Estimating the Optimal Dexketoprofen Pharmaceutical Formulation with Machine Learning Methods and Statistical Approaches

Objectives: Orally disintegrating tablets (ODTs) can be utilized without any drinking water; this feature makes ODTs easy to use and suitable for specific groups of patients. Oral administration of drugs is the most commonly used route, and tablets constitute the most preferable pharmaceutical dosage form. However, the preparation of ODTs is costly and requires long trials, which creates obstacles for dosage trials. The aim of this study was to identify the most appropriate formulation using machine learning (ML) models of ODT dexketoprofen formulations, with the goal of providing a cost-effective and timereducing solution.Methods: This research utilized nonlinear regression models, including the k-nearest neighborhood (k-NN), support vector regression (SVR), classification and regression tree (CART), bootstrap aggregating (bagging), random forest (RF), gradient boosting machine (GBM), and extreme gradient boosting (XGBoost) methods, as well as the t-test, to predict the quantity of various components in the dexketoprofen formulation within fixed criteria.Results: All the models were developed with Python libraries. The performance of the ML models was evaluated with R2 values and the root mean square error. Hardness values of 0.99 and 2.88, friability values of 0.92 and 0.02, and disintegration time values of 0.97 and 10.09 using the GBM algorithm gave the best results.Conclusions: In this study, we developed a computational approach to estimate the optimal pharmaceutical formulation of dexketoprofen. The results were evaluated by an expert, and it was found that they complied with Food and Drug Administration criteria.

Mobile Health Technology and Healthcare Providers: Systemic Barriers to Adoption

Objectives: Despite the growing use of mobile health (mHealth), certain barriers seem to be hindering the use of mHealth applications in healthcare. This article presents a systematic review of the literature on barriers associated with mHealth reported by healthcare professionals.Methods: This systematic review was carried out to identify studies published from January 2015 to December 2019 by searching four electronic databases (PubMed/MEDLINE, Web of Science, Embase, and Google Scholar). Studies were included if they reported perceived barriers to the adoption of mHealth from healthcare providers’ perspectives. Content analysis and categorization of barriers were performed based on a focus group discussion that explored researchers’ knowledge and experiences.Results: Among the 273 papers retrieved through the search strategy, 18 works were selected and 18 barriers were identified. The relevant barriers were categorized into three main groups: technical, individual, and healthcare system. Security and privacy concerns from the category of technical barriers, knowledge and limited literacy from the category of individual barriers, and economic and financial factors from the category of healthcare system barriers were chosen as three of the most important challenges related to the adoption of mHealth described in the included publications.Conclusions: mHealth adoption is a complex and multi-dimensional process that is widely implemented to increase access to healthcare services. However, it is influenced by various factors and barriers. Understanding the barriers to adoption of mHealth applications among providers, and engaging them in the adoption process will be important for the successful deployment of these applications.

Population Mobility, Lockdowns, and COVID-19 Control: An Analysis Based on Google Location Data and Doubling Time from India

Objectives: Physical distancing is a control measure against coronavirus disease 2019 (COVID-19). Lockdowns are a strategy to enforce physical distancing in urban areas, but they are drastic measures. Therefore, we assessed the effectiveness of the lockdown measures taken in the world’s second-most populous country, India, by exploring their relationship with community mobility patterns and the doubling time of COVID-19.Methods: We conducted a retrospective analysis based on community mobility patterns, the stringency index of lockdown measures, and the doubling time of COVID-19 cases in India between February 15 and April 26, 2020. Pearson correlation coefficients were calculated between the stringency index, community mobility patterns, and the doubling time of COVID-19 cases. Multiple linear regression was applied to predict the doubling time of COVID-19.Results: Community mobility drastically fell after the lockdown was instituted. The doubling time of COVID-19 cases was negatively correlated with population mobility patterns in outdoor areas (r = –0.45 to –0.58). The stringency index and outdoor mobility patterns were also negatively correlated (r = –0.89 to –0.95). Population mobility patterns (R2 = 0.67) were found to predict the doubling time of COVID-19, and the model’s predictive power increased when the stringency index was also added (R2 = 0.73).Conclusions: Lockdown measures could effectively ensure physical distancing and reduce short-term case spikes in India. Therefore, lockdown measures may be considered for tailored implementation on an intermittent basis, whenever COVID-19 cases are predicted to exceed the health care system’s capacity to manage.

Predicting Hospital Readmission in Heart Failure Patients in Iran: A Comparison of Various Machine Learning Methods

Objectives: Heart failure (HF) is a common disease with a high hospital readmission rate. This study considered class imbalance and missing data, which are two common issues in medical data. The current study’s main goal was to compare the performance of six machine learning (ML) methods for predicting hospital readmission in HF patients.Methods: In this retrospective cohort study, information of 1,856 HF patients was analyzed. These patients were hospitalized in Farshchian Heart Center in Hamadan Province in Western Iran, from October 2015 to July 2019. The support vector machine (SVM), least-square SVM (LS-SVM), bagging, random forest (RF), AdaBoost, and naïve Bayes (NB) methods were used to predict hospital readmission. These methods’ performance was evaluated using sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. Two imputation methods were also used to deal with missing data.Results: Of the 1,856 HF patients, 29.9% had at least one hospital readmission. Among the ML methods, LS-SVM performed the worst, with accuracy in the range of 0.57–0.60, while RF performed the best, with the highest accuracy (range, 0.90–0.91). Other ML methods showed relatively good performance, with accuracy exceeding 0.84 in the test datasets. Furthermore, the performance of the SVM and LS-SVM methods in terms of accuracy was higher with the multiple imputation method than with the median imputation method.Conclusions: This study showed that RF performed better, in terms of accuracy, than other methods for predicting hospital readmission in HF patients.

Research Development Using REDCap Software

Objectives: High-quality clinical research is dependent on adequate design, methodology, and data collection. The utilization of electronic data capture (EDC) systems is recommended to optimize research data through proper management. This paper’s objective is to present the procedures of REDCap (Research Electronic Data Capture), which supports research development, and to promote the utilization of this software among the scientific community.Methods: REDCap’s web application version 10.4.1 released on 2021 (Vanderbilt University) is an EDC system suitable for clinical research development. This paper describes how to join the REDCap consortium and presents how to develop survey instruments and use them to collect and analyze data.Results: Since REDCap is a web application that stimulates knowledge-sharing among the scientific community, its development is not finished and it is constantly receiving updates to improve the system. REDCap’s tools provide access control, audit trails, and data security to the research team.Conclusions: REDCap is a web application that can facilitate clinical research development, mainly in health fields, and reduce the costs of conducting research. Its tools allow researchers to make the best use of EDC components, such as data storage.

Five-Class Classification of Cervical Pap Smear Images: A Study of CNN-Error-Correcting SVM Models

Objectives: Different complex strategies of fusing handcrafted descriptors and features from convolutional neural network (CNN) models have been studied, mainly for two-class Papanicolaou (Pap) smear image classification. This paper explores a simplified system using combined binary coding for a five-class version of this problem.Methods: This system extracted features from transfer learning of AlexNet, VGG19, and ResNet50 networks before reducing this problem into multiple binary sub-problems using error-correcting coding. The learners were trained using the support vector machine (SVM) method. The outputs of these classifiers were combined and compared to the true class codes for the final prediction.Results: Despite the superior performance of VGG19-SVM, with mean ± standard deviation accuracy and sensitivity of 80.68% ± 2.00% and 80.86% ± 0.45%, respectively, this model required a long training time. There were also false-negative cases using both the VGGNet-SVM and ResNet-SVM models. AlexNet-SVM was more efficient in terms of running speed and prediction consistency. Our findings also showed good diagnostic ability, with an area under the curve of approximately 0.95. Further investigation also showed good agreement between our research outcomes and that of the state-of-the-art methods, with specificity ranging from 93% to 100%.Conclusions: We believe that the AlexNet-SVM model can be conveniently applied for clinical use. Further research could include the implementation of an optimization algorithm for hyperparameter tuning, as well as an appropriate selection of experimental design to improve the efficiency of Pap smear image classification.

Developing an Interactive Computer Program for Integrated Dental Education

Objectives: The knowledge of anatomy is an integral part of dental and medical education that builds the foundations of pathology, physiology, and other related disciplines. Traditional three-dimensional (3D) models used to teach anatomy cannot represent dynamic physiological processes and lack structural detail in the oral regions relevant for dental education. We developed an interactive computer program to teach oral anatomy, pathology, and microbiology in an integrated manner to improve students’ learning experiences.Methods: The computer program, Jawnatomy, was developed as a 3D human head. Cognitive load theory guided the design of the tool, with the goal of reducing the heavy cognitive load of learning anatomy and integrating this knowledge with pathology and microbiology. Keller’s attention, relevance, confidence, and satisfaction (ARCS) model of motivational design was used while creating the tool to improve learners’ motivation and engagement. Blender was used to create the graphics, and Unity 3D was used to incorporate interactivity in the program. The 3D renderings of oral anatomy and progression of tooth decay were created with the input of content experts.Results: Jawnatomy will be launched in our institution’s dentistry and dental hygiene program to support project- and team-based learning. This program will also be introduced to students as a self-directed learning tool to help them practice and strengthen their anatomical knowledge at their own pace.Conclusions: Surveys and focus groups will be conducted to evaluate and further improve the computer program. We believe that Jawnatomy will become an invaluable teaching tool for dental education.

Stakeholders’ Perceptions of the Implementation of a Patient-Centric Digital Health Application for Primary Healthcare in India

Objectives: Health systems are shifting from traditional methods of healthcare delivery to delivery using digital applications. This change was introduced at a primary care centre in Chandigarh, India that served a marginalised population. After establishing the digital health system, we explored stakeholders’ perceptions regarding its implementation.Methods: Ethnographic methods were used to explore stakeholders’ perceptions regarding the implementation of the Integrated Health Information System for Primary Health Care (IHIS4PHC), which was developed as a patient-centric digital health application. Data were collected using focus group discussions and in-depth interviews. Participatory observations were made of day-to-day activities including outpatient visits, outreach field visits, and methods of health practice. The collected information was analysed using thematic coding.Results: Healthcare workers highlighted that working with the digital health system was initially arduous, but they later realised its usefulness, as the digital system made it easier to search records and generate reports, rapidly providing evidence to make decisions. Auxiliary nurse midwives reported that recording information on computers saved time when generating reports; however, systematic and mandatory data entry made recording tedious. Staff were apprehensive about the use of computer-based data for monitoring their work performance. Patients appreciated that their previous records were now available on the computer for easy retrieval.Conclusions: The usefulness of the digital health application was appreciated by various primary healthcare stakeholders. Barriers persisted due to perceived needs for flexibility in delivering healthcare services, and apprehensions continued because of increased transparency, accountability, and dependence on computers and digital technicians.