Electronic Healthcare Record Research Articles

Secure Patient Authentication Scheme in the Healthcare System Using Symmetric Encryption

Recently, the incorporation of state-of-the-art technology such as Electronic Healthcare Records (EHRs), networks, and cloud computing has transformed the traditional healthcare system. However, security problems have arisen as a result of the integration of technology. Secure remote user authentication is a core part of the healthcare system to validate the user’s identification via an unsecured communication network. Since then, several remote user authentication schemes have been presented, each with its own set of pros and limitations. As a result, security, malicious attacks, and privacy concerns are considered one of the main challenges related to the healthcare system. In this paper, we propose a safe user authentication scheme for patients in the healthcare system that overcomes these flaws and confirms the security of the proposed work using scyther, a formal security tool. In the healthcare environment, our work provides an effective means to construct an environment capable of setting, registering, storing, searching, analyzing, authentication, and verifying electronic healthcare information in order to protect the information of patients. Furthermore, our suggested scheme uses symmetric encryption based on the crypto-hash function for accessing the anomaly of the patient’s identity and One-Time Password (OTP). Towards the end of the study, the performance analysis results indicate a delicate balance of security and performance that is frequently lacking in previous works.

An architectural design study of electronic healthcare record systems with associated context parameters on MIMIC III

An architectural design study of electronic healthcare record systems with associated context parameters on MIMIC III

Fusion of sequential visits and medical ontology for mortality prediction

The goal of mortality prediction task is to predict the future death risk of patients according to their previous Electronic Healthcare Records (EHR). The main challenge of mortality prediction is how to design an accurate and robust predictive model with sequential, multivariate, sparse and irregular EHR data. In addition, the performance of model may be affected by lack of sufficient information of some patients with rare diseases in EHRs. To address these challenges, we propose a model to fuse Sequential visits and Medical Ontology to predict patients’ death risk. SeMO not only learns reasonable embeddings for medical concepts from sequential and irregular visits, but also exploits medical ontology to improve the prediction performance. With integration of multivariate features, SeMO learns robust representations of medical codes, mitigating data insufficiency and insightful sequential dependencies among patient’s visits. Experimental results on real world datasets prove that the proposed SeMO improves the prediction performance compared with the baseline approaches. Our model achieves an precision of up to 0.975. Compared with RNN, the precision has been improved up to 2.204%.

Development of an algorithm to classify primary care electronic health records of alcohol consumption: experience using data linkage from UK Biobank and primary care electronic health data sources

ObjectivesDevelop a novel algorithm to categorise alcohol consumption using primary care electronic health records (EHRs) and asses its reliability by comparing this classification with self-reported alcohol consumption data obtained from...

An explainable machine learning framework for lung cancer hospital length of stay prediction

This work introduces a predictive Length of Stay (LOS) framework for lung cancer patients using machine learning (ML) models. The framework proposed to deal with imbalanced datasets for classification-based approaches using electronic healthcare records (EHR). We have utilized supervised ML methods to predict lung cancer inpatients LOS during ICU hospitalization using the MIMIC-III dataset. Random Forest (RF) Model outperformed other models and achieved predicted results during the three framework phases. With clinical significance features selection, over-sampling methods (SMOTE and ADASYN) achieved the highest AUC results (98% with CI 95%: 95.3–100%, and 100% respectively). The combination of Over-sampling and under-sampling achieved the second-highest AUC results (98%, with CI 95%: 95.3–100%, and 97%, CI 95%: 93.7–100% SMOTE-Tomek, and SMOTE-ENN respectively). Under-sampling methods reported the least important AUC results (50%, with CI 95%: 40.2–59.8%) for both (ENN and Tomek- Links). Using ML explainable technique called SHAP, we explained the outcome of the predictive model (RF) with SMOTE class balancing technique to understand the most significant clinical features that contributed to predicting lung cancer LOS with the RF model. Our promising framework allows us to employ ML techniques in-hospital clinical information systems to predict lung cancer admissions into ICU.

Catatonic Episodes Related to Substance Use: A Cross-Sectional Study Using Electronic Healthcare Records

Objective: Substance use has increasingly been linked to the onset of catatonic episodes; however, no large observational studies have examined this association. This study aimed to identify catatonic episodes temporally associated with acute intoxication, withdrawal or chronic substance use, investigate which substances were involved, and compare clinical characteristics of substance-related and non-substance-related catatonic episodes. Methods: This study retrospectively identified all catatonic episodes recorded in an electronic case register hosted at a large secondary mental health trust in London, UK. Episodes were categorized as substance-related if the clinical record reported either a positive urine drug screen, an ICD-10 diagnosis of a mental or behavioral disorder due to substance use, or documented substance use between two weeks prior to the catatonic episode and the date of the catatonic episode. Results: 108 of 2130 catatonic episodes (5.1%) were deemed substance-related. The number of contemporaneously reported substance-related episodes increased between 2007 and 2016 [r = 0.72, p = 0.02]. Episodes in the context of acute intoxication (n = 54) were most frequently related to cannabis (n = 31) or cocaine (n = 5) use, whilst those in the context of drug withdrawal (n = 8) were most commonly related to alcohol, opioids and benzodiazepines. There were 50 episodes of catatonia associated with chronic substance use without intoxication or withdrawal, of which the majority were related to cannabis use (n = 37). 21 episodes had overlapping intoxication, withdrawal and chronic use of different substances within an episode. Compared to catatonic episodes not related to substance use, episodes of substance-related catatonia occurred in individuals who were younger (mean age 31.3 years [SD 12.2] vs 35.7 years [SD 16.3], p = 0.01) and more likely to be men (74.0% vs 54.3%, p < 0.001). The clinical features of catatonia were similar between the two groups. Conclusions: A relatively small proportion of catatonic episodes were temporally associated with reported substance use within their electronic records. Substance-related catatonic episodes were mostly related to cannabis use, but other substances including cocaine, alcohol, opioids and benzodiazepines were sometimes implicated. This is likely an underestimate of substance-related catatonia use due to issues with documentation and appropriate investigation.

DS-Chain: A secure and auditable multi-cloud assisted EHR storage model on efficient deletable blockchain

In recent years, cloud storage service has widely attracted the healthcare industry. Healthcare organizations are gradually outsourcing the massive-scale electronic healthcare records (EHRs) on cloud paradigm. This specialized cloud-assisted EHR storage architecture facilitates the healthcare organizations with high scalability, flexibility, low-cost operations, and availability to outsourced EHRs. As EHR often contains patients’ sensitive medical information, it becomes essential to ensure the confidentiality and proper secrecy of the outsourced EHRs. Moreover, in the cloud-assisted EHR storage model, the patients no longer have direct control over their outsourced EHRs, which may also cause severe integrity and confidentiality related security issues. Presently, the healthcare industry observes that the emerging immutable blockchain technology properly attains the basic security needs for developing a secure cloud assisted EHR storage framework. Therefore, in this paper, we introduce a model named “DS-Chain”11A preliminary version of this paper was presented at the 22nd IEEE International Conference on High Performance Computing and Communications (IEEE HPCC - 2020).. - a novel deletable consortium blockchain based secure EHR storage model in a multi-cloud paradigm. The model’s key idea is to integrate each EHR outsourcing’s operations into a transaction on a novel efficient consortium blockchain. The proposed model ensures the confidentiality of the EHR’s sensitive medical information and guarantees the proper integrity and correctness of the outsourced EHRs. On the other hand, we employ the collaborative multi-cloud storage model that offers reasonable durability and availability for the outsourced EHRs in the cloud paradigm. Furthermore, we also arrange all the transactions according to their corresponding EHR’s type over the blockchain network, ensuring efficient block deletion. The detailed security analysis with proper formal proofs guarantees the computational intractability of the proposed model. Finally, the extensive performance analysis with test-simulations illustrates the feasibility and practicability of the proposed model.

Yellow fever vaccine usage in the United States and risk of neurotropic and viscerotropic disease: A retrospective cohort study using three healthcare databases

BackgroundYellow fever (YF) vaccines are highly effective and have a well-established safety profile despite the risk of rare serious adverse events (SAEs), vaccine-associated neurotropic (YEL-AND) and viscerotropic disease (YEL-AVD). This study aimed to describe US civilian YF vaccine usage, the population characteristics and pre-existing immunosuppressive medical conditions among those vaccinated, and to provide updated risk estimates of neurotropic and viscerotropic disease post-vaccination. MethodsA retrospective cohort study was conducted using de-identified patient information from Optum Electronic Healthcare Record (EHR) (2007–2019), Optum Clinformatics Data Mart (CDM) (2004–2019) and IBM MarketScan (2007–2019) databases. YF vaccine recipients were identified using relevant vaccination and procedural codes. Demographic characteristics and pre-existing medical conditions were described. Incidence proportions with 95% confidence intervals (CI) of neurotropic and viscerotropic diseases occurring ≤ 30 days post-vaccination, after exclusion of unlikely cases based on current clinical guidelines of YEL-AND and YEL-AVD, were calculated. ResultsA total of 92,205, 46,539 and 125,235 YF vaccine recipients were retrieved from Optum EHR, Optum CDM and IBM MarketScan databases, respectively. The majority of vaccine recipients were aged < 60 years (highest proportion aged 18–29 years) with a higher proportion of females overall. Few vaccine recipients (<1%) had conditions predisposing them to immunosuppression. Four non-fatal cases of neurotropic disease and zero cases of viscerotropic disease were identified. The incidence proportion of post-vaccination neurotropic disease was 1.41 (95% CI: 0.15–6.61) and 3.04 (95% CI: 0.86–8.11) per 100,000 vaccine recipients in Optum EHR and IBM MarketScan, respectively, with no events identified in Optum CDM. ConclusionsThis study provides updated insights into current YF vaccine usage in US civilian recipients and supports the safety profile of YF vaccines in US practice. The low frequency of pre-existing immunosuppressive medical conditions among vaccine recipients suggests good adherence to vaccination guidelines by healthcare practitioners. The risk of developing neurotropic and viscerotropic disease post-vaccination remains rare.

A Blockchain and NLP Based Electronic Health Record System: Indian Subcontinent Context

The healthcare system in the Indian subcontinent is plagued with numerous issues related to the access, transfer, and storage of patient's medical records. The lack of infrastructure to properly communicate and track records between all key participants has allowed the distribution of counterfeit drugs, dependency on unsafe methods of communication, and lack of trust between patients and providers. During the global COVID-19 pandemic, the need for a robust communication and record tracking system has been further emphasized. To facilitate efficient communication and mitigate the mentioned issues, a nationwide EHR (electronic health record) system must be introduced to bring the healthcare system into digital space. To further enhance security, efficiency, and cost, the innovation of Blockchain is introduced. Blockchain is a decentralized data structure that allows secure transactions between untrusted parties without needing a central authority. In this paper, a Hyperledger fabric-based Blockchain Electronic Healthcare Record (EHR) system is proposed. The system is integrated with technologies such as NLP (Natural Language Processing), and Machine Learning to provide users with practical features.

Extended Cohort for E-health, Environment and DNA (EXCEED) COVID-19 focus

Background: New data collection in established longitudinal population studies provides an opportunity for studying the risk factors and sequelae of the novel coronavirus disease 2019 (COVID-19), plus the indirect impacts of the COVID-19 pandemic on wellbeing. The Extended Cohort for E-health, Environment and DNA (EXCEED) cohort is a population-based cohort (N&gt;11,000), recruited from 2013 in Leicester, Leicestershire and Rutland. EXCEED includes consent for electronic healthcare record (EHR) linkage, spirometry, genomic data, and questionnaire data. Methods: Between May 2020 and July 2021, a new questionnaire was deployed in EXCEED, which captured COVID-19 symptoms, general physical and mental health, plus socioeconomic and environmental factors during the pandemic. An online system was developed to invite new participants to join EXCEED, with informed consent being provided online. New and existing participants then completed the COVID-19 questionnaire online. A subset of the new questionnaire respondents were invited to participate in COVID-19 serology substudies, using home antibody testing kits. Results: In total, 3,693 participants provided COVID-19 infection status (median age 62.9 (IQR 54.7-69.2), 58.9% female). Trends of monthly incidence proportions of COVID-19 in EXCEED (self-report or symptom-predicted) approximated local and national figures. Regression analysis of 2,768 participants with linked EHR data showed no obvious monotonic relationship between number of chronic diseases (of 16 pre-specified diseases) and COVID-19 infection. There were 2,144 participants with valid results from a kit allowing differentiation between antibodies due to vaccination or infection. Of these, 8.5% had results consistent with previous COVID-19 infection, and 85.9% had evidence of COVID-19 vaccination, but without evidence of infection. Conclusions: Enriching EXCEED with a new COVID-19 questionnaire and serology data may improve understanding of the risk factors, clinical sequelae and broader impacts of the COVID-19 pandemic in the general population. Controlled access to these data for bona fide researchers is via application to the EXCEED study.

Smart Medication for secure health with Internet of Things

For over a decade, network and technology has been improved to an equal extent which has led to an easy transmission of data over the entire globe. Besides growth and development of Internet of Things in our daily life such as health care and home automation, secured transmission is significant regarding how confidential and secured the information is, to assure the privacy. The data related to the health are acquired from medical devices and monitoring systems. Some information are acquired from the patient. In this project we will be more particular in gathering the information from the patient. They ultimately end up in Electronic Healthcare Records. These records are sent to labs, doctors, nurses and other parties involved. This enables doctors, caregivers to monitor patient's physiological conditions at any time according to the information obtained. Hence, it is based on this that this research work is carried out to determine the level at which the internet has been able to improve the delivery of healthcare services in the healthcare delivery system in Nigeria. Keywords: Internet of Things, Home Automation, Electronic Healthcare Records, medical devices, monitoring systems.

Trends in the Prescription of Benzodiazepine Receptor Agonists from 2009 to 2020: A Retrospective Study Using Electronic Healthcare Record Data of a University Hospital in Japan.

In recent years, the prescription trends of benzodiazepine receptor agonists (BZRAs) have not been investigated in Japan despite the publication of guidelines that promote cautious use of BZRAs. The prescription trend of BZRAs was assessed using the electronic healthcare records data of a University Hospital in Japan. The data from April 2009 to March 2021 were used. The following three types of outcomes were set: the proportion of patients who were prescribed with BZRAs within those prescribed hypnotics or anxiolytics; the mean number of the types of prescribed BZRAs, and the mean average daily doses of BZRAs. The same analysis was conducted for benzodiazepines (BZDs) and non-benzodiazepines (Z-drugs). As a result, we found that the proportions of patients prescribed BZRAs within those prescribed hypnotics or anxiolytics began to decrease, particularly from 2015 for patients aged <75 years and those aged ≥75 years. Further, the degree of decrease was larger in patients aged ≥75 years. The proportion for BZDs decreased particularly in the study period, and the proportion for Z-drugs also began to decrease approximately from 2016 in patients aged ≥75 years. The results suggest a possibility that guidelines affected the decreased prescriptions of BZRAs.

Identifying and evaluating clinical subtypes of Alzheimer\u2019s disease in care electronic health records using unsupervised machine learning

BackgroundAlzheimer’s disease (AD) is a highly heterogeneous disease with diverse trajectories and outcomes observed in clinical populations. Understanding this heterogeneity can enable better treatment, prognosis and disease management. Studies to date have mainly used imaging or cognition data and have been limited in terms of data breadth and sample size. Here we examine the clinical heterogeneity of Alzheimer's disease patients using electronic health records (EHR) to identify and characterise disease subgroups using multiple clustering methods, identifying clusters which are clinically actionable.MethodsWe identified AD patients in primary care EHR from the Clinical Practice Research Datalink (CPRD) using a previously validated rule-based phenotyping algorithm. We extracted and included a range of comorbidities, symptoms and demographic features as patient features. We evaluated four different clustering methods (k-means, kernel k-means, affinity propagation and latent class analysis) to cluster Alzheimer’s disease patients. We compared clusters on clinically relevant outcomes and evaluated each method using measures of cluster structure, stability, efficiency of outcome prediction and replicability in external data sets.ResultsWe identified 7,913 AD patients, with a mean age of 82 and 66.2% female. We included 21 features in our analysis. We observed 5, 2, 5 and 6 clusters in k-means, kernel k-means, affinity propagation and latent class analysis respectively. K-means was found to produce the most consistent results based on four evaluative measures. We discovered a consistent cluster found in three of the four methods composed of predominantly female, younger disease onset (43% between ages 42–73) diagnosed with depression and anxiety, with a quicker rate of progression compared to the average across other clusters.ConclusionEach clustering approach produced substantially different clusters and K-Means performed the best out of the four methods based on the four evaluative criteria. However, the consistent appearance of one particular cluster across three of the four methods potentially suggests the presence of a distinct disease subtype that merits further exploration. Our study underlines the variability of the results obtained from different clustering approaches and the importance of systematically evaluating different approaches for identifying disease subtypes in complex EHR.

Exploring population pharmacokinetic models in patients treated with vancomycin during continuous venovenous haemodiafiltration (CVVHDF)

BackgroundTherapeutic antibiotic dose monitoring can be particularly challenging in septic patients requiring renal replacement therapy. Our aim was to conduct an exploratory population pharmacokinetic (PK) analysis on PK of vancomycin following intermittent infusion in critically ill patients receiving continuous venovenous haemodiafiltration (CVVHDF); focussing on the influence of dialysis-related covariates.MethodsThis was a retrospective single-centre tertiary level intensive care unit (ICU) study, which included patients treated concurrently with vancomycin and CVVHDF between January 2015 and July 2016. We extracted clinical, laboratory and dialysis data from the electronic healthcare record (EHR), using strict inclusion criteria. A population PK analysis was conducted with a one-compartment model using the PMetrics population PK modelling package. A base structural model was developed, with further analyses including clinical and dialysis-related data to improve model prediction through covariate inclusion. The final selected model simulated patient concentrations using probability of target attainment (PTA) plots to investigate the probability of different dosing regimens achieving target therapeutic concentrations.ResultsA total of 106 vancomycin dosing intervals (155 levels) in 24 patients were examined. An acceptable 1-compartment base model was produced (Plots of observed vs. population predicted concentrations (Obs–Pred) R2 = 0.78). No continuous covariates explored resulted in a clear improvement over the base model. Inclusion of anticoagulation modality and vasopressor use as categorical covariates resulted in similar PK parameter estimates, with a trend towards lower parameter estimate variability when using regional citrate anti-coagulation or without vasopressor use. Simulations using PTA plots suggested that a 2 g loading dose followed by 750 mg 12 hourly as maintenance dose, commencing 12 h after loading, is required to achieve adequate early target trough concentrations of at least 15 mg/L.ConclusionsPTA simulations suggest that acceptable trough vancomycin concentrations can be achieved early in treatment with a 2 g loading dose and maintenance dose of 750 mg 12 hourly for critically ill patients on CVVHDF.

A class-contrastive human-interpretable machine learning approach to predict mortality in severe mental illness

Machine learning (ML), one aspect of artificial intelligence (AI), involves computer algorithms that train themselves. They have been widely applied in the healthcare domain. However, many trained ML algorithms operate as ‘black boxes’, producing a prediction from input data without a clear explanation of their workings. Non-transparent predictions are of limited utility in many clinical domains, where decisions must be justifiable. Here, we apply class-contrastive counterfactual reasoning to ML to demonstrate how specific changes in inputs lead to different predictions of mortality in people with severe mental illness (SMI), a major public health challenge. We produce predictions accompanied by visual and textual explanations as to how the prediction would have differed given specific changes to the input. We apply it to routinely collected data from a mental health secondary care provider in patients with schizophrenia. Using a data structuring framework informed by clinical knowledge, we captured information on physical health, mental health, and social predisposing factors. We then trained an ML algorithm and other statistical learning techniques to predict the risk of death. The ML algorithm predicted mortality with an area under receiver operating characteristic curve (AUROC) of 0.80 (95% confidence intervals [0.78, 0.82]). We used class-contrastive analysis to produce explanations for the model predictions. We outline the scenarios in which class-contrastive analysis is likely to be successful in producing explanations for model predictions. Our aim is not to advocate for a particular model but show an application of the class-contrastive analysis technique to electronic healthcare record data for a disease of public health significance. In patients with schizophrenia, our work suggests that use or prescription of medications like antidepressants was associated with lower risk of death. Abuse of alcohol/drugs and a diagnosis of delirium were associated with higher risk of death. Our ML models highlight the role of co-morbidities in determining mortality in patients with schizophrenia and the need to manage co-morbidities in these patients. We hope that some of these bio-social factors can be targeted therapeutically by either patient-level or service-level interventions. Our approach combines clinical knowledge, health data, and statistical learning, to make predictions interpretable to clinicians using class-contrastive reasoning. This is a step towards interpretable AI in the management of patients with schizophrenia and potentially other diseases.

Management of cardiovascular disease using an mHealth tool: a randomized clinical trial

Atherosclerotic cardiovascular disease (ASCVD) is a leading cause of death and morbidity worldwide. This randomized controlled, single-center, open-label trial tested the impact of a mobile health (mHealth) service tool optimized for ASCVD patient care. Patients with clinical ASCVD were enrolled and randomly assigned to the intervention or control group. Participants in the intervention group were provided with a smartphone application named HEART4U, while a dedicated interface integrated into the electronic healthcare record system was provided to the treating physicians. A total of 666 patients with ASCVD were enrolled, with 333 patients in each group. The estimated baseline 10-year risk of cardiovascular disease was 9.5% and 10.8% in the intervention and control groups, respectively, as assessed by the pooled cohort risk equations. The primary study endpoint was the change in the estimated risk at six months. The estimated risk increased by 1.3% and 1.1%, respectively, which did not differ significantly (P = 0.821). None of the secondary study endpoints showed significant differences between the groups. A post-hoc subgroup analysis showed the benefit was greater if a participant in the intervention group accessed the application more frequently. The present study demonstrated no significant benefits associated with the use of the mHealth tool in terms of the predefined study endpoints in stable patients with ASCVD. However, it also suggested that motivating patients to use the mHealth tool more frequently may lead to greater clinical benefit. Better design with a positive user experience needs to be considered for developing future mHealth tools for ASCVD patient care.Trial Registration: ClinicalTrials.gov NCT03392259

Analgesic prescribing in patients with inflammatory arthritis in England: an observational study using electronic healthcare record data.

ObjectivesInternational data suggest inflammatory arthritis (IA) pain management frequently involves opioid prescribing, despite little evidence of efficacy, and potential harms. We evaluated analgesic prescribing in English National Health Service-managed patients with IA.MethodsRepeated cross-sectional analyses in the Consultations in Primary Care Archive (primary care consultation and prescription data in nine general practices from 2000 to 2015) evaluated the annual prevalence of analgesic prescriptions in: (i) IA cases (RA, PsA or axial spondyloarthritis [SpA]), and (ii) up to five age-, sex- and practice-matched controls. Analgesic prescriptions were classified into basic, opioids, gabapentinoids and oral NSAIDs, and sub-classified into chronic and intermittent (≥3 and 1–2 prescriptions per calendar year, respectively).ResultsIn 2000, there were 594 cases and 2652 controls, rising to 1080 cases and 4703 controls in 2015. In all years, most (65.3–78.5%) cases received analgesics, compared with fewer (37.5–41.1%) controls. Opioid prescribing in cases fell between 2000 and 2015 but remained common with 45.4% (95% CI: 42.4%, 48.4%) and 32.9% (95% CI: 29.8%, 36.0%) receiving at least 1 and ≥3 opioid prescriptions, respectively, in 2015. Gabapentinoid prescription prevalence in cases increased from 0% in 2000 to 9.5% (95% CI: 7.9%, 11.4%) in 2015, and oral NSAID prescription prevalence fell from 53.7% (95% CI: 49.6%, 57.8%) in 2000 to 25.0% (95% CI: 22.4%, 27.7%) in 2015. Across years, analgesic prescribing was commoner in RA than PsA/axial SpA, and 1.7–2.0 times higher in cases than controls.ConclusionsAnalgesic prescribing in IA is common. This is at variance with existing evidence of analgesic efficacy and risks, and guidelines. Interventions are needed to improve analgesic prescribing in this population.

A Novel Methodology for Providing Security in Electronic Health Record Using Fuzzy Based Multi Agent System

&lt;p class="0abstract"&gt;Privacy and security are crucial when it comes to the implementation of Electronic Healthcare Records (HER). Whenever a patient visits a doctor, their health records are updated since it consists of vital information on the patient's health and well-being. It also comprises of description about the previous and current treatment quality.Multi-Agent Systems can support E-Healthcare applications for improving quality of life. The availability and use of extensive systems for EHR has increased dramatically. The EHR technology currently available consists of health information of various patients which helps those people to monitor their health. These information should be protected from being altered or mishandled. Various studies have been conducted in the past literature to improve the protection and privacy requirements in E-health services. Despite this, it hasn't been entirely improved. This article proposes a Fuzzy based multi-agent system architecture that uses agents and fuzzy logic to monitor the flow and access of the EHR record using fuzzy logic and multi agents. Architecture comprises of multi agent and fuzzy systems are proposed. In this system, we have employed Action/ Computation (Interface) agent, communication interface agent and verification agent and Communication Module Agent. These agents collaboratively worked one another in order to obtain the desired output. These agent based e-health system can increase the accuracy of data transfer by providing additional security in selecting the user who handles the data. It also monitors the communication between different medical units in the health system.&lt;/p&gt;

Effect of regulatory interventions on agomelatine use in Spain: A multiple intervention time-series analysis in a nationwide electronic healthcare record database.

Liver injury is an important identified risk for agomelatine and several measures were put in place to prevent and minimize such risk. The study aims to assess the impact of four interventions on the incidence of agomelatine use, particularly among patients aged ≥75 in Spain between 2011 and 2018. Quasi-experimental interrupted time-series analysis to examine data from a nationwide electronic healthcare record database (BIFAP). Quarterly cumulative incidence of agomelatine use per 100 000 patients was calculated and the impact of four regulatory interventions was quantified. The incidence of agomelatine use decreased by 85% and 87% from first quarter 2011 to last quarter 2018 in patients below and above 75 years old, respectively. Regulatory actions taken were not associated with an immediate and significant falling level of use or slope. The incidence was less than expected 6months after the first and third intervention for patients below and above 75 years old, and more than expected after the second and fourth intervention for both populations, though these analyses were underpowered to observe significant results. The downward trend became less pronounced, reaching a residual level of use, which remained stable in the last segment of the study period. New users of agomelatine decreased throughout the study period, starting before interventions took place. The effect of specific interventions might be masked by the progressive decrease tendency, constant over the study period. The effects of external factors that might overlap, unintended consequences, and issues concerning statistical modeling in situations where rates are already falling, should be considered when interpreting the results.

Development of a Structured Query Language and Natural Language Processing Algorithm to Identify Lung Nodules in a Cancer Centre.

Importance: The stratification of indeterminate lung nodules is a growing problem, but the burden of lung nodules on healthcare services is not well-described. Manual service evaluation and research cohort curation can be time-consuming and potentially improved by automation.Objective: To automate lung nodule identification in a tertiary cancer centre.Methods: This retrospective cohort study used Electronic Healthcare Records to identify CT reports generated between 31st October 2011 and 24th July 2020. A structured query language/natural language processing tool was developed to classify reports according to lung nodule status. Performance was externally validated. Sentences were used to train machine-learning classifiers to predict concerning nodule features in 2,000 patients.Results: 14,586 patients with lung nodules were identified. The cancer types most commonly associated with lung nodules were lung (39%), neuro-endocrine (38%), skin (35%), colorectal (33%) and sarcoma (33%). Lung nodule patients had a greater proportion of metastatic diagnoses (45 vs. 23%, p < 0.001), a higher mean post-baseline scan number (6.56 vs. 1.93, p < 0.001), and a shorter mean scan interval (4.1 vs. 5.9 months, p < 0.001) than those without nodules. Inter-observer agreement for sentence classification was 0.94 internally and 0.98 externally. Sensitivity and specificity for nodule identification were 93 and 99% internally, and 100 and 100% at external validation, respectively. A linear-support vector machine model predicted concerning sentence features with 94% accuracy.Conclusion: We have developed and validated an accurate tool for automated lung nodule identification that is valuable for service evaluation and research data acquisition.