Predictis: an IoT and machine learning-based system to predict risk level of cardio-vascular diseases.

BACKGROUND: Despite technological advancement in the field of healthcare, the worldwide burden of illness caused by cardio-vascular diseases (CVDs) is rising, owing mostly to a sharp increase in developing nations that are undergoing fast health transitions. People have been experimenting with techniques to extend their lives since ancient times. Despite this, technology is still a long way from attaining the aim of lowering mortality rates. METHODS: From methodological perspective, a design Science Research (DSR) approach is adopted in this research. As such, to investigate the current healthcare and interaction systems created for predicting cardiac disease for patients, we first analyzed the body of existing literature. After that, a conceptual framework of the system was designed using the gathered requirements. Based on the conceptual framework, the development of different components of the system was completed. Finally, the evaluation study procedure was developed taking into account the effectiveness, usability and efficiency of the developed system. RESULTS: To attain the objectives, we proposed a system consisting of a wearable device and mobile application, which allows the users to know their risk levels of having CVDs in the future. The Internet of Things (IoT) and Machine Learning (ML) techniques were adopted to develop the system that can classify its users into three risk levels (high, moderate and low risk of having CVD) with an F1 score of 80.4% and two risk levels (high and low risk of having CVD) with an F1 score of 91%. The stacking classifier incorporating best-performing ML algorithms was used for predicting the risk levels of the end-users utilizing the UCI Repository dataset. CONCLUSION: The resultant system allows the users to check and monitor their possibility of having CVD in near future using real-time data. Also, the system was evaluated from the Human-Computer Interaction (HCI) point of view. Thus, the created system offers a promising resolution to the current biomedical sector. TRIAL REGISTRATION: Not Applicable.

Is cadaveric dissection essential in medical education? A qualitative survey comparing pre-and post-COVID-19 anatomy courses.

CONTEXT: With the surge of the novel coronavirus (SARS-CoV-2 [COVID-19]), the modality of teaching anatomy has shifted from in-person cadaveric dissection to virtual lessons for incoming first-year medical students. As a result, we aim to assess the impact that this curriculum change has on student perspectives. OBJECTIVES: This study aims to understand the relative effect of a virtual anatomy course implemented during the pandemic (2019-2020) on the confidence, skills, and perspectives of first-year medical students compared to medical students who had traditional in-person anatomy at Rowan University School of Osteopathic Medicine (Rowan SOM) in Stratford, New Jersey. METHODS: The authors developed a 14-question survey to target gross anatomy students of the Classes of 2023 and 2024 at Rowan SOM. The Class of 2024 had a virtual anatomy lab compared to the Class of 2023, who had an in-person anatomy lab in their first year of medical school. The responses were analyzed to understand the difference between a hands-on cadaver lab and a virtual anatomy lab utilizing SPSS. RESULTS: The survey was administered to approximately 400 people, from which we received 149 responses (37.3%). Among all responses, 36.2% (n=54) belonged to the Class of 2023 who encountered hands-on cadaver experience, whereas 63.8% (n=95) belonged to the Class of 2024 who gained virtual anatomy lab experience. An independent t-test statistical analysis was utilized. Under the confidence domain, when students were asked about the understanding of trauma after their respective anatomy labs, 64.0% of the Class of 2023 (n=50) showed significantly higher confidence with p<0.001, compared to 15.4% for the Class of 2024 (n=78). Under the skills domain, the Class of 2023 (n=50) felt more comfortable with ultrasound (64.0%), identifying all of the pertinent anatomical structures and their respective locations on imaging (72.0%), and identifying the pathology (90.0%) with respective p values of <0.001, <0.001, and 0.004. Only 36.9% of Class of 2024 respondents shared similar comfort with ultrasound (n=84), 30.9% identifying pertinent anatomical structures (n=84) and 65.4% in identifying pathology (n=84). Under the attitude domain, the Class of 2023 (n=50) had more respect toward the human body with their hands-on cadaver experience (88.0%) than the Class of 2024 (n=89, 33.3%). CONCLUSIONS: Based on current results, it can be established that medical students who had in-person cadaveric dissection had a favorable attitude toward their anatomy course compared to students who had virtual anatomy during the COVID-19 pandemic.

Digital health interventions for cervical cancer care: A systematic review and future research opportunities.

BACKGROUND: Cervical cancer is a malignancy among women worldwide, which is responsible for innumerable deaths every year. The primary objective of this review study is to offer a comprehensive and synthesized overview of the existing literature concerning digital interventions in cervical cancer care. As such, we aim to uncover prevalent research gaps and highlight prospective avenues for future investigations. METHODS: This study adopted a Systematic Literature Review (SLR) methodology where a total of 26 articles were reviewed from an initial set of 1110 articles following an inclusion-exclusion criterion. RESULTS: The review highlights a deficiency in existing studies that address awareness dissemination, screening facilitation, and treatment provision for cervical cancer. The review also reveals future research opportunities like explore innovative approaches using emerging technologies to enhance awareness campaigns and treatment accessibility, consider diverse study contexts, develop sophisticated machine learning models for screening, incorporate additional features in machine learning research, investigate the impact of treatments across different stages of cervical cancer, and create more user-friendly applications for cervical cancer care. CONCLUSIONS: The findings of this study can contribute to mitigating the adverse effects of cervical cancer and improving patient outcomes. It also highlights the untapped potential of Artificial Intelligence and Machine Learning, which could significantly impact our society.

Empyema Versus Lung Abscess: A Case Report.

Lung abscesses and empyemas are 2 forms of pulmonary infection that can present with similar clinical features. However, empyemas are associated with higher morbidity and mortality, necessitating the need to distinguish one from the other. Plain radiographs can sometimes provide clues to help differentiate the 2 pathologies but more often than not, a computed tomography scan is required to confirm the diagnosis. Correct diagnosis is essential, as the goal standard therapeutic intervention for empyemas may be contraindicated in patients with lung abscesses. Empyemas require percutaneous or surgical drainage in combination with antibiotics, while lung abscesses are generally treated with antibiotics alone as drainage can be associated with various complications. We present a case of a 65-year-old man with parapneumonic empyema diagnosed with characteristic findings on chest computed tomography and treated with surgical drainage and antibiotics. We hope to improve patient outcomes by highlighting the classical radiographic findings that help distinguish empyema and abscess.