RESUMEN
Throughout evolution, bacteria and other microorganisms have learned efficient foraging strategies that exploit characteristic properties of their unknown environment. While much research has been devoted to the exploration of statistical models describing the dynamics of foraging bacteria and other (micro-) organisms, little is known, regarding the question of how good the learned strategies actually are. This knowledge gap is largely caused by the absence of methods allowing to systematically develop alternative foraging strategies to compare with. In the present work, we use deep reinforcement learning to show that a smart run-and-tumble agent, which strives to find nutrients for its survival, learns motion patterns that are remarkably similar to the trajectories of chemotactic bacteria. Strikingly, despite this similarity, we also find interesting differences between the learned tumble rate distribution and the one that is commonly assumed for the run and tumble model. We find that these differences equip the agent with significant advantages regarding its foraging and survival capabilities. Our results uncover a generic route to use deep reinforcement learning for discovering search and collection strategies that exploit characteristic but initially unknown features of the environment. These results can be used, e.g., to program future microswimmers, nanorobots, and smart active particles for tasks like searching for cancer cells, micro-waste collection, or environmental remediation.
Asunto(s)
Aprendizaje , Refuerzo en Psicología , Modelos Estadísticos , Movimiento (Física) , BacteriasRESUMEN
Aedes aegypti and Anopheles stephensi have challenged human health by transmitting several infectious disease agents, such as malaria, dengue fever, and yellow fever. Larvicides, especially in endemic regions, is an effective approach to the control of mosquito-borne diseases. In this study, the composition of three essential oil from the Artemisia L. family was analyzed by Gas Chromatography-Mass Spectrometry. Afterward, nanoliposomes containing essential oils of A. annua, A. dracunculus, and A. sieberi with particle sizes of 137 ± 5, 151 ± 6, and 92 ± 5 nm were prepared. Besides, their zeta potential values were obtained at 32 ± 0.5, 32 ± 0.6, and 43 ± 1.7 mV. ATR-FTIR analysis (Attenuated Total Reflection-Fourier Transform InfraRed) confirmed the successful loading of the essential oils. Moreover, The LC50 values of nanoliposomes against Ae. aegypti larvae were 34, 151, and 197 µg/mL. These values for An.stephensi were obtained as 23 and 90, and 140 µg/mL, respectively. The results revealed that nanoliposomes containing A. dracunculus exerted the highest potential larvicidal effect against Ae. aegypti and An. stephensi, which can be considered against other mosquitoes.
Asunto(s)
Aedes , Anopheles , Artemisia , Culex , Insecticidas , Aceites Volátiles , Animales , Humanos , Aceites Volátiles/farmacología , Aceites Volátiles/análisis , Larva , Insecticidas/química , Hojas de la Planta/química , Extractos Vegetales/químicaRESUMEN
BACKGROUND: Despite the importance of the privacy and confidentiality of patients' information, mobile health (mHealth) apps can raise the risk of violating users' privacy and confidentiality. Research has shown that many apps provide an insecure infrastructure and that security is not a priority for developers. OBJECTIVE: This study aims to develop and validate a comprehensive tool to be considered by developers for assessing the security and privacy of mHealth apps. METHODS: A literature search was performed to identify papers on app development, and those papers reporting criteria for the security and privacy of mHealth were assessed. The criteria were extracted using content analysis and presented to experts. An expert panel was held for determining the categories and subcategories of the criteria according to meaning, repetition, and overlap; impact scores were also measured. Quantitative and qualitative methods were used for validating the criteria. The validity and reliability of the instrument were calculated to present an assessment instrument. RESULTS: The search strategy identified 8190 papers, of which 33 (0.4%) were deemed eligible. A total of 218 criteria were extracted based on the literature search; of these, 119 (54.6%) criteria were removed as duplicates and 10 (4.6%) were deemed irrelevant to the security or privacy of mHealth apps. The remaining 89 (40.8%) criteria were presented to the expert panel. After calculating impact scores, the content validity ratio (CVR), and the content validity index (CVI), 63 (70.8%) criteria were confirmed. The mean CVR and CVI of the instrument were 0.72 and 0.86, respectively. The criteria were grouped into 8 categories: authentication and authorization, access management, security, data storage, integrity, encryption and decryption, privacy, and privacy policy content. CONCLUSIONS: The proposed comprehensive criteria can be used as a guide for app designers, developers, and even researchers. The criteria and the countermeasures presented in this study can be considered to improve the privacy and security of mHealth apps before releasing the apps into the market. Regulators are recommended to consider an established standard using such criteria for the accreditation process, since the available self-certification of developers is not reliable enough.
Asunto(s)
Aplicaciones Móviles , Telemedicina , Humanos , Privacidad , Reproducibilidad de los Resultados , InvestigadoresRESUMEN
Introduction: Mild cognitive impairment (MCI) is a primary disorder intensified by aging. Rapid diagnosis of MCI can prevent its progression towards the development of dementia. Thus, the present study was conducted to evaluate the psychometric features of the self-assessment Persian version of the Alzheimer questionnaire (AQ) in the elderly to detect MCI. Methods: First, the AQ was translated into the Persian language; then, its content validity was evaluated by the content validity index (CVI) and content validity ratio (CVR) method, and face validity was determined by two checklists for expert panel and the elderly. The convergent validity of the self-assessment AQ with the Montreal cognitive assessment (MoCA) was assessed using the Pearson correlation. The test-retest and internal consistency reliability were evaluated using intra-class correlation (ICC) and Kuder-Richardson coefficients, respectively. Moreover, the receiver operating characteristic curve was used to determine the optimal cut-off point of self-assessment AQ. Among 148 older people who took part in this study, 93 met our inclusion criteria (aged 60 years old or older, had reading and writing skills, and were able to speak and communicate). Results: A translated version of the questionnaire was named "M-check." The developed test showed good content and face validity. Statistically significant correlations were found between M-check and MoCA (r=-0.83, P<0.05). The Kuder-Richardson and ICC coefficients were obtained as 0.84 and 0.92, respectively. Area under the curve presented satisfactory values (Area under curve [AUC]=0.852, sensitivity=0.62, specificity=0.94). Conclusion: The M-check can be used as a valid and reliable instrument for assessing cognitive state and screening MCI in older adults. Highlights: All questions achieved desired face validity.The convergent validity of Alzheimer Questioner (AQ) was confirmed with high correlation.The AQ is statistically significant with Montreal Cognitive Assessment (MoCA).The AQ had acceptable stability, repeatability, and reliability.All findings demonstrated that the M-Check had high values in predicting MCI in the early stages. Plain Language Summary: Mild cognitive impairment (MCI) is a subset of mental disorders that is an early condition that may lead to dementia. People with MCI are usually prone to forgetfulness in a short time. If MCI is not detected in the early stages, it can progress to dementia or Alzheimer's to higher degrees. On the other hand, cognitive decline and MCI can cause major problems for patients and their families. So it is essential to act out as soon as possible. It is considered that a tool for the early identification of MCI that is self-assessed by individuals, without the presence of an expert and trained person to interpret the results, was not observed in Iran. Thus, the present study was conducted to evaluate the psychometric features of the self-assessment Persian version of the Alzheimer questionnaire (AQ) in the elderly. The results showed that the AQ is a simple one that can be quickly completed by any person at home or by family members of the elderly so that people can refer to the relevant specialist more soon if needed.
RESUMEN
Background: According to World Health Organization (WHO), cardiovascular diseases (CVDs) are the leading cause of death globally. Although significant progress has been made in the diagnosis of CVDs, more investigation can be helpful. Therefore, this study aimed to predict the risk of myocardial infarction (MI) using data mining algorithms. Methods: The applied data were related to the admitted patients in Rajaei specialized cardiovascular hospital located in Tehran. At first, a literature review and interview with a cardiologist were conducted to understand MI. Then, data preparation (cleaning and normalizing the data) was performed. After all, different classification algorithms were applied in IBM SPSS Modeler (14.2) software on the prepared data; and, power of the applied algorithms and the importance of the risk factors in predicting the probability of getting involved with MI was calculated in the mentioned software. Results: This study was able to predict MI % 75.28 and 77.77% in terms of accuracy and sensitivity, respectively. The results also revealed that cigarette consumption, addiction, blood pressure, and cholesterol were the most important risk factors in predicting the probability of getting involved with MI, respectively. Conclusions: Predicting studies aim to support rather than replace clinical judgment. Our prediction models are not sufficiently accurate to supplant decision-making by physicians but have considerable tips about MI risk factors.
RESUMEN
OBJECTIVES: Machine learning has been widely used to predict diseases, and it is used to derive impressive knowledge in the healthcare domain. Our objective was to predict in-hospital mortality from hospital-acquired infections in trauma patients on an unbalanced dataset. METHODS: Our study was a cross-sectional analysis on trauma patients with hospital-acquired infections who were admitted to Shiraz Trauma Hospital from March 20, 2017, to March 21, 2018. The study data was obtained from the surveillance hospital infection database. The data included sex, age, mechanism of injury, body region injured, severity score, type of intervention, infection day after admission, and microorganism causes of infections. We developed our mortality prediction model by random under-sampling, random over-sampling, clustering (k-mean)-C5.0, SMOTE-C5.0, ADASYN-C5.5, SMOTE-SVM, ADASYN-SVM, SMOTE-ANN, and ADASYN-ANN among hospital-acquired infections in trauma patients. All mortality predictions were conducted by IBM SPSS Modeler 18. RESULTS: We studied 549 individuals with hospital-acquired infections in a trauma hospital in Shiraz during 2017 and 2018. Prediction accuracy before balancing of the dataset was 86.16%. In contrast, the prediction accuracy for the balanced dataset achieved by random under-sampling, random over-sampling, clustering (k-mean)-C5.0, SMOTE-C5.0, ADASYN-C5.5, and SMOTE-SVM was 70.69%, 94.74%, 93.02%, 93.66%, 90.93%, and 100%, respectively. CONCLUSIONS: Our findings demonstrate that cleaning an unbalanced dataset increases the accuracy of the classification model. Also, predicting mortality by a clustered under-sampling approach was more precise in comparison to random under-sampling and random over-sampling methods.
RESUMEN
Obstructive Sleep Apnea (OSA) is the most common breathing-related sleep disorder, leading to increased risk of health problems. In this study, we investigated and evaluated the supervised machine learning methods to predict OSA. We used popular machine learning algorithms to develop the prediction models, using a dataset with non-invasive features containing 231 records. Based on the methodology, the CRISP-DM, the dataset was checked and the blanked data were replaced with average/most frequented items. Then, the popular machine learning algorithms were applied for modeling and the 10-fold cross-validation method was used for performance comparison purposes. The dataset has 231 records, of which 152 (65.8%) were diagnosed with OSA. The majority was male (143, 61.9%). The results showed that the best prediction model with an overall AUC reached the Naïve Bayes and Logistic Regression classifier with 0.768 and 0.761, respectively. The SVM with 93.42% sensitivity and the Naïve Bayes of 59.49% specificity can be suitable for screening high-risk people with OSA. The machine learning methods with easily available features had adequate power of discrimination, and physicians can screen high-risk OSA as a supplementary tool.
Asunto(s)
Apnea Obstructiva del Sueño , Teorema de Bayes , Femenino , Humanos , Aprendizaje Automático , Masculino , Polisomnografía , Aprendizaje Automático SupervisadoRESUMEN
Patient portals can have positive consequences in the empowerment of people with depression by raising awareness about their condition. Patient portals are important yet challenging technologies in the field of mental health care. We conducted a scoping review aiming to investigate some important characteristics and features of the mental health websites and related patient portal services for the target audience including people with depression. For this purpose, two reviewers independently entered the keywords in the popular search engines including Google, Yahoo, and Bing in April 2019, in order to find mental health websites that provide patient portal service targeting depression. Examination of the inclusion and exclusion criteria led finally to the selection of 31 websites. We found out that some features of patient portals including the online questionnaires, messaging between the patient and the healthcare provider, and medication refill were more consistent with the areas on which the mental healthcare providers focus, and thus can be effective in improving the progression of these areas. It is essential for patient portal providers to put more focus on expressing the patient portal's features and objectives on their websites. Besides, it is also necessary to conduct further research to investigate the obstacles and facilitators of the interactive features of the patient portals in the field of mental health care, particularly depression.
RESUMEN
BACKGROUND: We aimed to identify the indicators of healthcare fraud and abuse in general physicians' drug prescription claims, and to identify a subset of general physicians that were more likely to have committed fraud and abuse. METHODS: We applied data mining approach to a major health insurance organization dataset of private sector general physicians' prescription claims. It involved 5 steps: clarifying the nature of the problem and objectives, data preparation, indicator identification and selection, cluster analysis to identify suspect physicians, and discriminant analysis to assess the validity of the clustering approach. RESULTS: Thirteen indicators were developed in total. Over half of the general physicians (54%) were 'suspects' of conducting abusive behavior. The results also identified 2% of physicians as suspects of fraud. Discriminant analysis suggested that the indicators demonstrated adequate performance in the detection of physicians who were suspect of perpetrating fraud (98%) and abuse (85%) in a new sample of data. CONCLUSION: Our data mining approach will help health insurance organizations in low-and middle-income countries (LMICs) in streamlining auditing approaches towards the suspect groups rather than routine auditing of all physicians.
Asunto(s)
Minería de Datos/métodos , Prescripciones de Medicamentos/estadística & datos numéricos , Fraude/estadística & datos numéricos , Médicos Generales/estadística & datos numéricos , Seguro de Salud/estadística & datos numéricos , Mala Conducta Profesional/estadística & datos numéricos , Femenino , Humanos , Irán/epidemiología , Masculino , Práctica PrivadaRESUMEN
Inappropriate payments by insurance organizations or third party payers occur because of errors, abuse and fraud. The scale of this problem is large enough to make it a priority issue for health systems. Traditional methods of detecting health care fraud and abuse are time-consuming and inefficient. Combining automated methods and statistical knowledge lead to the emergence of a new interdisciplinary branch of science that is named Knowledge Discovery from Databases (KDD). Data mining is a core of the KDD process. Data mining can help third-party payers such as health insurance organizations to extract useful information from thousands of claims and identify a smaller subset of the claims or claimants for further assessment. We reviewed studies that performed data mining techniques for detecting health care fraud and abuse, using supervised and unsupervised data mining approaches. Most available studies have focused on algorithmic data mining without an emphasis on or application to fraud detection efforts in the context of health service provision or health insurance policy. More studies are needed to connect sound and evidence-based diagnosis and treatment approaches toward fraudulent or abusive behaviors. Ultimately, based on available studies, we recommend seven general steps to data mining of health care claims.