Hospital Information System Research Articles

Constructing a Hospital Department Development-Level Assessment Model: Machine Learning and Expert Consultation Approach in Complex Hospital Data Environments.

Every hospital manager aims to build harmonious, mutually beneficial, and steady-state departments. Therefore, it is important to explore a hospital department development assessment model based on objective hospital data. This study aims to use a novel machine learning algorithm to identify key evaluation indexes for hospital departments, offering insights for strategic planning and resource allocation in hospital management. Data related to the development of a hospital department over the past 3 years were extracted from various hospital information systems. The resulting data set was mined using neural machine algorithms to assess the possible role of hospital departments in the development of a hospital. A questionnaire was used to consult senior experts familiar with the hospital to assess the actual work in each hospital department and the impact of each department's development on overall hospital discipline. We used the results from this questionnaire to verify the accuracy of the departmental risk scores calculated by the machine learning algorithm. Deep machine learning was performed and modeled on the hospital system training data set. The model successfully leveraged the hospital's training data set to learn, predict, and evaluate the working and development of hospital departments. A comparison of the questionnaire results with the risk ranking set from the departments machine learning algorithm using the cosine similarity algorithm and Pearson correlation analysis showed a good match. This indicates that the department development assessment model and risk score based on the objective data of hospital systems are relatively accurate and objective. This study demonstrated that our machine learning algorithm provides an accurate and objective assessment model for hospital department development. The strong alignment of the model's risk assessments with expert opinions, validated through statistical analysis, highlights its reliability and potential to guide strategic hospital management decisions.

Toward Personalized Care and Patient Empowerment and Perspectives on a Personal Health Record in Hemophilia Care: Qualitative Interview Study.

To enable personalized treatment and shared decision-making in chronic care, relevant health information is collected. However, health information is often fragmented across hospital information systems, digital health apps, and questionnaire portals. This also pertains to hemophilia care, in which scattered information hampers integrated care. We intend to co-design a nationwide digital personal health record (PHR) for patients to help manage their health information. For this, user perspectives are crucial. This study aims to assess patients' and health care providers' perspectives regarding the use of a PHR in hemophilia care in the Netherlands, required functionalities, and expectations and concerns. In this semistructured interview study, 19 pediatric and adult persons with hemophilia, parents, and women with other inherited bleeding disorders, as well as 18 health care providers working within and outside of hemophilia treatment centers, participated. Perspectives of patients and providers were explored separately. To explore requirements, participants were asked to prioritize functionalities. Participants expected a PHR would increase the transparency of health information, improve patients' understanding of their illness, and help the coordination of care between health care providers and institutions. Prioritized functionalities included the integration of relevant health information and patient-entered data. Formulated expectations and concerns focused on 4 themes: usability, safety, inclusiveness, and implementation. While patients expressed worries over medicalization (ie, more confrontational reminders of their illness), providers were concerned about an increased workload. People with hemophilia, their parents, and health care providers welcomed the development of a PHR, as they expected it would result in better coordinated care. Formulated expectations and concerns will contribute to the successful development of a PHR for persons with hemophilia, and ultimately, for all persons with a chronic condition.

Breast cancer and cervical cancer: a comparison of the period before and during the COVID-19 pandemic

BackgroundThe coronavirus 2019 (COVID-19) pandemic impacted cancer health care in several countries, with delays in the detection and treatment of breast and cervical cancer. The objective of this study is to analyze and compare the screening, diagnosis and treatment of breast and cervical cancer in the pre-COVID period and during the COVID-19 period.MethodsCross-sectional study with secondary data collected from the Mortality Information System (SIM), Hospital Information System (SIH), Ambulatory Information System (SIA) and the Oncology Panel (PO) of breast cancer notifications with ICD C50.0 to C50.9 and cervix ICD C53.0 to C53.9, The analyzed period before the pandemic was from March 1 to October 1, 2019, and during the pandemic from March 1 to October 1, 2020. The period from 2013 to 2022 was also analyzed with the same information, including the number of diagnoses, treatments, and deaths from breast cancer and cervical cancer. The study population consisted of Brazilian women aged 25 to 70 years. In order to compare categorical variables between periods, the Chi-Square or Fisher’s Exact tests, and Mann-Whitney U tests were applied, and the Poisson Regression model was applied to model the number of reported cases of COVID-19 and the amount of procedures.ResultsThere was a decrease in the number of mammograms and cytopathological exams during COVID-19, as well as a decrease in cases of breast and cervical cancer. The Poisson regression showed that the increase in the number of COVID-19 cases caused a decrease in the number of breast cytopathological examinations, cervical-vaginal cytopathological examinations/microflora and screening, diagnosis, initiation of treatment for breast cancer and deaths from this disease. Meanwhile, in some regions of Brazil, as the number of Covid-19 increased, there was a significantly increase in the number of mammograms performed and cervical cancer diagnoses.ConclusionsThe COVID-19 period in 2020 significantly impacted screening, diagnosis, treatment for breast and cervical cancer.

Retrospective analysis of the resuscitation room management of nontraumatic critically ill children in a university emergency department (OBSERvE-DUS-PED study)

The establishment of a resuscitation room management for nontraumatic critically ill children appears to make sense. This study collected data of pediatric patients suffering from nontraumatic critically ill conditions treated in aresuscitation room. The retrospective OBSERvE-DUS-PED study (November 2019-October 2022) recorded pediatric patients (age < 18years) who were admitted to the emergency department (ED) for resuscitation room care. The routinely documented data on treatment were taken from the hospital information system MEDICO® and the patient data management system COPRA® in accordance with the OBSERvE dataset. The study was approved by the Ethics Committee of the Medical Faculty of the Heinrich Heine University (2023-2377). The study included 52pediatric resuscitation room patients. Adolescents aged 14-17years were the most frequent in the cohort representing 37% of the total and neonates/infants (0-1year) were lowest at 8%. The most common symptoms categorized according to ABCDE problems were disturbance of consciousness(D) at 61%, cardiovascular failure(C) at 25%, respiratory insufficiency(B) at 6%, airway obstruction(A) and exposure/environment (E) problems each at 4%. The out-of-hospital and in-hospital emergency procedures were performed with the following frequencies: venous (58%vs. 65%), intraosseous (14%vs. 2%) and central venous access (0%vs. 12%), invasive airway management (35% vs.8%), cardiopulmonary resuscitation (21%vs. 10%), vasopressors (15%vs. 17%), and intra-arterial pressure measurement (0%vs. 17%). The mean duration of resuscitation room management was 70 ± 43 min. The 30-day mortality was 17%. The OBSERvE-DUS-PED study demonstrates the major challenges in the care of critically ill nontraumatic pediatric patients, both in out-of-hospital and in-hospital management. The variety and complexity of the referral diagnoses as well as the immediate vital threat to the patients make it appear sensible to treat such patients primarily in aresuscitation room of the ED due to the available material, infrastructural and personnel resources.

New-onset diabetes mellitus in patients with COVID19 infection admitted to a tertiary care hospital: A single-center experience.

To determine the frequency of new-onset diabetes mellitus (NODM) in patients with COVID-19 in a tertiary care hospital. It was a retrospective descriptive study carried out in Lady Reading Hospital Peshawar, Khyber Pakhtunkhwa province of Pakistan from November 2021 to April 2022. All patients having new onset Diabetes Mellitus (NODM) were identified among a total of 300 patients admitted to the hospital with COVID-19 infection. Patients' data including relevant investigations were accessed through the hospital management information system (HMIS). SPSS version-23 was used for data entry and statistical analysis. Out of 300 COVID-19 patients included in the study, 163 (54.3%) were female and 137(45.7%) were male. The mean age of the patients was 56.80±13.72 (IQR 15) years. Frequency of the new onset diabetes was 44(14.7%); 19 (6.33%) male and 25(8.33%) female. Among the 44 NODM patients, the majority (57%) were female (p=0.720). Most (64%) of the patients with new-onset DM were in the middle age (p=0.018). A significant number of patients with COVID-19 infection are prone to develop new-onset diabetes during their admission to the hospital.

Clinical Characteristics, Serotypes and Antimicrobial Resistance of Invasive Salmonella Infections in HIV-Infected Patients in Hangzhou, China, 2012-2023.

Developing countries, invasive Salmonella infections can cause considerable morbidity and mortality. There is a relative lack of data on coinfection with Salmonella in HIV-infected patients in Hangzhou, China. In this study, we manually collected case data of patients aged >18 years with HIV combined with invasive Salmonella infections admitted to Xixi Hospital in Hangzhou from January 2012 to August 2023 by logging into the Hospital Information System, and identified 26 strains of invasive Salmonella using a fully automated microbiological identification system and mass spectrometer. Serotypes were determined using Salmonella diagnostic sera based on the White-Kauffmann-Le Minor scheme. Drug sensitivity tests were performed using the automated instrumental method of the MIC method. A total of 26 HIV-infected patients with invasive Salmonella coinfections were identified over 11 years; Twenty-five of the 26 patients (96.2%) were males, with a mean age of 33.5 years (26.75, 46.75). The most common type of infection was bloodstream infection (92.3%). One patient also had concomitant meningitis and osteoarthritis, followed by pneumonia (7.7%). The presence of multiple bacterial infections or even multiple opportunistic pathogens was clearly established in 7 (26.9%) patients. Three (11.6%) patients were automatically discharged from the hospital with deterioration of their condition, and one (3.8%) patient died. Salmonella enteritidis was the most common serotype in 6 patients (23.2%), and Salmonella Dublin was the most common serotype in 6 patients (23.2%). Drug sensitivity results revealed multidrug resistance in a total of 8 (30.8%) patients. The clinical presentation of invasive Salmonella infection in HIV patients is nonspecific and easily masked by other mixed infections. A CD4+ count <100 cells/µL and comorbid intestinal lesions may be important susceptibility factors. Salmonella has a high rate of resistance to common antibiotics, and the risk of multidrug resistance should not be ignored.

Neutrophil/Lymphocyte Ratio as a Biomarker of Response to H1-Antihistamine Therapy in Patients with Chronic Spontaneous Urticaria

Abstract Backgrounds: A large proportion of patients with chronic spontaneous urticaria (CSU) are resistant to a standard dose of antihistamine. Acknowledged biomarkers for identifying these patients have not been determined. The neutrophil/lymphocyte ratio (NLR) has been considered as an important indicator of inflammation in chronic diseases. Aims: To explore whether NLR could serve as a biomarker for predicting the response to H1-antihistamine in patients with CSU. Methods: This hospital-based, retrospective study included 109 patients with CSU diagnosed from 2017 to 2020 in our clinic and divided them into two groups by their responses to the 2-week antihistamine therapy of standard-dose: 69 with H1-antihistamine-refractory and 40 with non-H1-antihistamine-refractory CSU. The laboratory test results were collected from the hospital information system and integrated with SPSS software. Results: Patients refractory to H1-antihistamine had significantly higher median NLR (P = 0.039), age (3 P = 0.021), complement C3 (P = 0.026), presence of elevated WBC (P = 0.026) and elevated monocytes (MONO) (P = 0.045) and significantly lower IgM (P = 0.022). The binary logistic regression model revealed that NLR was significantly associated with H1-antihistamine-refractory of CSU (odds ratio (OR) 1.717, 95% confidence interval (CI) 1.065–2.766, P = 0.026), which was consistent with that after adjusted for potential confounding factors including age, complement C3, presence of elevated WBC and MONO, and IgM (OR 1.681, 95% CI 1.019–2.773, P = 0.042). Conclusion: Our results showed a strong and significant association between higher NLR and H1-antihistamine resistance in CSU, suggesting that NLR may be a potential biomarker for predicting the response to H1-antihistamine therapy in patients with CSU.

The relationship of COVID-19 severity with laboratory findings and neutrophil-to-lymphocyte ratio in patients admitted to a large teaching hospital in Iran: A cross-sectional study.

COVID-19 patients might be admitted to the hospital based on their clinical manifestations or to the intensive care unit (ICU) due to the severity of their symptoms or critical situation. Our main objective was to investigate clinical and demographic factors influencing COVID-19 patients' admission to the ICU and length of stay (LOS) using extracted data from the hospital information systems in Iran. The data of hospitalized patients with confirmed COVID-19 were retrieved from the health information system of Imam Khomeini Hospital Complex, Tehran, Iran between March 2020 and February 2022. The primary outcome was the ICU admission, and the secondary outcome was the LOS. The correlation analysis between laboratory findings and demographic data with ICU admission and LOS was done using SPSS 21.0, and p < 0.05 was considered significant. Of all the 4156 patients, 2391 (57.5%) were male and the mean age was 58.69 ± 8.19 years. Of these, 9.5% of patients were admitted to ICU at any time point during their hospital stay. Age and laboratory variables such as neutrophil-to-lymphocyte ratio (NLR), ALT (U/L), albumin (g/dL), plasma glucose (mg/dL), ferritin levels (ng/mL), and phosphorous levels (mg/dL) shown the significant relationship with ICU admission. Also, being a smoker and having hypoxemia had a significant relationship with longer stays in the hospital. In this study, we validated a cut-off value of 4.819 for NLR, calculated at hospitalization, as a useful predictor of disease progression and occurrence of serious clinical outcomes, such as ICU admission. The study examined various clinical factors associated with ICU admission in COVID-19 patients. The findings suggest that certain factors can increase the risk of ICU admission and influence the length of hospital stay which should be focused in future studies.

Protection of personal data and commercially confidential information under the Clinical Trials Regulation (EU) No. 536/ 2014 – EMA “Revised CTIS Transparency Rules”

The Clinical Trials Regulation (EU) No 536/2014 (CTR) came in force on January 31, 2022, specifying requirements for performing clinical trials in the EU and the European Economic Area (EEA). The CTR and the Clinical Trials Information System (CTIS) harmonise the approval process of clinical trials across the EU/EEA, provide a transparent process, and increase public access to information from clinical trials. Such transparency efforts must assure protection of personal data and commercially confidential information. The CTIS transparency rules were revised and recently implemented. The revised CTIS transparency rules focus on easier and earlier access by the public to documents of primary focus for patients and researchers. This article highlights the protection of personal data and commercially confidential information in public clinical trial documents according to the revised rules and also the EMA Policy 0070, which have overlapping transparency requirements. Medical writers and other functions involved in the preparation of regulatory documents during the clinical drug development play an integral role in applying transparency principles.

Implementation of the Use of the Hospital Management Information System (SIMRS) at the PKU Muhammadiyah Clinic, North Lombok

The advancement and development of information technology is currently growing so rapidly in all fields including in the health sector. Especially in hospitals. Hospital information systems have an important role in clinical and administrative services. One of the developments in information systems in hospitals is electronic medical records which have become an integral part of the online-based Hospital Management Information System (SIMRS) application which is computerized in an integrated system stored in a central database.

Salivary Interleukin-13 and Transforming Growth Factor Beta as Potential Biomarkers of Cancer Cachexia.

serum and saliva specimens were obtained from 78 patients. Forty-six patients were non-cachectic, and 32 patients were cachectic (per SCRINIO group criteria), all with metastatic solid tumors. Commercial ELISA kits were used to determine the salivary and serum concentrations of interleukin 13 (IL-13) and transforming growth factor beta (TGF-β) in two patient groups and healthy controls. Laboratory values were obtained from the hospital information system, and weight and height were measured at the time of sampling. A statistically significant difference was observed between the groups in saliva IL-13 concentrations but no difference in serum concentrations. Statistically significant differences were also observed between the groups in saliva and serum concentrations of TGF-β. Logistic regression analysis has identified salivary IL-13 and TGF-β as independent factors for cancer cachexia. We demonstrated saliva as a valuable specimen for cachexia investigation and established IL-13 and TGF-β as potential cancer cachexia biomarkers. Further research is needed to evaluate these findings.

Association Between Clubfoot and Neonatal Abstinence Syndrome in the United States, 2018-2022.

The United States has seen an increase in opioid use and misuse over the last 2 decades. Infants have been impacted by the opioid epidemic, with a reported 5-fold increase in the incidence of neonatal abstinence syndrome (NAS) over the last 2 decades. There are many conditions associated with NAS, and thus, the current study sought to examine the association between NAS and clubfoot. The study was retrospective, utilizing patient data from the Pediatric Hospital Information System (PHIS) database. Neonates presenting to any PHIS hospital between 2018 and 2022 were identified and included in the study. Patients with NAS and clubfoot were identified utilizing the International Classification of Diseases (ICD)-9 and 10 codes. Univariable and multivariable analyses were performed to investigate associations between clubfoot, race, ethnicity, insurance type, gestational age, length of stay, NAS, and comorbidity burden. A total of 458,274 patients were identified, of whom 2337 (0.5%) had a clubfoot diagnosis and 5431 (1.2%) had a diagnosis of NAS. Multivariable logistic regression revealed higher independent odds of clubfoot among patients with a diagnosis of NAS [odds ratio (OR): 1.49], patients with a greater number of comorbidities (OR: 4.75 for 1 comorbidity vs. none, and 21.19 for 2+ comorbidities, vs. none), patients with a greater gestational age (OR: 1.01 per week increase), and those with an increased length of stay (OR: 1.00 per day increase). A lower independent odds of clubfoot was observed among patients of Asian race (OR: 0.66), Hispanic/Latino ethnicity (OR: 0.80), non-Hispanic Black (OR: 0.75), and multiracial (OR: 0.80) ethnicity/race relative to non-Hispanic/Latino White patients (P<0.05 for all). Patients with a diagnosis of NAS demonstrated higher odds of clubfoot, in addition to sociodemographic factors, as well as comorbidity burden.

Combining PCT with CRP is better than separate testing for patients with bacteriuria in the intensive care unit: a retrospective study

BackgroundPrevious studies on PCT for urinary tract infections (UTI) have focused primarily on minors. This study investigated the predictive value of the neutrophil-to-lymphocyte ratio (NLR), C-reactive protein (CRP) level and procalcitonin (PCT) level in adult patients with bacteriuria in IUC.MethodsThis case‒control study included 85 patients with bacteriuria (PB) in the ICU from March 2021 to Jan 2024 based on positive urine culture results and a control group (n = 136) from Jan 2024 to March 2024. Patient data were collected using a hospital information management system. ROC curves of the NLR, CRP and PCT were use to predict the PB.ResultsThe AUCs of the NLR, CRP and PCT for the prediction of PB in ICU were 0.711 (95% CI 0.644–0.772), 0.855 (95% CI 0.800–0.900), and 0.884 (95% CI 0.832–0.924), respectively; the optimal thresholds were 8.02, 18.52 mg/L, and 0.215 ng/mL, respectively; the sensitivities were 69.0 (95% CI 56.9–79.5), 90.1 (95% CI 80.7–95.9), and 83.1 (95% CI 72.3–91.0), respectively; and the specificities were 67.6 (95% CI 59.1–75.4), 68.4 (95% CI 59.9–76.1), and 80.9 (95% CI 73.3–87.1), respectively. The negative predictive value (NPV) of CRP is greater than that of PCT. In bacteriuria caused by Candida infections, CRP and PCT have higher sensitivity and NPV.ConclusionsCombined CRP and PCT testing is more helpful for diagnosing bacteriuria. CRP and PCT have higher sensitivity and NPV in diagnosing bacteriuria caused by Candida infection.

The effectiveness of intratympanic injections with methylPREDnisolon versus placebo in the treatment of vertigo attacks in MENière’s disease (PREDMEN trial): a study protocol for a phase-3 multicentre, double-blinded, randomised, placebo-controlled trial

IntroductionIntratympanic corticosteroids are commonly used in the treatment of Menière’s disease (MD). However, few and small randomised controlled trials (RCT) on the effectiveness of intratympanic corticosteroids have been performed. A...

Comparison of the Effectiveness of Computed Tomography and Magnetic Resonance Imaging Techniques in Patient Groups Aged under and over 65 Years and Diagnosed with Ischemic Stroke in the Emergency Department

Objectives: Stroke is a condition with high morbidity and mortality. This study aims to investigate whether the effectiveness of Computed Tomography (CT) and diffusion-weighted Magnetic Resonance Imaging (MRI), the techniques that have a significant place in the diagnosis of ischemic stroke, the most common form of stroke, are affected by the physiological changes of advanced age. Methods: A total of 436 patients were included in the study. The study population was divided into two groups depending on age: those above 65 and those under 65. Medical files, both the emergency department and clinical ward files, of the patients who were admitted to the emergency department in nine months and admitted to the neurology clinic with the diagnosis of ischemic stroke were retrospectively analyzed. The time from admission to imaging was determined depending on patient files and the Hospital Management Information System (HBYS). The CT and MRI reports interpreted by radiologists were also reviewed. While recording the data, the presence of a lesion, its direction, and localization were also noted. Results: CT positivity was 21.3%, and the positivity of diffusion-weighted imaging was 82.1% in the study population. The time was shorter in the group of patients with positive CT results than in the group with negative CT results. In subjects under 65, the time between onset and imaging was shorter in the group with positive CT results than in the group with negative CT results. In subjects over 65, the time with positive CT results was not different from the group with negative CT results. It was determined that the mean time was shorter in the group with positive MRI results than in the group with negative results. In both the groups under the age of 65 and over the age of 65, the time interval was shorter in the patients with positive MRI results compared to those with negative MRI results. Conclusions: Regardless of the positivity or negativity of CT and MRI results, the mean time from symptom onset to imaging was shorter in the group under 65 years of age compared to the group over 65 years. Aging prolongs the time to admission and the neuroradiological response of geriatric patients.

Retrospective Evaluation of Patients Diagnosed with Brain Death in the Intensive Care Unit: A 10-year Single Center Analysis

Aim: This study aimed to investigate the demographic characteristics, clinical features, timing of the diagnosis of brain death, and factors associated with organ donation in patients diagnosed as brain dead in the intensive care unit in the last decade. Method: Between 01.01.2015-01.06.2024, the age, gender, intensive care unit hospitalization diagnoses, the day of intensive care unit hospitalization, blood groups, the number of patients diagnosed with brain death by years, the number of patients diagnosed with brain death, the number of patients who became donors, laboratory values on the day of intensive care unit hospitalization and the day of brain death diagnosis, the reasons why families did not accept organ donation were recorded from the patients' files and hospital information system. Results: A total of 59 patients were included in the study. Of the patients, 32 (54.24%) were female and 27 (45.76%) were male. The age distribution of the patients was seven (11.86%) aged 0-17 years, 29 (49.15%) aged 18-64 years, and 23 (38.98%) aged 65 years and older. The most common intensive care unit hospitalization diagnoses were intracerebral hemorrhage (35.59%), subarachnoid hemorrhage (16.95%), and CVA (13.56%). Although brain death was diagnosed in 83.05% of the patients in the first seven days, it was diagnosed in an average of 4.81 days in all patients. When the laboratory values between the day of admission to the intensive care unit and the day of brain death were diagnosed, a statistically significant difference was found in Na+, Cl-, K+, AST, BUN, and creatinine values (p0.05). Among the reasons for not accepting organ donation, familial reasons were the highest, with 79.66%. Conclusion: In order to increase the number of organ donations, it is important to raise public awareness and increase the level of knowledge of families about organ donation. Patients with poor neurological prognosis with hospitalization diagnoses such as intracranial hemorrhage, CVA, and Post CPR should be closely monitored for brain death and potential donors.

Trend of incompleteness of the race/color variable in hospitalizations due to COVID-19 whose outcome was death in Brazil, 2020-2022.

To analyze the incompleteness and trend of incompleteness of the race/color variable in hospitalizations due to COVID-19 whose outcome was death, in Brazil, between April 2020 and April 2022. Ecological time series study on the incompleteness of the race/color variable in hospitalizations due to COVID-19 whose outcome was death in Brazil, its macro-regions and Federative Units (FU), by joinpoint regression, calculation of Monthly Percent Change (MPC) and Average Monthly Percent Change (AMPC), based on data from the Hospital Information System of the Unified Health System (SIH/SUS). The incompleteness of the race/color variable in COVID-19 hospitalizations with a death outcome in Brazil was 25.85%, considered poor. All regions of the country had a poor degree of incompleteness, except for the South, which was considered regular. In the period analyzed, the joinpoint analysis revealed a stable trend in the incompleteness of the race/color variable in Brazil (AMPC = 0.54; 95%CI: -0.64 to 1.74; p = 0.37) and in the Southeast (AMPC = -0.61; 95%CI: -3.36 to 2.22; p = 0.67) and North (AMPC = 3.74; 95%CI: -0.14 to 7.78; p = 0.06) regions. The South (AMPC = 5.49; 95%CI: 2.94 to 8.11; p = 0.00002) and Northeast (AMP = 2.50; 95%CI: 0.77 to 4.25; p = 0.005) regions showed an increase in the incompleteness trend, while the Midwest (AMPC = -2.91 ; 95%CI: -5.26 to -0.51; p = 0.02) showed a downward trend. The proportion of poor completeness and the stable trend of incompleteness show that there was no improvement in the quality of filling in the race/color variable during the COVID-19 pandemic in Brazil, a fact that may have increased health inequalities for the black population and made it difficult to plan strategic actions for this population, considering the pandemic context. The results found reinforce the need to encourage discussion on the subject, given that the incompleteness of health information systems increases inequalities in access to health services and compromises the quality of health data.

Validation of a quantitative instrument measuring critical success factors and acceptance of Casemix system implementation in the total hospital information system in Malaysia

ObjectivesThis study aims to address the significant knowledge gap in the literature on the implementation of Casemix system in total hospital information systems (THIS). The research focuses on validating a...

Ensemble neural models for ICD code prediction using unstructured and structured healthcare data

Disease coding is the process of assigning one or more standardized diagnostic codes to clinical notes that are maintained by health practitioners (e.g. clinicians) to track patient condition. Such a coding process is often expensive and error-prone, as human medical coders primarily perform it. Automating diagnostic coding using Artificial Intelligence is seen as an essential solution in Hospital Information Management Systems and approaches built on Convolutional Neural Networks currently perform best. In this work, a neural model built on unstructured clinical text for enabling automatic diagnostic coding for given patient discharge summaries is proposed. We incorporate a structured self-attention mechanism designed to boost learning of label-specific vectors and the significant clinical text snippets associated with a certain label for this purpose. These vectors are then combined with a novel code description pipeline leveraging the descriptions provided for each standardized diagnostic code. The proposed model achieved best performance in terms of standard metrics over the MIMIC-III dataset, outperforming models based on Longformers and Knowledge graphs. Furthermore, to leverage structured clinical data to enhance the proposed model, and to enable improved diagnostic code prediction, model ensembling is considered. A neural model built on structured data by leveraging supervised machine learning algorithms such as random forest and boosting, is designed for multi-class code classification. Experimental results revealed that the proposed ensemble models show promising performance compared to traditional models that rely solely on unstructured or structured clinical data, emphasizing their suitability for real-world deployment.

Socioeconomic status as a risk factor for SARS-CoV-2 infection in pregnant women.

Due to the association between COVID-19 and adverse pregnancy outcomes, pregnant women are considered to be a vulnerable patient group. Studies have shown that low socioeconomic status (SES) is a risk factor for SARS-CoV-2 infection. COVID-19 and low SES are likely to have a synergistic adverse effect. This study aimed to evaluate the socioeconomic background, indicated by self-reported SES, educational level, and financial situation, in pregnant women who were positive for SARS-CoV-2. A case-control study was conducted, including all pregnant women with positive SARS-CoV-2 PCR tests at Kepler University Hospital Linz between May 2020 and August 2021 (n=150) and a control group matched 1:1 relative to gestational age at birth (n=150). Data were collected using written questionnaires and medical records from the hospital information system. Lower self-reported socioeconomic status (p=0.029) and lower education level (p=0.003) were detected in the COVID group. Mothers in the COVID group were significantly younger (p=0.024). However, after adjustment for educational attainment, younger age was not confirmed as a risk factor for SARS-CoV-2 infection during pregnancy (p=0.326). The social gradient was not explained by the assumed mediators and confounders. These findings confirm an association between lower socioeconomic status and the risk of SARS-CoV-2 infection during pregnancy. Since both socioeconomic factors and COVID-19 impose negative effects on pregnancy outcomes, health inequalities should be taken into consideration when implementing SARS-CoV-2 prevention measures and when providing health care for pregnant women from disadvantaged communities.