 3.9% between 3 and 6 months, and 6.2% between 6 and 12 months after diagnosis. The untreated group had the lowest baseline parameters (mean HbA1c 6.4%; FBG 6.9mmol/L) and maintained steady levels throughout follow-up. Baseline glycaemic parameters for those on early treatment with metformin (<3 months since diagnosis) were the highest among all groups (mean HbA1c 7.6%; FBG 8.8mmol/L), reaching controlled levels at 3 to 6 months (mean HbA1c 6.5%; FBG 6.9mmol/L) with sustained improvement until the end of follow-up (mean HbA1c 6.4%; FBG 6.9mmol/L at 18-24 months). Patients with timely and delayed treatment also improved their glycaemic parameters after initiating treatment (timely treatment: mean HbA1c 7.3% and FBG 8.3mmol/L at 3-6 months; 6.6% and 6.9mmol/L at 6-12 months; delayed treatment: mean HbA1c 7.2% and FBG 8.4mmol/L at 6-12 months; 6.7% and 7.1mmol/L at 12-18 months). Compared to those not managed with metformin, the corresponding average treatment effect for HbA1c at 18-24 months was +0.04% (95%CI -0.05;0.10) for early, +0.24% (95%CI 0.11;0.37) for timely, and +0.29% (95%CI 0.20;0.39) for delayed treatment. IMPLICATIONS: Early metformin therapy (<3 months) for patients recently diagnosed with diabetes consistently improved HbA1c and FBG levels in the first 24 months of diagnosis.

Automated Extraction of Stroke Severity from Unstructured Electronic Health Records using Natural Language Processing.

BACKGROUND: Multi-center electronic health records (EHR) can support quality improvement initiatives and comparative effectiveness research in stroke care. However, limitations of EHR-based research include challenges in abstracting key clinical variables from non-structured data at scale. This is further compounded by missing data. Here we develop a natural language processing (NLP) model that automatically reads EHR notes to determine the NIH stroke scale (NIHSS) score of patients with acute stroke. METHODS: The study included notes from acute stroke patients (>= 18 years) admitted to the Massachusetts General Hospital (MGH) (2015-2022). The MGH data were divided into training (70%) and hold-out test (30%) sets. A two-stage model was developed to predict the admission NIHSS. A linear model with the least absolute shrinkage and selection operator (LASSO) was trained within the training set. For notes in the test set where the NIHSS was documented, the scores were extracted using regular expressions (stage 1), for notes where NIHSS was not documented, LASSO was used for prediction (stage 2). The reference standard for NIHSS was obtained from Get With The Guidelines Stroke Registry. The two-stage model was tested on the hold-out test set and validated in the MIMIC-III dataset (Medical Information Mart for Intensive Care-MIMIC III 2001-2012) v1.4, using root mean squared error (RMSE) and Spearman correlation (SC). RESULTS: We included 4,163 patients (MGH = 3,876; MIMIC = 287); average age of 69 [SD 15] years; 53% male, and 72% white. 90% patients had ischemic stroke and 10% hemorrhagic stroke. The two-stage model achieved a RMSE [95% CI] of 3.13 [2.86-3.41] (SC = 0.90 [0.88-0. 91]) in the MGH hold-out test set and 2.01 [1.58-2.38] (SC = 0.96 [0.94-0.97]) in the MIMIC validation set. CONCLUSIONS: The automatic NLP-based model can enable large-scale stroke severity phenotyping from EHR and therefore support real-world quality improvement and comparative effectiveness studies in stroke.

Development and Evaluation of Surveillance System for Identifying Jail-Associated COVID-19 Cases in Minnesota, USA, 2022.

Confinement facilities are high-risk settings for the spread of infectious disease, necessitating timely surveillance to inform public health action. To identify jail-associated COVID-19 cases from electronic laboratory reports maintained in the Minnesota Electronic Disease Surveillance System (MEDSS), Minnesota, USA, the Minnesota Department of Health developed a surveillance system that used keyword and address matching (KAM). The KAM system used a SAS program (SAS Institute Inc., https://www.sas.com) and an automated program within MEDSS to identify confinement keywords and addresses. To evaluate KAM, we matched jail booking data from the Minnesota Statewide Supervision System by full name and birthdate to the MEDSS records of adults with COVID-19 for 2022. The KAM system identified 2,212 cases in persons detained in jail; sensitivity was 92.40% and specificity was 99.95%. The success of KAM demonstrates its potential to be applied to other diseases and congregate-living settings for real-time surveillance without added reporting burden.

Using interoperable nursing care data to improve outcomes for multiple traumas patients with Impaired Physical Mobility.

AIM(S): To demonstrate how interoperable nursing care data can be used by nurses to create a more holistic understanding of the healthcare needs of multiple traumas patients with Impaired Physical Mobility. By proposing and validating linkages for the nursing diagnosis of Impaired Physical Mobility in multiple trauma patients by mapping to the Nursing Outcomes Classification (NOC) and Nursing Interventions Classification (NIC) equivalent terms using free-text nursing documentation. DESIGN: A descriptive cross-sectional design, combining quantitative analysis of interoperable data sets and the Kappa's coefficient score with qualitative insights from cross-mapping methodology and nursing professionals' consensus. METHODS: Cross-mapping methodology was conducted in a Brazilian Level 1 Trauma Center using de-identified records of adult patients with a confirmed medical diagnosis of multiple traumas and Impaired Physical Mobility (a nursing diagnosis). The hospital nursing free-text records were mapped to NANDA-I, NIC, NOC and NNN linkages were identified. The data records were retrieved for admissions from September to October 2020 and involved medical and nursing records. Three expert nurses evaluated the cross-mapping and linkage results using a 4-point Likert-type scale and Kappa's coefficient. RESULTS: The de-identified records of 44 patients were evaluated and then were mapped to three NOCs related to nurses care planning: (0001) Endurance; (0204) Immobility Consequences: Physiological, and (0208) Mobility and 13 interventions and 32 interrelated activities: (6486) Environmental Management: Safety; (0840) Positioning; (3200) Aspiration Precautions; (1400) Pain Management; (0940) Traction/Immobilization Care; (3540) Pressure Ulcer Prevention; (3584) Skincare: Topical Treatment; (1100) Nutrition Management; (3660) Wound Care; (1804) Self-Care Assistance: Toileting; (1801) Self-Care Assistance: Bathing/Hygiene; (4130) Fluid Monitoring; and (4200) Intravenous Therapy. The final version of the constructed NNN Linkages identified 37 NOCs and 41 NICs. CONCLUSION: These valid NNN linkages for patients with multiple traumas can serve as a valuable resource that enables nurses, who face multiple time constraints, to make informed decisions efficiently. This approach of using evidence-based linkages like the one developed in this research holds high potential for improving patient's safety and outcomes. NO PATIENT OR PUBLIC CONTRIBUTION: In this study, there was no direct involvement of patients, service users, caregivers or public members in the design, conduct, analysis and interpretation of data or preparation of the manuscript. The study focused solely on analysing existing de-identified medical and nursing records to propose and validate linkages for nursing diagnoses.

Impact of Remote Medical Devices on Utilization of Medical Services in Pediatric Patients with Upper Respiratory Infections: A Retrospective Study.

Background: Remote mobile examination devices in telemedicine are a new technology in healthcare. Objective: To assess the utilization of visits using remote medical devices. Methods: A retrospective analysis of follow-up visits, referrals, laboratory testing and antibiotic prescriptions of 470,845 children's video visits with and without remote medical examination device and in-clinic visits. Results: Rates of follow-up visits, referrals and laboratory tests were higher in video visits compared to visit with medical device (OR of 1.27, 1.08, 1.93 respectfully). For in-clinic visits, rates of follow-up were lower but higher for referrals to subspecialists and laboratory test referrals when compared to telemedicine. Antibiotic prescriptions were provided at a lower rate in video visits compared to visits with a medical device (OR = 0.48) and in-clinic visits. Conclusions: Incorporating a remote medical device may reduce follow up visits, referrals and laboratory tests compared to a video visit without a device. The prevalence of antibiotic prescriptions did not escalate in telemedicine consultations.

OpenSAFELY: The impact of COVID-19 on azathioprine, leflunomide and methotrexate monitoring, and factors associated with change in monitoring rate.

AIMS: The COVID-19 pandemic created unprecedented pressure on healthcare services. This study investigates whether disease-modifying antirheumatic drug (DMARD) safety monitoring was affected during the COVID-19 pandemic. METHODS: A population-based cohort study was conducted using the OpenSAFELY platform to access electronic health record data from 24.2 million patients registered at general practices using TPP's SystmOne software. Patients were included for further analysis if prescribed azathioprine, leflunomide or methotrexate between November 2019 and July 2022. Outcomes were assessed as monthly trends and variation between various sociodemographic and clinical groups for adherence with standard safety monitoring recommendations. RESULTS: An acute increase in the rate of missed monitoring occurred across the study population (+12.4 percentage points) when lockdown measures were implemented in March 2020. This increase was more pronounced for some patient groups (70-79 year-olds: +13.7 percentage points; females: +12.8 percentage points), regions (North West: +17.0 percentage points), medications (leflunomide: +20.7 percentage points) and monitoring tests (blood pressure: +24.5 percentage points). Missed monitoring rates decreased substantially for all groups by July 2022. Consistent differences were observed in overall missed monitoring rates between several groups throughout the study. CONCLUSION: DMARD monitoring rates temporarily deteriorated during the COVID-19 pandemic. Deterioration coincided with the onset of lockdown measures, with monitoring rates recovering rapidly as lockdown measures were eased. Differences observed in monitoring rates between medications, tests, regions and patient groups highlight opportunities to tackle potential inequalities in the provision or uptake of monitoring services. Further research should evaluate the causes of the differences identified between groups.

Predicting pressure injury risk in hospitalised patients using machine learning with electronic health records: a US multilevel cohort study.

OBJECTIVE: To predict the risk of hospital-acquired pressure injury using machine learning compared with standard care. DESIGN: We obtained electronic health records (EHRs) to structure a multilevel cohort of hospitalised patients at risk for pressure injury and then calibrate a machine learning model to predict future pressure injury risk. Optimisation methods combined with multilevel logistic regression were used to develop a predictive algorithm of patient-specific shifts in risk over time. Machine learning methods were tested, including random forests, to identify predictive features for the algorithm. We reported the results of the regression approach as well as the area under the receiver operating characteristics (ROC) curve for predictive models. SETTING: Hospitalised inpatients. PARTICIPANTS: EHRs of 35 001 hospitalisations over 5 years across 2 academic hospitals. MAIN OUTCOME MEASURE: Longitudinal shifts in pressure injury risk. RESULTS: The predictive algorithm with features generated by machine learning achieved significantly improved prediction of pressure injury risk (p<0.001) with an area under the ROC curve of 0.72; whereas standard care only achieved an area under the ROC curve of 0.52. At a specificity of 0.50, the predictive algorithm achieved a sensitivity of 0.75. CONCLUSIONS: These data could help hospitals conserve resources within a critical period of patient vulnerability of hospital-acquired pressure injury which is not reimbursed by US Medicare; thus, conserving between 30 000 and 90 000 labour-hours per year in an average 500-bed hospital. Hospitals can use this predictive algorithm to initiate a quality improvement programme for pressure injury prevention and further customise the algorithm to patient-specific variation by facility.

Timing of antibiotic treatment identifies distinct clinical presentations among patients presenting with suspected septic shock.

Objective: Recent clinical guidelines for sepsis management emphasize immediate antibiotic initiation for suspected septic shock. Though hypotension is a high-risk marker of sepsis severity, prior studies have not considered the precise timing of hypotension in relation to antibiotic initiation and how clinical characteristics and outcomes may differ. Our objective was to evaluate antibiotic initiation in relation to hypotension to characterize differences in sepsis presentation and outcomes in patients with suspected septic shock. Methods: Adults presenting to the emergency department (ED) June 2012-December 2018 diagnosed with sepsis (Sepsis-III electronic health record [EHR] criteria) and hypotension (non-resolving for ≥30 min, systolic blood pressure <90 mmHg) within 24 h. We categorized patients who received antibiotics before hypotension ("early"), 0-60 min after ("immediate"), and >60 min after ("late") treatment. Results: Among 2219 patients, 55% received early treatment, 13% immediate, and 32% late. The late subgroup often presented to the ED with hypotension (median 0 min) but received antibiotics a median of 191 min post-ED presentation. Clinical characteristics notable for this subgroup included higher prevalence of heart failure and liver disease (p < 0.05) and later onset of systemic inflammatory response syndrome (SIRS) criteria compared to early/immediate treatment subgroups (median 87 vs. 35 vs. 20 min, p < 0.0001). After adjustment, there was no difference in clinical outcomes among treatment subgroups. Conclusions: There was significant heterogeneity in presentation and timing of antibiotic initiation for suspected septic shock. Patients with later treatment commonly had hypotension on presentation, had more hypotension-associated comorbidities, and developed overt markers of infection (eg, SIRS) later. While these factors likely contribute to delays in clinician recognition of suspected septic shock, it may not impact sepsis outcomes.

Sex differences in the intensity of statin prescriptions at initiation in a primary care setting.

BACKGROUND: Current guidelines for the prevention and management of cardiovascular diseases (CVD) provide similar recommendations for the use of statins in both women and men. In this study, we assessed sex differences in the intensity of statin prescriptions at initiation and in the achievement of treatment targets, among individuals without and with CVD, in a primary care setting. METHODS: Electronic health record data from statin users were extracted from the PHARMO Data Network. Poisson regressions were used to investigate sex differences in statin intensity and in the achievement of treatment targets. Analyses were stratified by age group, disease status and/or CVD risk category. RESULTS: We included 82 714 individuals (46% women) aged 40-99 years old. In both sexes, the proportion of individuals with a dispensed prescription for high-intensity statin at initiation increased between 2011 and 2020. Women were less likely to be prescribed high-intensity statins as compared with men, both in the subgroups without a history of CVD (risk ratio (RR) 0.69 (95% CI: 0.63 to 0.75)) and with CVD (RR 0.77 (95% CI: 0.74 to 0.81)). Women were less likely than men to achieve target levels of low-density lipoprotein cholesterol following statin initiation in the subgroup without CVD (RR 0.98 (95% CI: 0.97 to 1.00)) and with a history of CVD (RR 0.94 (95% CI: 0.89 to 0.98)). CONCLUSION: Compared with men, women were less likely to be prescribed high-intensity statins at initiation and to achieve treatment targets, both in people without and with a history of CVD, and independent of differences in other individual and clinical characteristics.

Identifying Psychosis Episodes in Psychiatric Admission Notes via Rule-based Methods, Machine Learning, and Pre-Trained Language Models.

Early and accurate diagnosis is crucial for effective treatment and improved outcomes, yet identifying psychotic episodes presents significant challenges due to its complex nature and the varied presentation of symptoms among individuals. One of the primary difficulties lies in the underreporting and underdiagnosis of psychosis, compounded by the stigma surrounding mental health and the individuals' often diminished insight into their condition. Existing efforts leveraging Electronic Health Records (EHRs) to retrospectively identify psychosis typically rely on structured data, such as medical codes and patient demographics, which frequently lack essential information. Addressing these challenges, our study leverages Natural Language Processing (NLP) algorithms to analyze psychiatric admission notes for the diagnosis of psychosis, providing a detailed evaluation of rule-based algorithms, machine learning models, and pre-trained language models. Additionally, the study investigates the effectiveness of employing keywords to streamline extensive note data before training and evaluating the models. Analyzing 4,617 initial psychiatric admission notes (1,196 cases of psychosis versus 3,433 controls) from 2005 to 2019, we discovered that the XGBoost classifier employing Term Frequency-Inverse Document Frequency (TF-IDF) features derived from notes pre-selected by expert-curated keywords, attained the highest performance with an F1 score of 0.8881 (AUROC [95% CI]: 0.9725 [0.9717, 0.9733]). BlueBERT demonstrated comparable efficacy an F1 score of 0.8841 (AUROC [95% CI]: 0.97 [0.9580,0.9820]) on the same set of notes. Both models markedly outperformed traditional International Classification of Diseases (ICD) code-based detection methods from discharge summaries, which had an F1 score of 0.7608, thus improving the margin by 0.12. Furthermore, our findings indicate that keyword pre-selection markedly enhances the performance of both machine learning and pre-trained language models. This study illustrates the potential of NLP techniques to improve psychosis detection within admission notes and aims to serve as a foundational reference for future research on applying NLP for psychosis identification in EHR notes.

Distributions of recorded pain in mental health records: a natural language processing based study.

OBJECTIVE: The objective of this study is to determine demographic and diagnostic distributions of physical pain recorded in clinical notes of a mental health electronic health records database by using natural language processing and examine the overlap in recorded physical pain between primary and secondary care. DESIGN, SETTING AND PARTICIPANTS: The data were extracted from an anonymised version of the electronic health records of a large secondary mental healthcare provider serving a catchment of 1.3 million residents in south London. These included patients under active referral, aged 18+ at the index date of 1 July 2018 and having at least one clinical document (≥30 characters) between 1 July 2017 and 1 July 2019. This cohort was compared with linked primary care records from one of the four local government areas. OUTCOME: The primary outcome of interest was the presence of recorded physical pain within the clinical notes of the patients, not including psychological or metaphorical pain. RESULTS: A total of 27 211 patients were retrieved. Of these, 52% (14,202) had narrative text containing relevant mentions of physical pain. Older patients (OR 1.17, 95% CI 1.15 to 1.19), females (OR 1.42, 95% CI 1.35 to 1.49), Asians (OR 1.30, 95% CI 1.16 to 1.45) or black (OR 1.49, 95% CI 1.40 to 1.59) ethnicities, living in deprived neighbourhoods (OR 1.64, 95% CI 1.55 to 1.73) showed higher odds of recorded pain. Patients with severe mental illnesses were found to be less likely to report pain (OR 0.43, 95% CI 0.41 to 0.46, p<0.001). 17% of the cohort from secondary care also had records from primary care. CONCLUSION: The findings of this study show sociodemographic and diagnostic differences in recorded pain. Specifically, lower documentation across certain groups indicates the need for better screening protocols and training on recognising varied pain presentations. Additionally, targeting improved detection of pain for minority and disadvantaged groups by care providers can promote health equity.