Electronic Medical Information Research Articles

A secure interoperable method for electronic health records exchange on cross platform blockchain network

An Electronic Health Record (EHR) store essential and sensitive patient's medical information. Since health information is highly confidential data, it should be accessible with the consent of the patient. Blockchain based EHR management system offers improvised privacy and patient-centric approach. EHR management systems are available with multiple blockchain platforms. Generally, EHRs are maintained at several independent blockchain platforms. EHR management systems should be capable of securely exchange data on cross platform blockchain network. The interoperability in such blockchain platforms should facilitate seamless cross-chain interaction and information exchange. This article proposes a method that facilitates secure EHR exchange on Ethereum and Hyperledger fabric network using hepatitis dataset. The key contributions of the proposed method include:•Hash lock based interoperable cross-chain method for EHR exchange across Ethereum and Hyperledger fabric.•Additional security to the EHR is ensured by partitioning EHR as on-chain (blockchain platform) and off-chain InterPlanetary File System (IPFS)•Secure Password Authentication-Based Key Exchange (SPAKE) based session management for EHR exchange across two parties.The proposed patient centric method is validated to ensures the successful exchange of patient EHR across Ethereum and Hyperledger fabric.

Emergency Medical Access Control System Based on Public Blockchain

IT has made significant progress in various fields over the past few years, with many industries transitioning from paper-based to electronic media. However, sharing electronic medical records remains a long-term challenge, particularly when patients are in emergency situations, making it difficult to access and control their medical information. Previous studies have proposed permissioned blockchains with limited participants or mechanisms that allow emergency medical information sharing to pre-designated participants. However, permissioned blockchains require prior participation by medical institutions, and limiting sharing entities restricts the number of potential partners. This means that sharing medical information with local emergency doctors becomes impossible if a patient is unconscious and far away from home, such as when traveling abroad. To tackle this challenge, we propose an emergency access control system for a global electronic medical information system that can be shared using a public blockchain, allowing anyone to participate. Our proposed system assumes that the patient wears a pendant with tamper-proof and biometric authentication capabilities. In the event of unconsciousness, emergency doctors can perform biometrics on behalf of the patient, allowing the family doctor to share health records with the emergency doctor through a secure channel that uses the Diffie-Hellman (DH) key exchange protocol. The pendant’s biometric authentication function prevents unauthorized use if it is stolen, and we have tested the blockchain’s fee for using the public blockchain, demonstrating that the proposed system is practical.

Suplatast tosilate reduces peripheral blood eosinophil levels in patients with eosinophilia: A real-world retrospective study

IntroductionEosinophilia is a rare disease characterized by an increase in eosinophils. Suplatast tosilate is a selective Th2 cytokine inhibitor that can reduce eosinophils. There is currently a lack of clinical studies of suplatast tosilate in the treatment of eosinophilia. Research objectiveTo explore whether suplatast tosilate can reduce blood eosinophil levels in eosinophilia and the factors that might influence the improvement. MethodsA real-world retrospective study of 20 patients with eosinophilia was conducted using electronic medical record information. The main outcome measure was the difference in peripheral blood absolute eosinophil count (AEC) and percentage (EOS%) before suplatast tosilate (baseline) and the lowest AEC during the 1-year period of suplatast tosilate treatment (post-treatment). Data on age, gender, disease duration, involved organs, and concomitant medication were collected, and subgroup analysis and linear regression analysis were performed. ResultsSubjects were predominantly male, with a mean age of 33 years and a disease duration of approximately 30 months. After treatment with suplatast tosilate, the patient's AEC (p ​= ​0.029) and EOS% (p ​= ​0.016) significantly decreased. The decline in eosinophils was more pronounced in patients who were male, age <33 years, disease duration <30 months and gastrointestinal system involvement. In addition, the shorter the course of the disease, the greater the relative decrease in eosinophils after suplatast tosilate treatment (β ​= ​−0.018, p ​< ​0.001). ConclusionsSuplatast tosilate is effective in reducing peripheral blood eosinophil levels in patients with eosinophilia. Large-scale prospective cohort studies are needed for further confirmation.

Early Cholecystectomy after Endoscopic Retrograde Cholangiopancreatography Is Feasible and Safe.

Laparoscopic cholecystectomy (LC) following endoscopic retrograde cholangiopancreatography (ERCP) is the preferred treatment for cholelithiasis with common bile duct stones. However, the optimal timing of LC after ERCP remains controversial. This study aimed to identify the ideal time interval between ERCP and LC. Data from patients who underwent LC after ERCP between November 2016 and August 2022 were retrieved from the electronic medical information system. The patients were categorized into early cholecystectomy (within 72 h of ERCP) and delayed cholecystectomy (after 72 h). The impact of the time interval between ERCP and LC on perioperative outcomes was analyzed. A total of 197 patients were included in the study, with 45 undergoing early cholecystectomy and 152 undergoing delayed cholecystectomy. No significant differences in the preoperative characteristics or operative morbidity were observed between the groups (p = 0.286). However, a significant correlation was found between the time interval from ERCP to LC and the total length of stay (r = -350, p < 0.001). The findings suggest that early cholecystectomy after ERCP is feasible and safe, and performing LC within the first 72 h does not adversely affect postoperative outcomes.

Electronic medical information and analytical system (EMIAS) as a tool for the new level of understanding and diagnosis of medication adherence in patients with myocardial infarction in primary care practice in Moscow

Introduction. The global community is increasingly using patients' prescription claims data as a dominant method for assessing medication adherence, which encouraged us to conduct this study.Aim. To adapt the existing international experience of using digital technologies to measure medication adherence to the routine practice of domestic health care at the outpatient level.Methods. We conducted a retrospective study of adherence to statin therapy in patients with myocardial infarction (MI) at a large primary care clinic in Moscow, which included 2 stages: 1st stage — compilation of international experience on medication adherence studies using pharmacy dispensing records; 2nd stage — testing the method of electronic prescription refill record to measure adherence. We calculated the proportion of days covered (PDC) by statin therapy over a 12‑month period following MI. Data on demography, anamnesis, lipid profile, and statin prescriptions were obtained from the electronic medical records of patients with acute MI from January 1 — December 31, 2022. A total of 109 patients were included according to the prespecified selection criteria.Results. An analysis of international experience demonstrated that the pharmacy dispensing record method has become widespread in recent decades in foreign countries and has established itself as an objective, noninvasive, and inexpensive method for measuring medication adherence. The study of adherence to statin therapy in post-MI patients using the electronic prescription refill record method revealed a mean PDC = 63.0±29.7 %. Optimal adherence (PDC≥80 %) throughout the 12‑month follow-up period was noted in 38 % of patients. When PDC was calculated separately for the 1st and 2nd half year, it was found that the proportion of patients with optimal adherence decreased by 17.6 % (p=0.04). Adherence correlated with the efficacy of statin therapy — a more pronounced reduction of LDL–C was observed in patients with PDC≥80 % compared with those who were insufficiently adherent (–1.47±1.09 vs –0.96±1.16 mmol/L; p=0.043).Conclusion. This study demonstrated the efficiency and information value of an electronic prescription refill record system for domestic primary care. After operational tuning, the proposed method can be integrated into EMIAS for routine medication adherence assessment.

Social determinants of health and disparities in spine surgery: a 10-year analysis of 8,565 cases using ensemble machine learning and multilayer perceptron

BACKGROUND CONTEXTThe influence of SDOH on spine surgery is poorly understood. Historically, researchers commonly focused on the isolated influences of race, insurance status, or income on healthcare outcomes. However, analysis of SDOH is becoming increasingly more nuanced as viewing social factors in aggregate rather than individually may offer more precise estimates of the impact of SDOH on healthcare delivery. PURPOSEThe aim of this study was to evaluate the effects of patient social history on length of stay (LOS) and readmission within 90 days following spine surgery using ensemble machine learning and multilayer perceptron. STUDY DESIGNRetrospective chart review. PATIENT SAMPLE8,565 elective and emergency spine surgery cases performed from 2013 to 2023 using our institution's database of longitudinally collected electronic medical record information. OUTCOMES MEASURESPatient LOS, discharge disposition, and rate of 90-day readmission. METHODSEnsemble machine learning and multilayer perceptron were employed to predict LOS and readmission within 90 days following spine surgery. All other subsequent statistical analysis was performed using SPSS version 28. To further assess correlations among variables, Pearson's correlation tests and multivariate linear regression models were constructed. Independent sample t-tests, paired sample t-tests, one-way analysis of variance (ANOVA) with post-hoc Bonferroni and Tukey corrections, and Pearson's chi-squared test were applied where appropriate for analysis of continuous and categorical variables. RESULTSBlack patients demonstrated a greater LOS compared to white patients, but race and ethnicity were not significantly associated with 90-day readmission rates. Insured patients had a shorter LOS and lower readmission rates compared to non-insured patients, as did privately insured patients compared to publicly insured patients. Patients discharged home had lower LOS and lower readmission rates, compared to patients discharged to other facilities. Marriage decreased both LOS and readmission rates, underweight patients showcased increased LOS and readmission rates, and religion was shown to impact LOS and readmission rates. When utilizing patient social history, lab values, and medical history, machine learning determined the top 5 most-important variables for prediction of LOS —along with their respective feature importances—to be insurance status (0.166), religion (0.100), ICU status (0.093), antibiotic use (0.061), and case status: elective or urgent (0.055). The top 5 most-important variables for prediction of 90-day readmission—along with their respective feature importances—were insurance status (0.177), religion (0.123), discharge location (0.096), emergency case status (0.064), and history of diabetes (0.041). CONCLUSIONSThis study highlights that SDOH is influential in determining patient length of stay, discharge disposition, and likelihood of readmission following spine surgery. Machine learning was utilized to accurately predict LOS and 90-day readmission with patient medical history, lab values, and social history, as well as social history alone.

The Association Between the Location of Subarachnoid Hemorrhage and the Occurrence of Takotsubo Cardiomyopathy: A Systematic Review and Meta-analysis.

Takotsubo cardiomyopathy (TCM) is a syndrome characterized by transient regional cardiac dysfunction of the left ventricle. The goal of this review is to better understand the relationship between the anatomic locations of subarachnoid hemorrhages (SAHs) and the development of TCM as identified through a review of cohort studies. From inception to December 2023, we systematically explored major electronic medical information sources to identify cases of TCM that developed after SAHs. The six selected studies included in the meta-analysis suggest a modest but statistically significant increase in the odds of the events in the posterior circulation group compared to the anterior circulation group, with a combined odds ratio (OR) estimate of around 1.45-1.46. The fixed effect model gives an overall OR of 1.45 with a 95% confidence interval (CI) of 1.01 to 2.10, z = 2.01, p = 0.0442, while the random effects model yields a slightly higher OR of 1.46 with the same 95% CI, z = 2.03, p = 0.0425. There is a tendency for SAH occurrence in the posterior cerebral circulation to cause SAH-related TCM more frequently than in the anterior cerebral circulation.

Joint B Vitamin Intake and Type 2 Diabetes Risk: The Mediating Role of Inflammation in a Prospective Shanghai Cohort.

Type 2 diabetes (T2D) is a global and complex public health challenge, and dietary management is acknowledged as critical in its prevention. Recent studies have highlighted the involvement of micronutrients in T2D pathophysiology; our study aims to assess the association between B vitamin intake and T2D risks and the mediating role of inflammation. In a prospective cohort design, data on B vitamins intake, including thiamine (B1), riboflavin (B2), niacin (B3), pyridoxine (B6), folate (B9), and cobalamin (B12), was obtained using a validated food frequency questionnaire (FFQ), and blood inflammatory biomarkers were analyzed according to standard protocol in the local hospitals at baseline from 44,960 adults in the Shanghai Suburban Adult Cohort and Biobank (SSACB). Incident T2D cases were identified according to a physician's diagnosis or medication records from the electronic medical information system. We employed logistic and weighted quantile sum regression models to explore the associations of single and combined levels of B vitamins with T2D and mediation analyses to investigate the effects of inflammation. Negative correlations between B vitamins and T2D were observed in the single-exposure models, except for B3. The analyses of joint exposure (B1, B2, B6, B9, and B12) also showed an inverse association (OR 0.80, 95% CI 0.71 to 0.88), with vitamin B6 accounting for 45.58% of the effects. Further mediation analysis indicated a mediating inflammatory impact, accounting for 6.72% of the relationship. Dietary intake of B vitamins (B1, B2, B6, B9, B12) was associated with a reduced T2D risk partially mediated by inflammation in Shanghai residents.

Construction and validation of clinical prediction model of acupuncture and moxibustion for Bell's palsy

To establish and validate a clinical prediction model of acupuncture and moxibustion for Bell's palsy so as to provide a tool for predicting the effect of acupuncture and moxibustion on Bell's palsy. A total of 269 patients with Bell's palsy were collected from department of acupuncture, moxibustion and tuina, Shengli Oilfield Central Hospital, neurology department, Shenxian County Central Hospital and department of rehabilitation medicine, Dongying Municipal Hospital of TCM from June 2018 to June 2023. All of these cases were treated with acupuncture and moxibustion. Of them, 182 cases, from department of acupuncture, moxibustion and tuina, Shengli Oilfield Central Hospital and neurology department, Shenxian County Central Hospital, were randomized into a training group (128 cases) and an internal validation group (54 cases); 87 cases from department of rehabilitation medicine, Dongying Municipal Hospital of TCM were assigned to an external validation group. The clinical data of all of the cases were extracted from the electronic medical record information platform. Using SPSS25.0 and R4.2.3, through univariate and multivariate Logistic regression analysis, the independent factors influencing the effects of acupuncture and moxibustion on Bell's palsy were identified. By means of internal and external validations, the receiver operating characteristic curve (ROC), the goodness-of-fit curve (GFC) and the decision curve analysis (DCA) were plotted. The sensitivity, specificity, accuracy, positive predictive value and negative predictive value of the model were calculated; and its comprehensive performance was evaluated. The results of the multivariate Logistic regression analysis showed that the independent factors for the unsatisfactory effect on Bell's palsy were advanced age, severe symptoms before treatment, no use of steroids within 72 h of onset, and lack of acupuncture-moxibustion therapy during the acute phase or single acupuncture-moxibustion protocol (P<0.05, P<0.01). Based on these factors, nomogram model and online columnar plot prediction tool (https://bmuchen.shinyapps.io/dynnomapp/) were established. The area under the ROC curve of the model was 0.921 (95% CI: 0.877, 0.966), 0.876 (95% CI: 0.787, 0.966), and 0.846 (95% CI: 0.766, 0.926) in the training group, the internal validation group, and the external validation group, respectively, indicating good predictive value. The model showed a satisfactory calibration curve alignment. The decision threshold in the range of 0 to 0.8 provided clinical benefits for participants. The model exhibited the sensitivity from 65.9% to 88.0%, the specificity ranging from 77.3% to 90.7%, the accuracy from 77.8% to 85.9%, the positive predictive value from 83.3% to 90.1%, and the negative predictive value from 70.8% to 78.7%. The comprehensive evaluation indicated a satisfactory clinical application value of the model. The clinical prediction model of acupuncture and moxibustion for Bell's palsy is valuable in its practice and promotion to a certain extent. The predicted results are conductive to clinicians' judgement of the effect of acupuncture and moxibustion for this disease and making effective and high-quality clinical decisions, as well as formulating the optimal therapeutic regimen.

Electronic medical information systems and timeliness of care in the emergency department: a scoping review

BackgroundAlthough many emergency department (ED) settings have implemented an electronic medical information system (EMIS) and EMIS tools in an effort to improve timeliness of care outcomes, there remains a paucity of scientific information on this topic. We therefore performed a scoping review to describe the range of EMIS interventions and their impacts on time-based outcomes in the ED.MethodsWe searched four bibliographic databases to identify potentially relevant records published after 2014 in English. Two reviewers assessed records for eligibility using a two-step screening process. We then extracted data on the type of EMIS, outcomes assessed, and reported results. Findings were summarized in tabular form and grouped by time-based outcome.ResultsTwenty-five studies met the eligibility criteria, with approximately half being retrospective studies. Interventions varied among studies; they generally included a new or updated EMIS, EMIS tools related to disease diagnosis and/or management, triage tools, or health information exchange platforms. Included studies compared interventions with relevant comparator groups, such as prior versions of an EMIS, absence of an EMIS, pen-and-paper documentation, and/or communication via telephone and fax. The most common outcomes reported were length of stay (n = 17 studies) and time to medication (n = 6 studies), followed by time to order, time to provider, and time from result to disposition. Reported effects of the interventions were generally inconsistent, showing either improvements, delays, or no change in examined outcomes.ConclusionsAdditional research is needed to determine how electronic medical information may be used in the ED to improve timeliness of care. Findings from this review can be used to inform future systematic reviews that evaluate the impact of these systems and tools on specific quality of care measures.

Development and validation of a risk prediction model and prediction tools for post-thrombotic syndrome in patients with lower limb deep vein thrombosis

PurposeOur research aims to compare the predictive performance of decision tree algorithms (DT) and logistic regression analysis (LR) in constructing models, and develop a Post-Thrombotic Syndrome (PTS) risk stratification tool. MethodsWe retrospectively collected and analyzed relevant case information of 618 patients diagnosed with DVT from January 2012 to December 2021 in three different tertiary hospitals in Jiangxi Province as the modeling group. Additionally, we used the case information of 212 patients diagnosed with DVT from January 2022 to January 2023 in two tertiary hospitals in Hubei Province and Guangdong Province as the validation group. We extracted electronic medical record information including general patient data, medical history, laboratory test indicators, and treatment data for analysis. We established DT and LR models and compared their predictive performance using receiver operating characteristic (ROC) curves and confusion matrices. Internal and external validations were conducted. Additionally, we utilized LR to generate nomogram charts, calibration curves, and decision curves analysis (DCA) to assess its predictive accuracy. ResultsBoth DT and LR models indicate that Year, Residence, Cancer, Varicose Vein Operation History, DM, and Chronic VTE are risk factors for PTS occurrence. In internal validation, DT outperforms LR (0.962 vs 0.925, z = 3.379, P < 0.001). However, in external validation, there is no significant difference in the area under the ROC curve between the two models (0.963 vs 0.949, z = 0.412, P = 0.680). The validation results of calibration curves and DCA demonstrate that LR exhibits good predictive accuracy and clinical effectiveness. A web-based calculator software of nomogram (https://sunxiaoxuan.shinyapps.io/dynnomapp/) was utilized to visualize the logistic regression model. ConclusionsThe combination of decision tree and logistic regression models, along with the web-based calculator software of nomogram, can assist healthcare professionals in accurately assessing the risk of PTS occurrence in individual patients with lower limb DVT.

Exploring the impact of primary care utilization and health information exchange upon treatment patterns and clinical outcomes of glioblastoma patients.

There is limited literature describing care coordination for patients with glioblastoma (GBM). We aimed to investigate the impact of primary care and electronic health information exchange (HIE) between neurosurgeons, oncologists, and primary care providers (PCP) on GBM treatment patterns, postoperative outcomes, and survival. We identified adult GBM patients undergoing primary resection at our institution (2007-2020). HIE was defined as shared electronic medical information between PCPs, oncologists, and neurosurgeons. Multivariate logistic regression analyses were used to determine the effect of PCPs and HIE upon initiation and completion of adjuvant therapy. Kaplan-Meier and multivariate Cox regression models were used to evaluate overall survival (OS). Among 374 patients (mean age ± SD: 57.7 ± 13.5, 39.0% female), 81.0% had a PCP and 62.4% had electronic HIE. In multivariate analyses, having a PCP was associated with initiation (OR: 7.9, P < 0.001) and completion (OR: 4.4, P < 0.001) of 6 weeks of concomitant chemoradiation, as well as initiation (OR: 4.0, P < 0.001) and completion (OR: 3.0, P = 0.007) of 6 cycles of maintenance temozolomide thereafter. Having a PCP (median OS [95%CI]: 14.6[13.1-16.1] vs. 10.8[8.2-13.3] months, P = 0.005) and HIE (15.40[12.82-17.98] vs. 13.80[12.51-15.09] months, P = 0.029) were associated with improved OS relative to counterparts in Kaplan-Meier analysis and in multivariate Cox regression analysis (hazard ratio [HR] = 0.7, [95% CI] 0.5-1.0, P = 0.048). In multivariate analyses, chemoradiation (HR = 0.34, [95% CI] 0.2-0.7, P = 0.002) and maintenance temozolomide (HR = 0.5, 95%CI 0.3-0.8, P = 0.002) were associated with improved OS relative to counterparts. Effective care coordination between neurosurgeons, oncologists, and PCPs may offer a modifiable avenue to improve GBM outcomes.

The Red Cross Red Crescent Health Information System (RCHIS): an electronic medical records and health information management system for the red cross red crescent emergency response units

BackgroundThe Red Cross and Red Crescent Movement (RCRC) utilizes specialized Emergency Response Units (ERUs) for international disaster response. However, data collection and reporting within ERUs have been time-consuming and paper-based. The Red Cross Red Crescent Health Information System (RCHIS) was developed to improve clinical documentation and reporting, ensuring accuracy and ease of use while increasing compliance with reporting standards.Case presentationRCHIS is an Electronic Medical Record (EMR) and Health Information System (HIS) designed for RCRC ERUs. It can be accessed on Android tablets or Windows laptops, both online and offline. The system securely stores data on Microsoft Azure cloud, with synchronization facilitated through a local ERU server. The functional architecture covers all clinical functions of ERU clinics and hospitals, incorporating user-friendly features. A pilot study was conducted with the Portuguese Red Cross (PRC) during a large-scale event. Thirteen super users were trained and subsequently trained the staff. During the four-day pilot, 77 user accounts were created, and 243 patient files were documented. Feedback indicated that RCHIS was easy to use, requiring minimal training time, and had sufficient training for full utilization. Real-time reporting facilitated coordination with the civil defense authority.ConclusionsThe development and pilot use of RCHIS demonstrated its feasibility and efficacy within RCRC ERUs. The system addressed the need for an EMR and HIS solution, enabling comprehensive clinical documentation and supporting administrative reporting functions. The pilot study validated the training of trainers’ approach and paved the way for further domestic use of RCHIS. RCHIS has the potential to improve patient safety, quality of care, and reporting efficiency within ERUs. Automated reporting reduces the burden on ERU leadership, while electronic compilation enhances record completeness and correctness. Ongoing feedback collection and feature development continue to enhance RCHIS’s functionality. Further trainings took place in 2023 and preparations for international deployments are under way. RCHIS represents a significant step toward improved emergency medical care and coordination within the RCRC and has implications for similar systems in other Emergency Medical Teams.

Digital health and cardiovascular healthcare professionals in Portugal: Current status, expectations and barriers to implementation

Introduction and ObjectivesDigital health (DH) is a broad concept, bringing together technology and healthcare, that is playing an increasingly important role in the daily routine of healthcare professionals (HCPs) and promises to contribute to the prevention and treatment of cardiovascular disease. There are no solid data on the position of Portuguese HCPs toward the implementation of DH in cardiovascular medicine. This national cross-sectional study aims to provide a snapshot of DH implementation in Portuguese cardiovascular HCP routines and to identify both expectations and barriers to its adoption. MethodsAn 18-question survey was created specifically for this study and distributed to 1174 individuals on the Portuguese Society of Cardiology mailing list. ResultsWe collected 117 valid responses (response rate 10%). Almost all participants had smartphones and laptops, and two-thirds had tablets. Electronic medical information systems were the most used DH tool (84% of respondents) and were considered the most important for improving cardiovascular care. Implantable technologies (sensors and devices), telemedicine and social media were used by more than two out of three respondents and considered «very important» or «extremely important» by most of them. Most participants showed positive expectations regarding the impact of DH in cardiovascular medicine: 78% agreed that DH could improve health outcomes, 64% that it promotes health literacy and 63% that it could decrease healthcare costs. The top-rated barriers were patients’ inability to use smartphones, limited access to electronic devices, and lack of legal regulation of DH. ConclusionMost Portuguese cardiovascular HCPs had at least three electronic devices (mainly smartphones, laptops and tablets) and showed positive expectations regarding DH's current and future impact on cardiovascular medicine. Patient DH literacy, technology adoption, and DH regulation were identified as the most important barriers to increasing the adoption of DH tools in cardiovascular medicine.

Comparison of machine learning approaches for positive airway pressure adherence prediction in a veteran cohort

BackgroundAdherence to positive airway pressure (PAP) therapy for sleep apnea is suboptimal, particularly in the veteran population. Accurately identifying those best suited for other therapy or additional interventions may improve adherence. We evaluated various machine learning algorithms to predict 90-day adherence.MethodsThe cohort of VA Northeast Ohio Health Care system patients who were issued a PAP machine (January 1, 2010–June 30, 2015) had demographics, comorbidities, and medications at the time of polysomnography obtained from the electronic health record. The data were split 60:20:20 into training, calibration, and validation data sets, with no use of validation data for model development. We constructed models for the first 90-day adherence period (% nights ≥4 h use) using the following algorithms: linear regression, least absolute shrinkage and selection operator, elastic net, ridge regression, gradient boosted machines, support vector machine regression, Bayes-based models, and neural nets. Prediction performance was evaluated in the validation data set using root mean square error (RMSE).ResultsThe 5,047 participants were 38.3 ± 11.9 years old, and 96.1% male, with 36.8% having coronary artery disease and 52.6% with depression. The median adherence was 36.7% (interquartile range: 0%, 86.7%). The gradient boosted machine was superior to other machine learning techniques (RMSE 37.2). However, the performance was similar and not clinically useful for all models without 30-day data. The 30-day PAP data and using raw diagnoses and medications (vs. grouping by type) improved the RMSE to 24.27.ConclusionComparing multiple prediction algorithms using electronic medical record information, we found that none has clinically meaningful performance. Better adherence predictive measures may offer opportunities for personalized tailoring of interventions.

A machine learning-based prediction model for postoperative delirium in cardiac valve surgery using electronic health records

BackgroundPrevious models for predicting delirium after cardiac surgery remained inadequate. This study aimed to develop and validate a machine learning-based prediction model for postoperative delirium (POD) in cardiac valve surgery patients.MethodsThe electronic medical information of the cardiac surgical intensive care unit (CSICU) was extracted from a tertiary and major referral hospital in southern China over 1 year, from June 2019 to June 2020. A total of 507 patients admitted to the CSICU after cardiac valve surgery were included in this study. Seven classical machine learning algorithms (Random Forest Classifier, Logistic Regression, Support Vector Machine Classifier, K-nearest Neighbors Classifier, Gaussian Naive Bayes, Gradient Boosting Decision Tree, and Perceptron.) were used to develop delirium prediction models under full (q = 31) and selected (q = 19) feature sets, respectively.ResultThe Random Forest classifier performs exceptionally well in both feature datasets, with an Area Under the Curve (AUC) of 0.92 for the full feature dataset and an AUC of 0.86 for the selected feature dataset. Additionally, it achieves a relatively lower Expected Calibration Error (ECE) and the highest Average Precision (AP), with an AP of 0.80 for the full feature dataset and an AP of 0.73 for the selected feature dataset. To further evaluate the best-performing Random Forest classifier, SHAP (Shapley Additive Explanations) was used, and the importance matrix plot, scatter plots, and summary plots were generated.ConclusionsWe established machine learning-based prediction models to predict POD in patients undergoing cardiac valve surgery. The random forest model has the best predictive performance in prediction and can help improve the prognosis of patients with POD.

Assessment of Information Technology in Electronic Medical Records Using the Concept Health Technology Assessment at X Jepara Hospital

&lt;div&gt;&lt;table cellspacing="0" cellpadding="0" align="left"&gt;&lt;tbody&gt;&lt;tr&gt;&lt;td align="left" valign="top"&gt;&lt;p&gt;&lt;em&gt;Hospitals as health service providers need to study the equipment used in health services, which is called a Health Technology Assessment. This research aims to determine the assessment of electronic medical record information technology using the Health Technology Assessment concept at regional General Hospital X Jepara. This research uses a qualitative method with a descriptive design. The research was conducted at the regional general hospital X Jepara which was carried out from March to June 2023. There were 13 informants in this research with 9 main informants and 3 triangulation informants. Data collection techniques use in-depth interviews, observation, and document study. Data analysis for this research is data reduction, data presentation, and conclusion. The results of this research on the concept of effectiveness can increase productivity, be more efficient, make it very easy to publish patient medical records in summary and detail, and doctors and nurses can easily access patient data by logging in using their password. Patient privacy is also maintained with limited access to open it. Service is fast and can increase satisfaction and improve hospital services from an economic perspective using health technology assessment methods. The characteristic aspect of using electronic medical records is that it makes hospital services easier. The security aspect of patient data is guaranteed because system access can only be accessed by users with an account, and the rights of each user are guaranteed. The management of the regional general hospital will easily use electronic medical records and improve the service and quality of Regional General Hospital X Jepara.&lt;/em&gt;&lt;/p&gt;&lt;/td&gt;&lt;/tr&gt;&lt;/tbody&gt;&lt;/table&gt;&lt;/div&gt; &lt;strong&gt;&lt;em&gt;Keywords: Electronic medical record, Effectiveness, Economic, Technical characteristic, Security&lt;/em&gt;&lt;/strong&gt;

DEVELOPMENT OF METHODOLOGY AND TOOLS FOR REGULAR MONITORING, ASSESSMENT OF THE QUALITY OF WORK OF THE ELECTRONIC HEALTHCARE SYSTEM AND IMPROVEMENT OF THE WORK OF EXISTING SERVICES

Introduction. Medical information systems have become an important tool in the complex of providing medical care. They allow storing the patient's medical data, analyzing information at many levels, and using modern electronic and telemedicine technologies. The glossary of the concept of health care informatization defines a medical information system as a type of system characterized by a complex of methodological principles, technical means, management algorithms designed for the collection, storage, analysis, forecasting and transmission of medical information in health care institutions.&#x0D; The aim: To analyze the level of satisfaction of medical workers regarding the functioning of the electronic health care system and medical information systems in all areas of medical activity, by evaluating the data of the electronic questionnaire.&#x0D; Materials and methods: A group of 213 user experts from 11 regions of Ukraine and the city of Kyiv was formed to assess the overall quality of the electronic health care system. Informational, analytical-statistical, graphic, and system analysis methods were applied.&#x0D; Results. The information entered into the medical information systems is subsequently widely used by doctors, other medical personnel, patients, and the administration of the health care facility. However, numerous functional deficiencies, and user wishes were identified. Assessing them will contribute to the improvement of e-Health.&#x0D; Conclusions: Medical information systems (MIS) have become an integral attribute of the practical activity of all doctors. The development of MIS in Ukraine continues in intensive and extensive ways. The first MIS were autonomous and responded to local clinical and administrative needs. The problems of the country's health care management can be corrected through the wide and rational use of MIS, their integration into a single electronic system. This will make it possible to analyze medical data at the level of the country, region, institution and thus be able to apply the correct management decisions. Informatization of health care is a global trend, and in Ukraine it is developing at an unusually fast pace. Therefore, the assessment of convenience, efficiency, and interoperability of MIS should become a permanent tool for monitoring and prompt response by both doctors and health care managers. Medical workers are quite satisfied with the functioning of medical information systems in Ukraine, but the issues between technical solutions and practical use of the application remain unresolved.

Patterns in staff reported surgical instrument errors point to failures in visualization as a critically weak point in sterile processing of surgical instruments

BackgroundSurgical Instrument Errors (missing, broken, bioburden/contamination etc.) account for significant delays in the operating room. During sterile processing, instruments must be inspected for correctness, functionality, and cleanliness (bioburden) prior to packaging for sterilization. The environment where these tasks are performed is typically high stress and high throughput. There is a growing body of research in human performance that indicates that under stress, the skill of human visualization (inspection and identification) deteriorates. Furthermore, error modeling of sterile processing of surgical instruments suggests that the tasks at highest risk for errors involve human visualization. Reporting of Surgical Instrument Errors at our institution falls to OR staff and, during the period of this study, was done through a mechanism termed the Patient safety notice or PSN. PSNs are filed via computer through the healthcare system website. There is no integration or linkage of the PSN to the electronic medical record and information in all fields must be typed in as it does not automatically populate. We hypothesized that the most common PSNs reporting Surgical Instrument Errors would involve tasks of visualization (inspection, identification). Accordingly, the most common reported Surgical Instrument Errors would be missing instruments, bioburden/contamination, and broken instruments. We also hypothesized that due to the complexity and lack of both data automation and integration with the electronic medical record in filing PSNs, the majority of PSNs reporting Surgical Instrument Errors would be incomplete. To test these two hypotheses, we analyzed one year's worth staff reported Surgical Instrument Error rates at two hospitals with the operating rooms at both locations serviced by a single sterile processing facility. MethodsThis study was conducted at a major healthcare center that houses 38 ORs located at 3 sites (Children's (8), Adult inpatient (24) and Adult outpatient (6)) all of which share a sterile processing facility. Staff reported Patient Safety Notices (PSNs), a reporting mechanism for safety events, were collected from July 2019 through June of 2020. PSNs reporting the following Surgical Instrument Errors: missing instrument (listed on the count sheet but absent from the tray), broken instrument, assembly or packaging error, wrong instrument, failed sterilization/bioburden/contamination, fleet management (trays missing), extra instrument and transport errors were identified. Raw annual rates of reported Surgical Instrument Errors were determined for each hospital. Rates per surgical service line (percent affected cases) per hospital were then determined by dividing the annual number of reported errors per service by the annual number of cases per service line. Whether the instrument error affected the sterile field was determined as well. An analysis of bioburden/contamination error rates and Surgical Instrument Error types by hospital was also determined. Results368 PSNs reporting 419 Surgical Instrument Errors were identified over a 12-month period (0.0432 errors/OR/elective OR day). The majority of reported errors (83 %) had to do with failures in inspection (bioburden/contamination) or in tracking and identification (missing). At both hospitals, cardiovascular surgery had the highest reported error rates per case (4.47 % of cases affected at the Adult hospital and 3.68 % of cases affected at the Children's hospital). In only 64 instances was the sterile field reported to be affected by the error. Bioburden/contamination was the most commonly reported instrument error (68.97 %) with the most common types of bioburden/contamination being debris, blood and tissue, failed instrument cleaning due to incomplete disassembly and the presence of hair. Overall, only 20.4 % of PSN had all fields filled to completion and 15 % were submitted days after the event (average of 12.70 ± 27.97 days, median of 2 days). Conclusionsthe data from this study indicates that failure in human visualization vis-à-vis inspection and identification are the root cause of the majority (83 %) of staff reported Surgical Instrument Errors. This manifests primarily through problems with bioburden/contamination and missing instruments. Implementation of technologies to improve inspection and identification and ultimately tracking of surgical instruments should substantially reduce Surgical Instrument Error rates. Furthermore, staff dependent reporting of these errors is rarely done to completion and a significant portion of events are reported days after an event. These latter findings suggest that the process is cumbersome and likely impedes accurate and timely reporting and may results in underreporting of Surgical Instrument Errors.

Research on Electronic Medical Record Information Sharing: A Bibliometric Analysis

Objective :This study aimed to conduct a bibliometric analysis of information sharing in electronic medical records. Use bibliometric methods to discover the research directions in this field, the spatiotemporal distribution of research results, and the temporal trends of research hotspots. Methods: This article uses bibliometric analysis methods to analyze relevant research on electronic medical record information sharing. The Web of Science (WOS) database was used to extract the publications. Through keyword searches and limiting literature sources to core journals, 1779 articles were ultimately included in the analysis. Citespace6.2.4 was used for bibliometric analysis. Results: The number of related studies shows a stable upward trend. The application and technological optimizations were the subjects analyzed in most studies. Based on the primary geographic distribution of published articles, the United States was the country that published the most articles. Conclusion: We found that research on laws, regulations, and information ethics is insufficient. These research directions are worth further exploration. In addition, the advancement of information technology is also a solution to the problems in electronic medical record information sharing.