Background: Prolonged length of stay (LOS) following targeted temperature management (TTM) admini... more Background: Prolonged length of stay (LOS) following targeted temperature management (TTM) administered after cardiac arrest may affect healthcare plans and expenditures. This study identified risk factors for prolonged LOS in patients with cardiac arrest receiving TTM and explored the association between LOS and neurological outcomes after TTM. Methods: The retrospective cohort consisted of 571 non-traumatic cardiac arrest patients aged 18 years or older, treated with cardiopulmonary resuscitation (CPR), had a Glasgow Coma Scale score <8, or were unable to comply with commands after the restoration of spontaneous circulation (ROSC), and received TTM less than 12 hours after ROSC. Prolonged LOS was defined as LOS beyond the 75th quartile of the entire cohort. We analyzed and compared relevant variables and neurological outcomes between the patients with and without prolonged LOS and established prediction models for estimating the risk of prolonged LOS. Results: The patients with in-hospital cardiac arrest had a longer LOS than those with out-of-hospital cardiac arrest (p = 0.0001). Duration of CPR (p = 0.02), underlying heart failure (p = 0.001), chronic obstructive pulmonary disease (p = 0.008), chronic kidney disease (p = 0.026), and post-TTM seizures (p = 0.003) were risk factors for prolonged LOS. LOS was associated with survival to hospital discharge, and patients with the lowest and highest Cerebral Performance Category scores at discharge had a shorter LOS. A logistic regression model based on parameters at discharge achieved an area under the curve of 0.840 to 0.896 for prolonged LOS prediction, indicating the favorable performance of this model in predicting LOS in patients receiving TTM. Conclusions: Our study identified clinically relevant risk factors for prolonged LOS following TTM and developed a prediction model that exhibited adequate predictive performance. The findings of this study broaden our understanding regarding factors associated with hospital stay and can be beneficial while making clinical decisions for patients with cardiac arrest who receive TTM.
The study investigated mental health status of the students of public and private universities, t... more The study investigated mental health status of the students of public and private universities, their willingness to take vaccine against COVID-19, and its association with fear, anxiety, and depression. A cross-sectional electronic survey was conducted from July 26 to September 15, 2021, using a well-structured questionnaire among 504 university students. The average age of the participants was 22.92 ± 2.28 years and 76.98% of them were willing to vaccinate against COVID-19. The fear of COVID-19 was found mild, and depression level was demonstrated moderate among the students irrespective of the university types. Moreover, Masters/MPhil/PhD students and the students living in semi-urban areas had the highest rate of willingness to vaccinate. The study demonstrated that level of fear, anxiety, and depression was directly associated with increased willingness to vaccinate among the tertiary level students in Bangladesh. The outcome of this study sketched a positive association of knowledge and education with better management of pandemic in a society.
Telemedicine is used to assist and support remote medical care for patients. Our objective was to... more Telemedicine is used to assist and support remote medical care for patients. Our objective was to build up a REST Webservices alert engine that receives clinical parameters from patients of vital signs and basic laboratories to monitor patients remotely. We built a REST API using FHIR, so it can interoperate with other applications, send data to be processed, and receive a response. If the API detects a health risk situation, it sends an alert about the medical parameters that are controlled. The results of the processed data, news and alert, can return synchronously or asynchronously, at the same time that the data to be processed is being sent. The alerts generated can be automatically sent to a web service, mail or WhatsApp of the physician. The alert message comes out as normal, low, medium and high risk. The presented approach establishes communication that enables timely health information exchange. We conducted an experiment (with fictitious data) where we sent several queries by Postman. Finally, we evaluated the communication to be successful by manual checking. The use of the API significantly improves the monitoring of chronic patients. Many works show the effectiveness of telemedicine to improve the control of certain chronic diseases. In addition, telemedicine interventions were also found to significantly improve other health outcomes. Our API enables us to transfer data and produce alerts successfully. This gives us hope that a future with ubiquitous healthcare information interoperability is possible using our system.
High Blood Pressure (HBP) is a disorder characterized by elevated levels of pressure in blood ves... more High Blood Pressure (HBP) is a disorder characterized by elevated levels of pressure in blood vessels and constituted one of the risk factors for cardiovascular diseases and mortality. This work proposed the development of the Expert System for the Diagnosis of Secondary HBP, an innovative tool capable of providing accurate and personalized diagnoses by considering multiple factors. The system evaluated blood pressure levels to classify the degree of HBP and analyzed various clinical parameters to identify possible grounds of secondary hypertension.
We use an alert engine based on NEWS (National Early Warning Score) to monitor diabetic patients ... more We use an alert engine based on NEWS (National Early Warning Score) to monitor diabetic patients with the aim of identifying early signs of deterioration or complications of patients remotely. The idea is to leverage a scoring system originally designed for pediatric patients to predict clinical deterioration and adapt it to track and monitor diabetic conditions. The benefits of a NEWS-based alert engine for diabetic patients is that it enables early detection of disturbances as it identifies warning signs of diabetic ketoacidosis (DKA) or hypoglycemic events before they become critical. This enables personalized interventions based on individual risk scores. This engine improves the flow of information between healthcare teams, leading to timely responses. Supports physicians with data-driven insights to make better treatment decisions. Adopting a NEWS-based alert engine for diabetic patients significantly enhances the monitoring process, helping to prevent complications and improve outcomes through proactive interventions.
During the early phase of the COVID-19 pandemic, reverse transcriptase-polymerase chain reaction ... more During the early phase of the COVID-19 pandemic, reverse transcriptase-polymerase chain reaction (RT-PCR) testing faced limitations, prompting the exploration of machine learning (ML) alternatives for diagnosis and prognosis. Providing a comprehensive appraisal of such decision support systems and their use in COVID-19 management can aid the medical community in making informed decisions during the risk assessment of their patients, especially in low-resource settings. Therefore, the objective of this study was to systematically review the studies that predicted the diagnosis of COVID-19 or the severity of the disease using ML. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA), we conducted a literature search of MEDLINE (OVID), Scopus, EMBASE, and IEEE Xplore from January 1 to June 31, 2020. The outcomes were COVID-19 diagnosis or prognostic measures such as death, need for mechanical ventilation, admission, and acute respiratory distress syndrome. We included peer-reviewed observational studies, clinical trials, research letters, case series, and reports. We extracted data about the study's country, setting, sample size, data source, dataset, diagnostic or prognostic outcomes, prediction measures, type of ML model, and measures of diagnostic accuracy. Bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). This study was registered in the International Prospective Register of Systematic Reviews (PROSPERO), with the number CRD42020197109. The final records included for data extraction were 66. Forty-three (64%) studies used secondary data. The majority of studies were from Chinese authors (30%). Most of the literature (79%) relied on chest imaging for prediction, while the remainder used various laboratory indicators, including hematological, biochemical, and immunological markers. Thirteen studies explored predicting COVID-19 severity, while the rest predicted diagnosis. Seventy percent of the articles used deep learning models, while 30% used traditional ML algorithms. Most studies reported high sensitivity, specificity, and accuracy for the ML models (exceeding 90%). The overall concern about the risk of bias was "unclear" in 56% of the studies. This was mainly due to concerns about selection bias. ML may help identify COVID-19 patients in the early phase of the pandemic, particularly in the context of chest imaging. Although these studies reflect that these ML models exhibit high accuracy, the novelty of these models and the biases in dataset selection make using them as a replacement for the clinicians' cognitive decision-making questionable. Continued research is needed to enhance the robustness and reliability of ML systems in COVID-19 diagnosis and prognosis.
The International Classification of Diseases (ICD) code is a diagnostic classification standard t... more The International Classification of Diseases (ICD) code is a diagnostic classification standard that is frequently used as a referencing system in healthcare and insurance. However, it takes time and effort to find and use the right diagnosis code based on a patient's medical records. In response, deep learning (DL) methods have been developed to assist physicians in the ICD coding process. Our findings propose a deep learning model that utilized clinical notes from medical records to predict ICD-10 codes. Our research used text-based medical data from the outpatient department (OPD) of a university hospital from January to December 2016. The dataset used clinical notes from five departments, and a total of 21,953 medical records were collected. Clinical notes consisted of a subjective component, objective component, assessment, plan (SOAP) notes, diagnosis code, and a drug list. The dataset was divided into two groups: 90% for training and 10% for test cases. We applied natural language processing (NLP) technique (word embedding, Word2Vector) to process the data. A deep learning-based convolutional neural network (CNN) model was created based on the information presented above. Three metrics (precision, recall, and F-score) were used to calculate the achievement of the deep learning CNN model. Clinically acceptable results were achieved through the deep learning model for five departments (precision: 0.53-0.96; recall: 0.85-0.99; and F-score: 0.65-0.98). With a precision of 0.95, a recall of 0.99, and an F-score of 0.98, the deep learning model performed the best in the department of cardiology. Our proposed CNN model significantly improved the prediction performance for an automated ICD-10 code prediction system based on prior clinical information. This CNN model could reduce the laborious task of manual coding and could assist physicians in making a better diagnosis.
Bangabandhu Sheikh Mujib Medical University Journal, Jun 25, 2023
Background: The automa c coding of electronic medical records with ICD (Interna onal Classifica o... more Background: The automa c coding of electronic medical records with ICD (Interna onal Classifica on of Diseases) codes is an area of interest due to its poten al in improving efficiency and streamlining processes such as billing and outcome tracking. Ar ficial intelligence (AI), par cularly convolu onal neural networks (CNN) have been suggested as a possible mechanism for automa c coding. To this end, a rapid review has been undertaken in order to assess the current use of CNN in predic ng ICD codes from electronic medical records. Methods: A er screening PubMed, IEEE Xplore, Scopus, and Google Scholar, 11 studies were analyzed for the use of CNN in predic ng ICD codes. We used ar ficial intelligence and ICD predic on as keywords in the search strategy. Results: The analysis yielded a recommenda on to further explore and research CNN frameworks as a promising lead to automa c ICD coding when paired with word embedding and/or neural transfer learning, while keeping research open to a wide variety of AI techniques. Conclusion: CNN frameworks are promising for the predic on of ICD codes from clinical notes.
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Background: The Posttraumatic Stress Disorder Checklist (PCL-5) is the most widely used screening... more Background: The Posttraumatic Stress Disorder Checklist (PCL-5) is the most widely used screening tool in assessing posttraumatic stress disorder symptoms, based on the Diagnostic and Statistical Manual of Mental disorders (DSM-5) criteria. This study aimed to evaluate the psychometric properties of the newly translated Bangla PCL-5. Methods: A cross-sectional survey was carried out among 10,605 individuals (61.0% male; mean age: 23.6 ± 5.5 [13-71 years]) during May and June 2020, several months after the onset of the COVID-19 outbreak in Bangladesh. The survey included the Bangla PCL-5 and the PHQ-9 depression scale. We used confirmatory factor analysis to test the four-factor DSM-5 model, the six-factor Anhedonia model, and the seven-factor hybrid model. Results: The Bangla PCL-5 displayed adequate internal consistency (Cronbach's alpha = 0.90). The Bangla PCL-5 score was significantly correlated with scores of the PHQ-9 depression scale, confirming strong convergent validity. Confirmatory factor analyses indicated the models had a good fit to the data, including the four-factor DSM-5 model, the six-factor Anhedonia model, and the seven-factor hybrid model. Overall, the seven-factor hybrid model exhibited the best fit to the data. Conclusions: The Bangla PCL-5 appears to be a valid and reliable psychometric screening tool that may be employed in the prospective evaluation of posttraumatic stress disorder in Bangladesh.
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Background: Prolonged length of stay (LOS) following targeted temperature management (TTM) admini... more Background: Prolonged length of stay (LOS) following targeted temperature management (TTM) administered after cardiac arrest may affect healthcare plans and expenditures. This study identified risk factors for prolonged LOS in patients with cardiac arrest receiving TTM and explored the association between LOS and neurological outcomes after TTM. Methods: The retrospective cohort consisted of 571 non-traumatic cardiac arrest patients aged 18 years or older, treated with cardiopulmonary resuscitation (CPR), had a Glasgow Coma Scale score <8, or were unable to comply with commands after the restoration of spontaneous circulation (ROSC), and received TTM less than 12 hours after ROSC. Prolonged LOS was defined as LOS beyond the 75th quartile of the entire cohort. We analyzed and compared relevant variables and neurological outcomes between the patients with and without prolonged LOS and established prediction models for estimating the risk of prolonged LOS. Results: The patients with in-hospital cardiac arrest had a longer LOS than those with out-of-hospital cardiac arrest (p = 0.0001). Duration of CPR (p = 0.02), underlying heart failure (p = 0.001), chronic obstructive pulmonary disease (p = 0.008), chronic kidney disease (p = 0.026), and post-TTM seizures (p = 0.003) were risk factors for prolonged LOS. LOS was associated with survival to hospital discharge, and patients with the lowest and highest Cerebral Performance Category scores at discharge had a shorter LOS. A logistic regression model based on parameters at discharge achieved an area under the curve of 0.840 to 0.896 for prolonged LOS prediction, indicating the favorable performance of this model in predicting LOS in patients receiving TTM. Conclusions: Our study identified clinically relevant risk factors for prolonged LOS following TTM and developed a prediction model that exhibited adequate predictive performance. The findings of this study broaden our understanding regarding factors associated with hospital stay and can be beneficial while making clinical decisions for patients with cardiac arrest who receive TTM.
Supplementary material: Problematic internet use among young and adult population in Bangladesh: Correlates with lifestyle and online activities during the COVID-19 pandemic
Additional file 1 of Depressive symptoms associated with COVID-19 preventive practice measures, daily activities in home quarantine and suicidal behaviors: Findings from a large-scale online survey in Bangladesh
Additional file 1. Details information of volunteers who contributed during the data collection p... more Additional file 1. Details information of volunteers who contributed during the data collection periods.
Background: Smoking is recognized as a major public health problem in the world.Materials & Metho... more Background: Smoking is recognized as a major public health problem in the world.Materials & Methods: The objective of the study was to assess the prevalence and determinant of adolescent smoking in West Kafrul Dhaka. This was a cross sectional study conducted in 2013 among 150 adolescent boys of school and slum.Results: The results showed 35.33% adolescent boys had smoking habit. Most of the adolescent (86.79%) had started smoking when they were 14-17 years old. This study found that peers influence (50.94 %) was the most common causes of smoking. Among the boys who live in slum, 80% were smoker and among the school going boys 15% were smoker.Conclusion: Smoking was very common among middle-class male teenagers and even more prevalent among youths from nearby slums. Awareness program on tobacco will be an effective way to control.Anwer Khan Modern Medical College Journal Vol. 9, No. 1: Jan 2018, P 34-38
The Posttraumatic Stress Disorder Checklist (PCL) is a widely used DSM-correspondent self-report ... more The Posttraumatic Stress Disorder Checklist (PCL) is a widely used DSM-correspondent self-report measure of PTSD symptoms. The PCL was recently revised to reflect DSM-5 changes to the PTSD criteria. In this article, the authors describe the development and initial psychometric evaluation of the PCL for DSM-5 (PCL-5). Psychometric properties of the PCL-5 were examined in 2 studies involving trauma-exposed college students. In Study 1 (N = 278), PCL-5 scores exhibited strong internal consistency (α = .94), test-retest reliability (r = .82), and convergent (rs = .74 to .85) and discriminant (rs = .31 to .60) validity. In addition, confirmatory factor analyses indicated adequate fit with the DSM-5 4-factor model, χ(2) (164) = 455.83, p < .001, standardized root mean square residual (SRMR) = .07, root mean squared error of approximation (RMSEA) = .08, comparative fit index (CFI) = .86, and Tucker-Lewis index (TLI) = .84, and superior fit with recently proposed 6-factor, χ(2) (164) = 3...
Uploads
Papers by jakir masud