Fake pharmaceuticals: A review of current analytical approaches
داروهای تقلبی: مروری بر روش های تحلیلی در حال حاضر-2019
Poor quality pharmaceuticals may have serious consequences for human health because of treatment failure, development of antimicrobial resistance and dramatic adverse drug reactions. This can significantly undermine consumers confidence in healthcare systems and cause an increase in healthcare costs. The vast array of analytical approaches available nowadays makes an important contribution to distinguishing between genuine and fake medicines. The scientific literature published mostly over the last decade on this subject matter was searched and the support provided by modern analytical techniques in combating falsified drugs was discussed. This survey showed that chromatography–based techniques, often in combination with mass spectrometry, have the lions share. In turn, also colorimetry, infrared spectroscopy and Raman spectroscopy appear to be rather popular approaches.
Mining patient-specific and contextual data with machine learning technologies to predict cancellation of children’s surgery
استخراج داده های خاص و اختصاصی بیمار با فناوری های یادگیری ماشین برای پیش بینی لغو جراحی کودکان-2019
Background: Last-minute surgery cancellation represents a major wastage of resources and can cause significant inconvenience to patients. Our objectives in this study were: 1) To develop predictive models of last-minute surgery cancellation, utilizing machine learning technologies, from patient-specific and contextual data from two distinct pediatric surgical sites of a single institution; and 2) to identify specific key predictors that impact children’s risk of day-of-surgery cancellation. Methods and findings: We extracted five-year datasets (2012–2017) from the Electronic Health Record at Cincinnati Children’s Hospital Medical Center. By leveraging patient-specific information and contextual data, machine learning classifiers were developed to predict all patient-related cancellations and the most frequent four cancellation causes individually (patient illness, “no show,” NPO violation and refusal to undergo surgery by either patient or family). Model performance was evaluated by the area under the receiver operating characteristic curve (AUC) using ten-fold cross-validation. The best performance for predicting all-cause surgery cancellation was generated by gradient-boosted logistic regression models, with AUC 0.781 (95% CI: [0.764,0.797]) and 0.740 (95% CI: [0.726,0.771]) for the two campuses. Of the four most frequent individual causes of cancellation, “no show” and NPO violation were predicted better than patient illness or patient/family refusal. Models showed good cross-campus generalizability (AUC: 0.725/0.735, when training on one site and testing on the other). To synthesize a human-oriented conceptualization of pediatric surgery cancellation, an iterative step-forward approach was applied to identify key predictors which may inform the design of future preventive interventions. Conclusions: Our study demonstrated the capacity of machine learning models for predicting pediatric patients at risk of last-minute surgery cancellation and providing useful insight into root causes of cancellation. The approach offers the promise of targeted interventions to significantly decrease both healthcare costs and also families’ negative experiences.
Keywords: Pediatric surgery cancellation | Quality improvement | Predictive modeling | Machine learning
Sexually Transmitted Diseases Among US Adolescents and Young Adults
بیماریهای مقاربتی در بین نوجوانان و بزرگسالان آمریکایی-2019
Although sexually transmitted diseases (STDs) affect individuals of all ages, they take a particularly heavy toll on young people. Expanded, integrated, multilevel approaches are warranted to reverse recent increases in STDs and improve sexual and reproductive health outcomes for adolescents and young adults in the United States. Approaches must reach beyond clinics and school classrooms; capitalize on cuttingedge, youth-friendly technologies; and change social contexts in ways that encourage young people’s healthy sexual decision-making.
KEYWORDS : Adolescents | Young adults | Sexually transmitted diseases | Epidemiology | Clinical practice guidelines | Prevention
Aging out of adolescent delinquency: Results from a longitudinal sample of youth and young adults
پیر شدن از بزهکاری در نوجوانان: نتایج حاصل از یک نمونه طولی از جوانان و بزرگسالان-2019
One of the most consistent findings to emerge from criminological research is the age-crime curve. To date, however, there has not been much consensus regarding the mechanism(s) that are responsible for creating the distribution of crime across age. The current study uses this backdrop as a springboard to examine the potential factors that might account for why some adolescents who are heavily involved in nonviolent and violent delinquency “age out” of crime and delinquency during the transition to adulthood whereas others persist with such behavior. To do so, data from the National Longitudinal Study of Adolescent to Adult Health (Add Health) are analyzed. The results reveal relatively inconsistent effects of multiple socialization and individual differences measures on the aging out process across multiple time periods. Two measures—delinquent peers and low selfcontrol— however, do have some statistically significant effects on some of the aging out measures. The potential reasons for the results are discussed and directions for future research are offered.
Keywords: Add health | Age-crime | Aging out | Delinquency | Socialization
Malpractice risk and medical treatment selection
خطر سوء استفاده و انتخاب درمان پزشکی-2019
Westudy howlegal and financial incentives affectmedical decisions. Using patient-level data fromItaly, weidentify the effect of a change in medical liability pressure by exploiting the geographical distribution of hospitals across court districts, where some districts increase the predictability of expected damages per injury while others do not. Using a difference-in-differences identification strategy, we show that as certainty of compensation increases, c-sections increase by 6.5 percentage points. There is no statistically significant effect on secondary health outcomes of either mothers or newborns, but the increase is higher for low-risk than high-risk mothers. The increase is driven by hospitals that have lower quality, are governed by inefficient court districts, face lower expected damages, and are paid more per c-section.
Keywords: Scheduled damages | Cesarean sections | Difference in differences
An Expert System Gap Analysis and Empirical Triangulation of Individual Differences, Interventions, and Information Technology Applications in Alertness of Railroad Workers
تجزیه و تحلیل شکاف سیستم خبره و مثلث تجربی تفاوت های فردی ، مداخلات و کاربردهای فناوری اطلاعات در هوشیاری کارگران راهآهن-2019
In this abstract we would like to provide some exciting concrete information including the article’s main impact and significance on expert and intelligent systems. The main impact is that the PTC expert intelligent system fills in the gaps between the human and software decision making processes. This gap analysis is analyzed via empirical triangulation of rail worker data collected from its groups, individuals and the rail industry itself. We utilize an expert intelligent system PTC information technology application to both measure and to improve the alertness of the groups and workers in order to improve the overall safety of the railways through reduced human errors and failures to prevent accidents. Many individual differences in alertness among military, railroad, and other industry workers stem from a lack of sufficient sleep. This continues to be a concern in the railroad industry, even with the implementation of positive train control (PTC) expert system technology. Information technology aids such as PTC cannot prevent all accidents, and errors and failures with PTC may occur. Furthermore, drug interventions are a short-term solution for improving alertness. This study investigated the effect of sleep deprivation on the alertness of railroad signalmen at work, individual differences in alertness, and the information technology available to improve alertness. We investigated various information and communication technology control systems that can be used to maintain operational safety in the railroad industry in the face of incompatible circadian rhythms due to irregular hours, weekend work, and night operations. To fully explain individual differences after the adoption of technology, our approach posits the necessary parameters that one must consider for reason-oriented action, sequential updating, feedback, and technology acceptance in a unified model. This triangulation can help manage workers by efficiently increasing their productivity and improving their health. In our analysis we used R statistical software and Tableau. To test our theory, we issued an Apple watch to a locomotive engineer. The perceived usefulness, perceived ease of use, and actual use he reported led to an analysis of his sleep patterns that eventually ended in his adoption of a sleep apnea device and an improvement in his alertness and effectiveness. His adoption of the technology also resulted in a decrease in his use of chemical interventions to increase his alertness. Our model shows that the alertness of signalmen can be predicted. Therefore, we recommend that the alertness of all railroad workers be predicted given the safety limitations of PTC.
Keywords : Sleep Deprivation | Fatigue | Stress | Expert System | Alertness | Empirical Analysis
How older people became less afraid of crime: An age-period-cohort analysis using repeated cross-sectional survey data
چگونه افراد مسن تر از جرم و جنایت کمتر می ترسند: تحلیل با سن دوره کوهورت با استفاده از تکرار داده های مروری به صورت مقطعی-2019
One of the most robust predictors of fear of crime is age: Older people tend to be more fearful. Yet, many questions beyond the basic cross-sectional relationship remain unexplored. We investigate cohort effects on fear of crime, applying graphical analyses and a version of the hierarchical age-period-cohort (HAPC) analysis to eight waves of the German subset of the European Social Survey. We hypothesize that health improvements and the educational expansion in postwar Germany led to a decreasing cohort trend, and that children exposed to traumatic experiences and adverse living conditions during and after World War II report higher levels of perceived insecurity throughout the life course. We argue that cross-sectional age differences are, in fact, to a large extent cohort effects, mediated by improved self-rated health and increasing education. The analyses also unveil a recent period effect after 2014. These novel findings add considerably to the understanding of the temporal dynamics of fear of crime.
Keywords: Fear of crime | Age-period-cohort analysis | Generation | Education | Health
Development of machine learning algorithms for prediction of mortality in spinal epidural abscess
توسعه الگوریتم های یادگیری ماشین برای پیش بینی مرگ و میر در آبسه اپیدورال ستون فقرات-2019
BACKGROUND CONTEXT: In-hospital and short-term mortality in patients with spinal epidural abscess (SEA) remains unacceptably high despite diagnostic and therapeutic advancements. Forecasting this potentially avoidable consequence at the time of admission could improve patient management and counseling. Few studies exist to meet this need, and none have explored methodologies such as machine learning. PURPOSE: The purpose of this study was to develop machine learning algorithms for prediction of in-hospital and 90-day postdischarge mortality in SEA. STUDY DESIGN/SETTING: Retrospective, case-control study at two academic medical centers and three community hospitals from 1993 to 2016. PATIENTS SAMPLE: Adult patients with an inpatient admission for radiologically confirmed diagnosis of SEA. OUTCOME MEASURES: In-hospital and 90-day postdischarge mortality. METHODS: Five machine learning algorithms (elastic-net penalized logistic regression, random forest, stochastic gradient boosting, neural network, and support vector machine) were developed and assessed by discrimination, calibration, overall performance, and decision curve analysis. RESULTS: Overall, 1,053 SEA patients were identified in the study, with 134 (12.7%) experiencing in-hospital or 90-day postdischarge mortality. The stochastic gradient boosting model achieved the best performance across discrimination, c-statistic=0.89, calibration, and decision curve analysis. The variables used for prediction of 90-day mortality, ranked by importance, were age, albumin, platelet count, neutrophil to lymphocyte ratio, hemodialysis, active malignancy, and diabetes. The final algorithm was incorporated into a web application available here: https://sorg-apps.shinyapps.io/seamortality/. CONCLUSIONS: Machine learning algorithms show promise on internal validation for prediction of 90-day mortality in SEA. Future studies are needed to externally validate these algorithms inindependent populations.
Keywords: Artificial intelligence | Healthcare | Machine learning | Mortality | Spinal epidural abscess | Spine surgery
The legal determinants of health: harnessing the power of law for global health and sustainable development
عوامل قانونی سلامت: بهره گیری از قدرت قانون برای سلامت جهانی و توسعه پایدار-2019
Health risks in the 21st century are beyond the control of any government in any country. In an era of globalisation, promoting public health and equity requires cooperation and coordination both within and among states. Law can be a powerful tool for advancing global health, yet it remains substantially underutilised and poorly understood. Working in partnership, public health lawyers and health professionals can become champions for evidence-based laws to ensure the public’s health and safety. This Lancet Commission articulates the crucial role of law in achieving global health with justice, through legal instruments, legal capacities, and institutional reforms, as well as a firm commitment to the rule of law. The Commission’s aim is to enhance the global health community’s understanding of law, regulation, and the rule of law as effective tools to advance population health and equity.
Machine learning for phenotyping opioid overdose events
یادگیری ماشین برای فنوتیپ وقایع مصرف بیش از حد مواد افیونی-2019
Objective: To develop machine learning models for classifying the severity of opioid overdose events from clinical data. Materials and methods: Opioid overdoses were identified by diagnoses codes from the Marshfield Clinic population and assigned a severity score via chart review to form a gold standard set of labels. Three primary feature sets were constructed from disparate data sources surrounding each event and used to train machine learning models for phenotyping. Results: Random forest and penalized logistic regression models gave the best performance with cross-validated mean areas under the ROC curves (AUCs) for all severity classes of 0.893 and 0.882 respectively. Features derived from a common data model outperformed features collected from disparate data sources for the same cohort of patients (AUCs 0.893 versus 0.837, p value=0.002). The addition of features extracted from free text to machine learning models also increased AUCs from 0.827 to 0.893 (p value < 0.0001). Key word features extracted using natural language processing (NLP) such as ‘Narcan’ and ‘Endotracheal Tube’ are important for classifying overdose event severity. Conclusion: Random forest models using features derived from a common data model and free text can be effective for classifying opioid overdose events.
Keywords: Machine learning | Opioid | Phenotype | Overdose | Electronic health record