Disease Classification Research Articles

Unraveling under-five mortality causes in Iran: a comprehensive systematic review and meta-analysis

BackgroundThis study systematically reviewed the causes of child death across different age groups based on the International Classification of Diseases, 10th Revision (ICD-10) criteria.MethodsA comprehensive search was conducted in seven electronic databases and two search engines to identify all studies examining child mortality in any part of Iran or the entire country. Hand searching, gray literature, and bibliographies were also utilized. Data were synthesized descriptively and through meta-analysis.ResultsA total of 35 studies were included, encompassing 58,519 death cases across various age groups. According to the ICD-10 classification, the most common causes of Neonatal Mortality Rates (NMR) were pregnancy, childbirth, and puerperium-related conditions (41.1%), congenital malformations (19.2%), and certain conditions originating in the perinatal period (14.5%). For Infant Mortality Rates (IMR), the leading causes were congenital malformations (44.0%), pregnancy, childbirth, and related conditions (14.5%), and respiratory and cardiovascular diseases (8.7%). In the age group of 28 days to 5 years, the primary causes of death were pregnancy, childbirth, and puerperium-related issues (27.5%), congenital malformations and chromosomal abnormalities (21.6%), and respiratory and cardiovascular disease (9.3%). For children aged 1 to 5 years, congenital malformations (29.1%), external causes (19.6%), and respiratory and cardiovascular disorders (7.2%) were the most significant causes of death. The meta-analysis revealed that immaturity [0.171 (PI: 0.032–0.561)] in infants aged 0–28 days, and congenital malformations in the age groups of 28 to 1 year [0.261 (PI: 0.166–0.385)] and 28 to 5 years [0.173 (PI: 0.078–0.342)] were the leading causes of death.ConclusionsThe findings of this study provide valuable insights for priority-setting interventions aimed at reducing child mortality according to the prevalence rate of specific causes in different age groups.

Trends in Cannabis-related Hospitalizations in Arizona from 2016-2021 and Associations with Mental Health-related Hospitalizations.

To examine trends in cannabis-related hospital visits in Arizona from 2016-2021 and associations with hospital visits for a mental health condition. Data were emergency department and inpatient hospital discharge records from all Arizona licensed hospitals from 2016-2021. Records comprised 18,758,614 hospital visits. Cannabis-related visits were defined by International Classification of Diseases (ICD) diagnostic code for cannabis use (unspecified use, abuse, dependence) or poisoning. Mental health visits were defined by ICD diagnostic codes for mental health conditions. The rate of cannabis-related hospital visits increased from 1,301.50 per 100k visits in 2016 to 1,565.54 per 100k visits in 2021 - a 20% increase. The increase was larger for visits by adolescents and older adults ages 65+ -- 63.94% and 84.45%, respectively. Cannabis-related visits were 7.75 (95% CI: 7.69, 7.81) times as likely as visits unrelated to cannabis to have a mental health condition as the primary diagnosis from 2016-2021, and were 2.32 (95% CI: 2.30, 2.34) times as likely after adjustment for covariates, including alcohol and other substance-related diagnoses. The association between cannabis-related visits and mental health-related visits increased each year, particularly for older adults ages 65+. The rate of cannabis-related hospital visits is increasing, as is the cannabis-related risk of a hospital visit for a mental health condition. The increases are especially pronounced among hospital visits by older adults (ages 65+), highlighting the need for prevention and intervention in this under-recognized at-risk group.

Shopaholism – aetiology, characteristics, models and concepts of cognitive-behavioural therapy

The article addresses the issue of shopaholism as a disorder, examining its existing definitions and functioning diagnostic criteria within the context of its exclusion from official disease classifications, despite its increasing prevalence and negative impact on the lives of individuals. The study highlights that, although not formally recognised as a disease entity, shopaholism is discussed in scientific literature under various terms, such as compulsive buying, impulsive buying, or shopping addiction, and can be considered a form of behavioural addiction. The article emphasises the complex aetiology of shopaholism, suggesting that it results from a combination of biological, cognitive, emotional, and social factors. The authors also demonstrate from a cognitive-behavioural perspective how core beliefs, values, and self-esteem may contribute to the development and persistence of the disorder. In addition, the article discusses therapeutic approaches including pharmacotherapy and, above all, cognitive-behavioural psychotherapy, which is emerging as a key approach in the treatment of shopaholism, with efficacy proven by numerous studies. This therapy aims at cognitive restructuring to modify negative thoughts, improve impulse control, and foster healthier coping strategies to deal with negative emotions. The article explores the complexity of shopping addiction, drawing on both historical and contemporary cognitive models to conceptualise individual cases and develop effective therapeutic plans. It also highlights proven techniques and methods. By adopting a cognitive-behavioural perspective, mental health professionals can provide patients with a targeted and personalised treatment. From the perspective of treatment, the key challenge is not abstinence but working with beliefs and values, as well as cognitive and behavioural techniques.

Conventional Machine Learning and Ensemble Learning Techniques in Cardiovascular Disease Prediction and Analysis

Cardiovascular diseases, which significantly affect the heart and blood vessels, are one of the leading causes of death worldwide. Early diagnosis and treatment of these diseases, which cause approximately 19.1 million deaths, are essential. Many problems, such as coronary artery disease, blood vessel disease, irregular heartbeat, heart muscle disease, heart valve problems, and congenital heart defects, are included in this disease definition. Today, researchers in the field of cardiovascular disease are using approaches based on diagnosis-oriented machine learning. In this study, feature extraction is performed for the detection of cardiovascular disease, and classification processes are performed with a Support Vector Machine, Naive Bayes, Decision Tree, K-Nearest Neighbor, Bagging Classifier, Random Forest, Gradient Boosting, Logistic Regression, AdaBoost, Linear Discriminant Analysis and Artificial Neural Networks methods. A total of 918 observations from Cleveland, Hungarian Institute of Cardiology, University Hospitals of Switzerland, and Zurich, VA Medical Center were included in the study. Principal Component Analysis, a dimensionality reduction method, was used to reduce the number of features in the dataset. In the experimental findings, feature increase with artificial variables was also performed and used in the classifiers in addition to feature reduction. Support Vector Machines, Decision Trees, Grid Search Cross Validation, and existing various Bagging and Boosting techniques have been used to improve algorithm performance in disease classification. Gaussian Naïve Bayes was the highest-performing algorithm among the compared methods, with 91.0% accuracy on a weighted average basis as a result of a 3.0% improvement.

Analysis of existing techniques for image-based recognition of agricultural crops diseases

An analysis of existing methods for processing and identifying the disease of agricultural crops was carried out. Other methods for identifying informative regions, including Fourier transformation, k-means clustering, Histogram Equalization, Scale-Invariant Feature Transform (SIFT), Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG) algorithms, as well as their combinations were reviewed. The studied approaches demonstrated high accuracy in the identification and classification of various plant diseases. The study examined hybrid models, such as, for example, logistic regression with decision trees and Extreme Learning Machines (ELM). The accuracy of the Support Vector Machine (SVM), ELM, and Decision Trees algorithms were compared, convinced, that the importance of choosing the right parameters and fine-tuning to improve accuracy is important. The methods of deep learning such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) and their usage in the scope of the image recognition, which are also used for disease recognition, were examined. The recognition accuracy of several CNN models was compared: DenseNet121, MobileNetV2, NASNetMobile and EfficientNetB0, and the last demonstrated the best results. The modification of ready-made architectures, including the architecture of the EfficientNetB0 neural network, has been analyzed as a way of adapting existing models to specific recognition requirements.

Pigeon Pea Leaves Disease Detection and Classification Using YOLO v9 with Transfer Learning

Pigeon Pea Leaves Disease Detection and Classification Using YOLO v9 with Transfer Learning

Assessment of Children and Adolescents’ Admissions to Pediatric Psychiatric Emergency Department

Objective Emergencies in child and adolescent psychiatry are prevalent, and pediatric psychiatric emergency departments play a crucial role in acute intervention during mental health-related crises. This retrospective cross-sectional study aimed to analyze the characteristics of children and adolescents who were admitted to a pediatric psychiatric emergency department. Method The data were collected from the records of 8803 patients (females 56.6%, Mage = 15.07 ± 2.6) admitted to our pediatric psychiatry emergency department between 2014 and 2021. Diagnoses were made using the International Statistical Classification of Diseases, 10th Revision. We used descriptive statistics to determine patient characteristics and conducted a regression analysis to compare the changes in the admissions numbers by the year. Results It was found that depressive disorder was the highest psychiatric diagnosis, with a percentage of 21.4%. Depressive disorder, autism spectrum disorder, and obsessive-compulsive disorder have shown an increase over the years. In 2020, with the onset of the COVID-19 pandemic, psychiatric admissions reached their lowest level. The percentage of hospitalizations was 21.1% for the total of all years. No significant change was found in the total number of admissions, sex, and age. Conclusions The number of admissions for female adolescents who were diagnosed with depressive disorder to our pediatric psychiatry emergency department is shown to be high. The fact that these patients seek help more frequently should be taken into consideration during the planning of mental health services for outpatient and inpatient clinics as well as pediatric psychiatry emergency services.

Risk of short-term cardiovascular disease in relation to the mode of delivery in singleton pregnancies: a retrospective cohort study

Cardiovascular disease (CVD) is increasing in prevalence and affects up to 4% of pregnancies in otherwise healthy persons. The specific factors that drive the development of CVD in pregnant people are poorly characterised. This study aimed to determine whether the mode of delivery in singletons affects the risk of cardiovascular morbidity and mortality within one year in patients without prior CVD. We designed a retrospective cohort study utilising the Nationwide Readmissions Database (NRD) to identify singleton delivery hospitalisations in the United States from Jan 1, 2010 to Nov 30, 2018. International Classification of Disease (ICD) versions 9 and 10 codes were used to identify patients with readmission for CVD within the calendar year of index delivery. Patients aged 15-54 who underwent a singleton vaginal or caesarean delivery were included. Patients with pre-existing CVD hospitalisations before or during delivery, ectopic pregnancies, or abortive outcomes were excluded. Participant data was retrieved from the NRD database. The primary outcome was hospital readmission, defined by ICD 9 and 10 codes for fatal or non-fatal CVD in the same calendar year as delivery. Cox proportional hazard regression models were used to adjust for confounders. These included maternal age, hospital bed size, hospital type, hospital teaching status, income quartile, insurance, and year of delivery. Additional sub-analyses were performed adjusting for hypertensive disorders of pregnancy and diabetes mellitus. Of the 14,179,299 singleton deliveries, 32% (n=4,553,492) underwent a caesarean. CVD readmissions occurred in 255.2 per 100,000 (n=11,710) caesarean deliveries compared with 133.9 per 100,000 (n=12,507) vaginal deliveries (rate difference [RD], 121.4, 95% confidence interval [CI], 114.8-127.9; hazard ratio [HR] adjusted for all confounders including hypertensive disorders of pregnancy and diabetes mellitus was 1.42, 95% CI 1.35-1.50). This association was highest in the first 0-29 days following delivery (HR 1.68, 95% CI 1.59-1.78). The risk of readmission for CVD persisted for one year. These findings suggest that caesarean delivery of singletons is associated with a higher risk of cardiovascular morbidity in patients without pre-existing CVD. This risk was highest in the first month but remained elevated for one year after delivery. These findings add to the accumulating evidence that undergoing caesarean delivery may have long-standing health implications and support the extension of the post-partum surveillance period. Limitations of this study include the lack of adjustment for body mass index, race, and parity. We were also unable to determine the reason for the caesarean delivery. None.

Suicide Mortality in the United States, 2002-2022.

This report provides final 2022 suicide numbers and age-adjusted rates, updating a provisional 2022 suicide report. Data were analyzed using National Vital Statistics System multiple cause-of-death mortality files for 2002 through 2022, with suicide deaths identified using International Classification of Diseases, 10th Revision underlying cause-of-death codes U03, X60-X84, and Y87.0. Age-adjusted death rates were calculated using the direct method and the 2000 U.S. standard population. Pairwise comparisons were conducted using the z test with an alpha level of 0.05, and trends were assessed using the Joinpoint Regression Program (5.0.2). After increasing from 2002 to 2018, the age-adjusted suicide rate declined from 2018 (14.2 deaths per 100,000 standard population) through 2020 (13.5) but then increased 5%, to 14.2 in 2022. Following a period of decline between 2018 and 2020, suicide rates generally increased between 2020 and 2022 for females ages 25 and older. For males ages 10-14 and 15-24, rates decreased between 2020 and 2022, while rates for older age groups generally increased. For females in 2022, firearm-related suicide (2.0) was the leading means of suicide, with rates generally increasing since 2007. For males in 2022, firearm-related suicide (13.5) was the leading means of suicide, with rates increasing since 2006.

Thoracic Trauma: Diagnosis And Treatment

The study of chest injuries which profoundly impact quality of life, life expectancy, disability rates, and mortality is of significant importance. In clinical research, the authors analyzed diagnostic results from 527 patients aged 18 to 85 with closed chest trauma, consisting of 82% men and 18% women. The study confirms that traumatic chest injuries are severe conditions that necessitate strict adherence to well-defined diagnostic and treatment guidelines. It is advisable to utilize thoracoscopy and video-assisted thoracoscopy for managing hemothoraxes with small volumes of bleeding, as these minimally invasive techniques can enhance patient outcomes and reduce recovery times. The incorporation of advanced three-dimensional (3D) printing technologies into medical practice for chest injuries is also recommended, as it can improve surgical planning and enable personalized treatment strategies. Moreover, 3D printing can aid in the fabrication of patient-specific implants and prosthetics, thereby enhancing the effectiveness of reconstructive surgeries. Further research is needed on pharmacotherapy when using medications in accordance with the codes of the 11th revision of the International Classification of Diseases, to optimize therapeutic efficacy. Additionally, an in-depth study of the integrated ABC/VEN-analysis of drug prescriptions in pharmacotherapeutic regimens for thoracic trauma treatment dynamics in both inpatient and outpatient healthcare facilities is recommended. This could lead to better resource allocation, improved patient care, and the development of more effective treatment protocols. Emphasizing interdisciplinary collaboration among surgeons, radiologists, and pharmacologists is crucial to advance the management of chest trauma, ensuring that patients receive comprehensive and holistic care throughout their recovery process.

Deep residual 2D convolutional neural network for cardiovascular disease classification

Cardiovascular disease (CVD) continues to be a major global health concern, underscoring the need for advancements in medical care. The use of electrocardiograms (ECGs) is crucial for diagnosing cardiac conditions. However, the reliance on professional expertise for manual ECG interpretation poses challenges for expanding accessible healthcare, particularly in community hospitals. To address this, there is a growing interest in leveraging automated and AI-driven ECG analysis systems, which can enhance diagnostic accuracy and efficiency, making quality cardiac care more accessible to a broader population. In this study, we implemented a novel deep two-dimensional convolutional neural network (2D-CNN) on a dataset of PTB-XL for cardiac disorder detection. The studies were performed on 2, 5, and 23 classes of cardiovascular diseases. The our network in classifying healthy/sick patients achived an AUC of 95% and an average accuracy of 87.85%. In 5-classes classification, our model achieved an AUC of 93.46% with an average accuracy of 89.87%. In a more complex scenario involving classification into 23 different classes, the model achieved an AUC of 92.18% and an accuracy of 96.88%. According to the experimental results, our model obtained the best classification result compared to the other methods based on the same public dataset. This indicates that our method can aid healthcare professionals in the clinical analysis of ECGs, offering valuable assistance in diagnosing CVD and contributing to the advancement of computer-aided diagnosis technology.

Clinical characteristics and risk factors associated with diverse manifestations of COVID-19 in patients aged 85 years and older.

The goal of this study is to assess the clinical attributes exhibited by patients aged 85 years and older who present different manifestations of COVID-19, and to examine the factors influencing the classification of the disease severity. This retrospective study was conducted at a single center, encompassing an analysis of clinical data obtained from patients with COVID-19 admitted to a general geriatric hospital in Hangzhou, Zhejiang, China, during the period from December 20, 2022, to February 1, 2023. The study focused on 91 eligible patients whose disease severity was compared based on the imaging findings. A total of 91 patients aged 85 years and older, with a median age of 92, including 46 males, 10 exhibiting mild symptoms, 48 moderate cases, and 33 severe cases met the inclusion criteria. Notably, disease severity displayed a significant correlation with age (p < 0.011). All patients presented with complicated chronic underlying conditions and a history of prolonged medication use. Rheumatic immune diseases (p = 0.040) and endocrine medications, primarily hypoglycemic agents (p = 0.034), exhibited statistical significance. Additionally, markers such as lactate dehydrogenase (LDH) (p = 0.030), interleukin 6 (IL-6) (p = 0.014), and D-dimer (p = 0.007) revealed significant associations with disease severity. Chest computed tomography scans predominantly revealed inflammatory features (n = 81, 89.0%). Notably, patients classified as having mild or moderate conditions exhibited eventual improvement, while 13 patients (39.4%) among the severe cases succumbed to the disease. The classification of disease among patients aged 85 years or older old is correlated with advanced age, concurrent rheumatic immune diseases, and prolonged administration of endocrine medications. Furthermore, patients with elevated levels of LDH, IL-6, and D-dimer demonstrated a higher propensity for developing severe diseases.

A Graph-Informed Modeling Framework Empowering Gene Pathway Discovery.

This study introduces a novel graph-informed modeling framework for improving the statistical analysis of gene expression data, particularly in the context of identifying differentially expressed gene pathways and gene expression-assisted disease classification in a high-dimensional data setting. By integrating gene regulatory network information into hypothesis testing for the difference between mean vectors and linear discriminant analysis, we aim to effectively capture and utilize previously validated external gene interaction information. Our method leverages a block-coordinate descent approach which enables us to incorporate mixed graph information into linear structural equation modeling, accommodating directed/undirected edges and potential cycles in gene regulatory networks. Extensive simulations under various data scenarios have demonstrated the effectiveness of our approach with improved power for gene pathway tests and disease classification over existing methods. An application to a lung cancer dataset from the Cancer Genome Atlas Program (TCGA) further exemplifies the potential of our graph-informed approach in empowering the detection of differentially expressed gene pathways and gene expression-based classification of different lung cancer stages. Our findings underscore the potential utility of incorporating gene regulatory network information in gene pathway analysis, setting the stage for future advancements in gene pathway discovery, disease diagnosis, and treatment strategies.

Privacy-Preserving Transfer Learning Framework for Kidney Disease Detection

This paper introduces a new privacy-preserving transfer learning framework for the classification of kidney diseases. In the proposed framework, transfer learning is employed for feature extraction, and differential privacy is used to obtain noisy gradients. A variety of CNN architectures, including Xception, ResNet50, InceptionResNetV2, MobileNet, DenseNet201, InceptionV3, and VGG19 are utilized to evaluate the proposed framework. Analysis of a large dataset of 12,400 labeled kidney CT images shows that transfer learning architectures based on the proposed framework achieve excellent accuracy ratios in privacy-preserving classification. These results demonstrate the effectiveness of the proposed framework in enabling transfer learning models to classify kidney diseases while ensuring privacy. The MobileNet architecture stands out for its exceptional performance, with an impressive accuracy of 99.83% in privacy-preserving classification. Considering the findings of this study, it is evident that the proposed framework is appropriate for the early and private diagnosis of kidney diseases and promotes the achievement of promising results in this field.

Classification of Pulmonary Diseases Using a Deep Learning Stacking Ensemble Model

Classification of Pulmonary Diseases Using a Deep Learning Stacking Ensemble Model

RELATIONSHIP BETWEEN POSITIVE AND NEGATIVE SYMPTOMS WITH DIMENSIONS OF QUALITY OF LIFE IN PATIENTS WITH SCHIZOPHRENIA

Introduction: Schizophrenia is an endogenous psychotic disorder, which is characterized by the presence of positive and negative symptoms that affect the normal functioning of patients and play important role in their quality of life. Purpose: The main purpose of this research was to introduce the relationship between positive and negative symptoms and quality of life in patients with schizophrenia. Methods: The research involved 40 randomly selected male and female respondents from 18 to 60 years of age who suffer from schizophrenia according to the diagnostic criteria of the International Classification of Diseases – ICD 10. The instruments used are: the Positive and Negative Syndrome Scale (PANSS), and the Scale for the quality of life (WHOQOL Questionnaire - BREF). The statistical analysis of the data was done with the SPSS software package (version 20). Results: The study showed that there is a statistically significant negative relationship between positive symptoms of schizophrenia and mental health (r= -.682, p&lt;.01), positive symptoms and social relationships (r=-.764, p&lt;.01), positive symptoms and living conditions (r=-.732, p&lt;.05). Regarding negative symptoms of schizophrenia and dimensions of quality of life, it was found that there is a statistically positive significant relationship between negative symptoms of schizophrenia and physical health (r=.833, p&lt;.01); negative symptoms of schizophrenia and mental health (r=-.752, p&lt;.05); negative symptoms of schizophrenia and social relationships (r=.831, p&lt;.01); and negative symptoms of schizophrenia and living conditions (r=.850, p&lt;.01). Conclusion: Quality of life is a broad concept that includes a person's subjective opinion regarding their physical and psychological health, social relationships and the environment. This study emphasizes that positive symptoms of schizophrenia negatively affects the dimensions of quality of life in all the above-mentioned areas.

Rise in Autism Spectrum Disorder Diagnoses: A Comparative Analysis of Pre-pandemic and Pandemic Periods.

Introduction This study analyzes the rise in autism spectrum disorder (ASD) diagnoses by comparing pre-pandemic (2017-2019) and pandemic period (2021-2023) data from two private pediatric practices with different populations in New York. The year 2020 was out of the analysis to focus on the impact after the shutdowns on ASD, and there were disruptions in clinic operations during that year. Clinic I primarily served an African-American ethnic population, while Clinic II primarily served an Asian population. Methods A retrospective analysis was conducted using de-identified patient numbers from the electronic medical records (EMR) of two private clinics. Only the numbers of new patients diagnosed each year were included from January 1, 2017, to December 31, 2019 (pre-pandemic), and January 1, 2021, to December 31, 2023 (pandemic). Sixteen ASD International Statistical Classification of Diseases and Related Health Problems 10th Revision (ICD-10) codes were included in this analysis. Descriptive and inferential statistics were used to find important patterns and determine statistical significance. Results The study included 537 patients, 182 from Clinic I and 355 from Clinic II. Clinic I demonstrated a significant increase in ASD diagnoses, from 63 (pre-pandemic) to 119 (pandemic) (χ2=17.23; p=0.000033). Clinic II demonstrated a significant increase in ASD diagnoses, from 149 (pre-pandemic) to 206 (pandemic) (χ2=9.15; p=0.00248). Conclusion The significant increase in ASD diagnoses in two private pediatric practices with different populations indicates a notable association with the shutdown periods and the pandemic. Factors such as disrupted routines, changes in access to healthcare services, and increased parental awareness may have contributed to this rise. Further longitudinal studies are needed to understand the long-term impacts of the pandemic on ASD diagnoses and care.

Six Myths and Misconceptions about Essential Tremor.

There are myths and misperceptions about most human diseases, and neurological diseases are no exception. In many instances, myths and misconceptions reflect what is no more than the collective failure of the field to catch up with the state of the science in that field. Hence, one may perhaps refer to these as "lags" rather than myths. As the field of medicine attempts to be evidence-based, it is best to remain true to published data and the state of the science. In this paper, I review six myths and misconceptions about ET. Myth 1 relates to the natural history and prognosis of ET. Myths 2 and 3 relate to the biological basis of ET, whereas myths 4 and 5 relate to the expression of the core clinical feature of ET. Finally, myth 6 focuses on the issue of disease classification. The myths are as follows: Myth 1: "ET is not associated with a shorter life expectancy". Myth 2: "The pathophysiology of ET remains unclear". Myth 3: "There have also been studies that do not show any cerebellar degeneration". Myth 4: "ET is a postural or a kinetic tremor". Myth 5: "Action tremor in ET is usually bilateral and symmetric". Myth 6: "ET plus". As neurologists, we are not ignorant of feedback loops. A regular review of facts should help to frame one's output. As such, one's formulations and output will be firmly grounded in data.

Extracting Critical Information from Unstructured Clinicians' Notes Data to Identify Dementia Severity Using a Rule-Based Approach: Feasibility Study.

The severity of Alzheimer disease and related dementias (ADRD) is rarely documented in structured data fields in electronic health records (EHRs). Although this information is important for clinical monitoring and decision-making, it is often undocumented or "hidden" in unstructured text fields and not readily available for clinicians to act upon. We aimed to assess the feasibility and potential bias in using keywords and rule-based matching for obtaining information about the severity of ADRD from EHR data. We used EHR data from a large academic health care system that included patients with a primary discharge diagnosis of ADRD based on ICD-9 (International Classification of Diseases, Ninth Revision) and ICD-10 (International Statistical Classification of Diseases, Tenth Revision) codes between 2014 and 2019. We first assessed the presence of ADRD severity information and then the severity of ADRD in the EHR. Clinicians' notes were used to determine the severity of ADRD based on two criteria: (1) scores from the Mini Mental State Examination and Montreal Cognitive Assessment and (2) explicit terms for ADRD severity (eg, "mild dementia" and "advanced Alzheimer disease"). We compiled a list of common ADRD symptoms, cognitive test names, and disease severity terms, refining it iteratively based on previous literature and clinical expertise. Subsequently, we used rule-based matching in Python using standard open-source data analysis libraries to identify the context in which specific words or phrases were mentioned. We estimated the prevalence of documented ADRD severity and assessed the performance of our rule-based algorithm. We included 9115 eligible patients with over 65,000 notes from the providers. Overall, 22.93% (2090/9115) of patients were documented with mild ADRD, 20.87% (1902/9115) were documented with moderate or severe ADRD, and 56.20% (5123/9115) did not have any documentation of the severity of their ADRD. For the task of determining the presence of any ADRD severity information, our algorithm achieved an accuracy of >95%, specificity of >95%, sensitivity of >90%, and an F1-score of >83%. For the specific task of identifying the actual severity of ADRD, the algorithm performed well with an accuracy of >91%, specificity of >80%, sensitivity of >88%, and F1-score of >92%. Comparing patients with mild ADRD to those with more advanced ADRD, the latter group tended to contain older, more likely female, and Black patients, and having received their diagnoses in primary care or in-hospital settings. Relative to patients with undocumented ADRD severity, those with documented ADRD severity had a similar distribution in terms of sex, race, and rural or urban residence. Our study demonstrates the feasibility of using a rule-based matching algorithm to identify ADRD severity from unstructured EHR report data. However, it is essential to acknowledge potential biases arising from differences in documentation practices across various health care systems.

Epidemiological investigation of different types of Crohn's disease patients undergoing first abdominal surgery in the era of biological agents: a population-based cohort study.

Before the era of biological agents, most Crohn's disease patients required at least one intestinal resection surgery after diagnosis. However, clinical data regarding the abdominal surgery rates for Crohn's disease patients in the era of biological agents is not yet fully clear and needs to be updated. We retrospectively collected clinical data from 1115 Crohn's disease patients diagnosed and treated medically at The Second Xiangya Hospital of Central South University from January 2016 to January 2024. Using abdominal intestinal resection surgery as a clinical outcome, propensity score matching was employed to eliminate confounding factors. We explored the timing and proportion of abdominal surgery in patients with different Montreal classifications of Crohn's disease during the natural course of the disease, as well as the impact of the duration of the natural course and the use of biological agents on surgical outcomes. Montreal classification type B had the greatest impact on Crohn's disease surgery, especially with a higher proportion of type B3 patients undergoing surgery. Type A1 Crohn's disease patients underwent surgery earlier than types A2 and A3. The occurrence of behavior changes (B Change) during the natural course of the disease is a poor prognostic signal, indicating a significantly increased likelihood of surgery. The duration of the natural course from the onset of gastrointestinal symptoms to diagnosis and clinical observation outcomes did not directly affect the likelihood of surgery in Crohn's disease patients. Compared with Crohn's disease patients who did not receive biological agents, the surgery rate was significantly lower in patients who used biological agents. Additionally, Crohn's disease patients who received biological agents within 1 month of diagnosis had a significantly lower likelihood of undergoing surgical intervention. Moreover, Crohn's disease patients who received biological agent treatment within 19 months of the onset of gastrointestinal symptoms also had a significantly lower likelihood of undergoing surgery than other Crohn's disease patients. In the era of biological agents, the risk of surgical intervention varies among Crohn's disease patients with different Montreal classifications, particularly when there is type B3 disease or a B Change. Clinicians should pay closer attention to surgical indications in such cases. For Crohn's disease patients, shortening the natural course before diagnosis and early use of biological agents after diagnosis can significantly reduce the risk of abdominal surgery.