scholarly journals Explainable Machine Learning Prediction for Mortality of COVID-19 in the Colombian Population

2021 ◽  
Author(s):  
Gabriel Ricardo Vásquez Morales ◽  
Sergio Mauricio Martínez Monterrubio ◽  
Juan Antonio Recio García ◽  
Pablo Moreno Ger
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Public Health Problem ◽  
Classification Model ◽  
Global Public Health ◽  
The Neural Network ◽  
Large Numbers ◽  
History Of ◽  
The One ◽  
Global Public Health Problem

Abstract The COVID-19 pandemic, which began in late 2019, has become a global public health problem, resulting in large numbers of people infected and dead. One of the greatest challenges in dealing with the disease is to identify those people who are most at risk of becoming infected, seriously ill and dying from the virus, so that they can be isolated in a targeted manner and thus reduce mortality rates. This article proposes the use of machine learning, and specifically of neural networks and random forest to build two complementary models that identify the probability that a person has of dying because of COVID-19. The models are trained with the demographic information and medical history of two population groups: on the one hand, 43,000 people who died from COVID-19 in Colombia during 2020, and on the other hand, a random sample of 43,000 people who became ill with COVID-19 during the same period of time, but later recovered. After training the neural network classification model, evaluation metrics were applied that yielded an 88% accuracy value. However, transparency is a major requirement for the explicability of COVID-19 prognosis. Therefore, a complementary random forest model is trained that allows the identification of the most significant predictors of mortality by COVID-19.

scholarly journals Explainable Machine Learning Prediction for COVID-19 Mortality in the Colombian Population

2021 ◽  
Author(s):  
Gabriel Ricardo Vásquez Morales ◽  
Sergio Mauricio Martínez Monterrubio ◽  
Juan Antonio Recio García ◽  
Pablo Moreno Ger
Keyword(s):  
Machine Learning ◽  
Public Health Problem ◽  
Classification Model ◽  
Global Public Health ◽  
Demographic Information ◽  
The Neural Network ◽  
Large Numbers ◽  
History Of ◽  
Seriously Ill ◽  
Global Public Health Problem

Abstract The COVID-19 pandemic, which began in late 2019, has become a global public health problem, resulting in large numbers of infections and deaths. One of the greatest challenges in dealing with the disease is to identify those people who are most at risk of becoming infected, seriously ill and dying from the virus so that they can be isolated in a targeted manner to reduce mortality rates. This article proposes using machine learning, specifically neural networks, and random forests, to build two complementary models that identify the probability that a person has of dying because of COVID-19. The models are trained with the demographic information and medical history of two population groups: 43,000 people who died from COVID-19 in Colombia during 2020, and a random sample of 43,000 people who became ill with COVID-19 during the same period but later recovered. After training the neural network classification model, evaluation metrics were applied that yielded an 88% accuracy value. However, transparency is a major requirement for the explicability of the COVID-19 prognosis. Therefore, a complementary random forest model was trained that identified the most significant predictors of mortality by COVID-19.

scholarly journals Characteristics of Individuals with Self-Harm: A Retrospective Descriptive Study from Karachi, Pakistan

2021 ◽  
Author(s):  
Ambreen Tharani ◽  
Salima Farooq ◽  
Maryam Ali ◽  
Uroosa Talib ◽  
Murad Moosa Khan
Keyword(s):  
Psychiatric Illness ◽  
Tertiary Care ◽  
Public Health Problem ◽  
Descriptive Study ◽  
Global Public Health ◽  
Over The Counter ◽  
Prevention Programmes ◽  
History Of ◽  
Self Harm ◽  
Global Public Health Problem

Abstract Background: Self-Harm (SH) is a major global public health problem which is under-researched in Pakistan. A prior act of self-harm is one of the strongest predictors of future suicide.Method: This retrospective descriptive study describes the characteristics of SH cases (n=350) that presented to a tertiary care teaching hospital in Karachi, Pakistan, from January 2013 to December 2017. Details related to demography, history, associated factors, access to methods used, and intent to die were collected on a structured proforma and analysed using STATA version 14. Results: It was found that self-harm acts were twice as more common in females than in males. More than half of the reported cases were in the age group 20-39 years. Drug overdose and use of insecticides were the two most common methods used in both genders. Depression was identified in nearly half of the reported SH cases. Intention to die was found to be 3 times greater among patients with psychiatric illness as compared to those with no history of psychiatric illness. Conclusion: This study suggests that limiting access to lethal means, regulating over-the-counter sale of medications, and safe storage of pesticides can possibly serve as effective measures to minimize self-harm incidences. Moreover, integration of suicide assessment and prevention programmes for the general population is also suggested.

4H-1,3-Benzothiazin-4-one a Promising Class Against MDR/XDR-TB

2019 ◽  
Vol 19 (8) ◽  
pp. 567-578 ◽  
Author(s):  
Marcus Vinicius Nora de Souza ◽  
Thais Cristina Mendonça Nogueira
Keyword(s):  
Treatment Time ◽  
Public Health Problem ◽  
New Drugs ◽  
Global Public Health ◽  
Synthesis Mechanism ◽  
Highly Active ◽  
Latent Disease ◽  
Resistant Strains ◽  
Chemical Class ◽  
Global Public Health Problem

Nowadays, tuberculosis (TB) is an important global public health problem, being responsible for millions of TB-related deaths worldwide. Due to the increased number of cases and resistance of Mycobacterium tuberculosis to all drugs used for the treatment of this disease, we desperately need new drugs and strategies that could reduce treatment time with fewer side effects, reduced cost and highly active drugs against resistant strains and latent disease. Considering that, 4H-1,3-benzothiazin-4-one is a promising class of antimycobacterial agents in special against TB-resistant strains being the aim of this review the discussion of different aspects of this chemical class such as synthesis, mechanism of action, medicinal chemistry and combination with other drugs.

scholarly journals Transformer Oil Quality Assessment Using Random Forest with Feature Engineering

Energies ◽  
2021 ◽  
Vol 14 (7) ◽  
pp. 1809
Author(s):  
Mohammed El Amine Senoussaoui ◽  
Mostefa Brahami ◽  
Issouf Fofana
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Oil Quality ◽  
Principal Component ◽  
Condition Assessment ◽  
Classification Performance ◽  
Transformer Oil ◽  
Classification Model ◽  
Insulation Degradation ◽  
Transformer Oils

Machine learning is widely used as a panacea in many engineering applications including the condition assessment of power transformers. Most statistics attribute the main cause of transformer failure to insulation degradation. Thus, a new, simple, and effective machine-learning approach was proposed to monitor the condition of transformer oils based on some aging indicators. The proposed approach was used to compare the performance of two machine-learning classifiers: J48 decision tree and random forest. The service-aged transformer oils were classified into four groups: the oils that can be maintained in service, the oils that should be reconditioned or filtered, the oils that should be reclaimed, and the oils that must be discarded. From the two algorithms, random forest exhibited a better performance and high accuracy with only a small amount of data. Good performance was achieved through not only the application of the proposed algorithm but also the approach of data preprocessing. Before feeding the classification model, the available data were transformed using the simple k-means method. Subsequently, the obtained data were filtered through correlation-based feature selection (CFsSubset). The resulting features were again retransformed by conducting the principal component analysis and were passed through the CFsSubset filter. The transformation and filtration of the data improved the classification performance of the adopted algorithms, especially random forest. Another advantage of the proposed method is the decrease in the number of the datasets required for the condition assessment of transformer oils, which is valuable for transformer condition monitoring.

scholarly journals A novel framework for designing a multi-DoF prosthetic wrist control using machine learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Chinmay P. Swami ◽  
Nicholas Lenhard ◽  
Jiyeon Kang
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Upper Limb ◽  
Daily Living ◽  
Machine Learning Algorithms ◽  
Data Sets ◽  
Random Forest Regression ◽  
Prosthetic Devices ◽  
Upper Limb Function ◽  
The Neural Network

AbstractProsthetic arms can significantly increase the upper limb function of individuals with upper limb loss, however despite the development of various multi-DoF prosthetic arms the rate of prosthesis abandonment is still high. One of the major challenges is to design a multi-DoF controller that has high precision, robustness, and intuitiveness for daily use. The present study demonstrates a novel framework for developing a controller leveraging machine learning algorithms and movement synergies to implement natural control of a 2-DoF prosthetic wrist for activities of daily living (ADL). The data was collected during ADL tasks of ten individuals with a wrist brace emulating the absence of wrist function. Using this data, the neural network classifies the movement and then random forest regression computes the desired velocity of the prosthetic wrist. The models were trained/tested with ADLs where their robustness was tested using cross-validation and holdout data sets. The proposed framework demonstrated high accuracy (F-1 score of 99% for the classifier and Pearson’s correlation of 0.98 for the regression). Additionally, the interpretable nature of random forest regression was used to verify the targeted movement synergies. The present work provides a novel and effective framework to develop an intuitive control for multi-DoF prosthetic devices.

Adherence to Primary Prevention and Skin Self-Examination Practices by Spanish Melanoma Patients

Dermatology ◽  
2021 ◽  
pp. 1-7
Author(s):  
Irene Torrecilla-Martínez ◽  
Esperanza Manrique-Silva ◽  
Victor Traves ◽  
Celia Requena ◽  
Eduardo Nagore
Keyword(s):  
Primary Prevention ◽  
Cutaneous Melanoma ◽  
Public Health Problem ◽  
Global Public Health ◽  
Prevention Measures ◽  
Online Questionnaire ◽  
Cross Sectional ◽  
History Of ◽  
High Level ◽  
Self Examination

<b><i>Background:</i></b> The incidence of cutaneous melanoma, an important global public health problem, has been increasing over the last several decades. <b><i>Objectives:</i></b> In order to decrease melanoma-related mortality, ways to communicate and implement the correct methods for conducting primary and secondary prevention measures (such as early detection via self-examination) should be investigated. <b><i>Materials and Methods:</i></b> An observational, cross-sectional, retrospective study consisting of 409 patients diagnosed with cutaneous melanoma was conducted. An online questionnaire was created to evaluate knowledge levels, attitudes, and adherence to primary preventive measures and to skin self-examination practices. <b><i>Results:</i></b> The results revealed that even when 43% of the patients perform cutaneous self-examinations, only half of them fully followed the recommendations. Patients aged &#x3c;45 years, female, with a I–II phototype, with an intermediate/high level of education, and with a history of NMSC were more likely to have an adequate degree of knowledge. Moreover, patients aged &#x3c;45 years and with an adequate degree of knowledge more frequently showed an adequate adherence to the primary prevention measures. Finally, patients aged 45–60 years and with an adequate degree of knowledge presented a good adherence to the self-skin examination measures. <b><i>Limitations:</i></b> Possible limitations of this study were memory bias through the influence of age within the study population, and bias due to a greater proportion of subjects with a high education level. <b><i>Conclusion:</i></b> Within the population of patients with melanoma, a high percentage of patients do not rigorously follow the recommended prevention measures. Our study highlights the need to implement awareness in this population to improve the prevention of cutaneous cancer.

A REVIEW ON GLOBAL TRENDS IN HEART FAILURE AND EVOLUTION OF ANGIOTENSIN–NEPRILYSIN INHIBITOR

2020 ◽  
pp. 32-37
Author(s):  
VEERENDRA UPPARA ◽  
SAISEKHAR KODIVANDLA ◽  
ASHIK ALI SHAIK
Keyword(s):  
Heart Failure ◽  
Public Health Problem ◽  
Global Public Health ◽  
Middle Income ◽  
Global Trends ◽  
Middle Income Countries ◽  
Health Loss ◽  
Neprilysin Inhibitor ◽  
Health Related ◽  
Global Public Health Problem

Heart failure (HF) is a major global public health problem irrespective of its causes. It generates an enormous clinical, societal, and economic, health loss burden with an increase in its prevalence reaching an epidemic proportion. The morbidity and mortality associated with heart failure are increasing the health-related burdens worldwide, especially in low- and middle-income countries. This review highlights the trends in HF burden, the clinical spectrum of HF, and the importance of neurohormonal pathways and the evolution of angiotensin receptor neprilysin inhibition in HF with updated clinical practice guidelines.

scholarly journals Medication Error in Anaesthesia – A Review

2016 ◽  
Vol 27 (1) ◽  
pp. 31-35
Author(s):  
Montosh Kumar Mondal ◽  
Beauty Rani Roy ◽  
Shibani Banik ◽  
Debabrata Banik
Keyword(s):  
Public Health ◽  
Risk Factors ◽  
Medication Error ◽  
Medication Errors ◽  
Health Problem ◽  
Preventive Measures ◽  
Medical Profession ◽  
Public Health Problem ◽  
Global Public Health ◽  
Global Public Health Problem

Medication error is a major cause of morbidity and mortality in medical profession . There is an increasing recognition that medication errors are causing a substantial global public health problem, as many result in harm to patients and increased costs to health providers.Anaesthesia is now safe and routine, yet anaesthetists are not immune from making medication errors and the consequences of their mistakes may be more serious than those of doctors in other specialties. Steps are being taken to determine the extent of the problem of medication error in anaesthesia. In this review, incidence, types, risk factors and preventive measures of the medication errors are discussed in detail.Journal of Bangladesh Society of Anaesthesiologists 2014; 27(1): 31-35

Sign in / Sign up

Export Citation Format

Share Document