A Mathematical Framework for Combining Decisions of Multiple Experts toward Accurate and Remote Diagnosis of Malaria Using Tele-Microscopy

We propose a methodology for digitally fusing diagnostic decisions made by multiple medical experts in order to improve accuracy of diagnosis. Toward this goal, we report an experimental study involving nine experts, where each one was given more than 8,000 digital microscopic images of individual human red blood cells and asked to identify malaria infected cells. The results of this experiment reveal that even highly trained medical experts are not always self-consistent in their diagnostic decisions and that there exists a fair level of disagreement among experts, even for binary decisions (i.e., infected vs. uninfected). To tackle this general medical diagnosis problem, we propose a probabilistic algorithm to fuse the decisions made by trained medical experts to robustly achieve higher levels of accuracy when compared to individual experts making such decisions. By modelling the decisions of experts as a three component mixture model and solving for the underlying parameters using the Expectation Maximisation algorithm, we demonstrate the efficacy of our approach which significantly improves the overall diagnostic accuracy of malaria infected cells. Additionally, we present a mathematical framework for performing ‘slide-level’ diagnosis by using individual ‘cell-level’ diagnosis data, shedding more light on the statistical rules that should govern the routine practice in examination of e.g., thin blood smear samples. This framework could be generalized for various other tele-pathology needs, and can be used by trained experts within an efficient tele-medicine platform.     

Augmenting Epidemiological Models with Point-Of-Care Diagnostics Data

Although adoption of newer Point-of-Care (POC) diagnostics is increasing, there is a significant challenge using POC diagnostics data to improve epidemiological models. In this work, we propose a method to process zip-code level POC datasets and apply these processed data to calibrate an epidemiological model. We specifically develop a calibration algorithm using simulated annealing and calibrate a parsimonious equation-based model of modified Susceptible-Infected-Recovered (SIR) dynamics. The results show that parsimonious models are remarkably effective in predicting the dynamics observed in the number of infected patients and our calibration algorithm is sufficiently capable of predicting peak loads observed in POC diagnostics data while staying within reasonable and empirical parameter ranges reported in the literature. Additionally, we explore the future use of the calibrated values by testing the correlation between peak load and population density from Census data. Our results show that linearity assumptions for the relationships among various factors can be misleading, therefore further data sources and analysis are needed to identify relationships between additional parameters and existing calibrated ones. Calibration approaches such as ours can determine the values of newly added parameters along with existing ones and enable policy-makers to make better multi-scale decisions.     

Closing the translation gap: AI applications in digital pathology

Recent advances in artificial intelligence show tremendous promise to improve the accuracy, reproducibility, and availability of medical diagnostics across a number of medical subspecialities. This is especially true in the field of digital pathology, which has recently witnessed a surge in publications describing state-of-the-art performance for machine learning models across a wide range of diagnostic applications. Nonetheless, despite this promise, there remain significant gaps in translating applications for any of these technologies into actual clinical practice. In this review, we will first give a brief overview of the recent progress in applying AI to digitized pathology images, focusing on how these tools might be applied in clinical workflows in the near term to improve the accuracy and efficiency of pathologists. Then we define and describe in detail the various factors that need to be addressed in order to successfully close the “translation gap” for AI applications in digital pathology.     

以问题为中心的学习方法在高职社区问诊技能教学中的应用

目的:探讨以问题为中心的教学方法(problem-based learning,PBL)在高职社区问诊教学中的效果,寻求更有效的现代医学教育方法。方法:在高职社区问诊技能学习中开展以问题为中心的教学方法(PBL),分析问诊中存在的问题,以提高知识应用与沟通能力。结果:通过对62名高职医学生进行问诊技能和见习报告评分显示,成绩优良比率为89%,满意度调查显示83.87%的高职医学生对PBL教学方法满意。PBL教学可以让高职医学生灵活的利用自已的时间,进行比较主动的学习,可以更好的发现高职医学生在问诊见习中存在的问题,有利于提高高职医学生的问诊技能及医患沟通能力,但实施中所需时间较长,占用课时多。结论:PBL教学对高职医学生的主动学习能力、问诊技能及医患沟通能力的提高有利,医学生对PBL教学方法满意度高。在医学教育中可以将PBL教学和传统教学方法结合起来,以在有效的时间里达到更好的教学效果。     

Automatic infection detection based on electronic medical records

Background

Making accurate patient care decision, as early as possible, is a constant challenge, especially for physicians in the emergency department. The increasing volumes of electronic medical records (EMRs) open new horizons for automatic diagnosis. In this paper, we propose to use machine learning approaches for automatic infection detection based on EMRs. Five categories of information are utilized for prediction, including personal information, admission note, vital signs, diagnose test results and medical image diagnose.

Results

Experimental results on a newly constructed EMRs dataset from emergency department show that machine learning models can achieve a decent performance for infection detection with area under the receiver operator characteristic curve (AUC) of 0.88. Out of all the five types of information, admission note in text form makes the most contribution with the AUC of 0.87.

Conclusions

This study provides a state-of-the-art EMRs processing system to automatically make medical decisions. It extracts five types of features associated with infection and achieves a decent performance on automatic infection detection based on machine learning models.

     

肝包虫病的诊断现状及进展

肝包虫病是畜牧地区常见的寄生虫病,是一种人畜共患病,非牧地区偶尔也可以见到,可以通过与狗等动物密切接触直接感染,还可以通过呼吸道吸入虫卵或经消化道误食含有虫卵感染的食物或水源等方式感染使人患病,并且可以寄生于人体内各个部位,但以肝脏最为多见,严重危害人体健康和畜牧业的发展。加强肝包虫病的诊断是防控本疾病的重要措施之一,在不能排除肝包虫病的情况下,应结合病史、化验室检查、B超、CT等影像学检查、免疫学检查进行综合分析,给出明确诊断,以防止误诊、漏诊。近年来随着分子生物学以及病原学等技术的发展,为包虫病的诊断提供更多的方法和信息,本文将从肝包虫病的病史及临床表现、影像学检查、免疫学检查、分子生物学检查及病原学检查等方面对其诊断现状及进展做一综述。     

Artificial intelligence in the diagnosis of COVID-19: challenges and perspectives

Artificial intelligence (AI) is being used to aid in various aspects of the COVID-19 crisis, including epidemiology, molecular research and drug development, medical diagnosis and treatment, and socioeconomics. The association of AI and COVID-19 can accelerate to rapidly diagnose positive patients. To learn the dynamics of a pandemic with relevance to AI, we search the literature using the different academic databases (PubMed, PubMed Central, Scopus, Google Scholar) and preprint servers (bioRxiv, medRxiv, arXiv). In the present review, we address the clinical applications of machine learning and deep learning, including clinical characteristics, electronic medical records, medical images (CT, X-ray, ultrasound images, etc.) in the COVID-19 diagnosis. The current challenges and future perspectives provided in this review can be used to direct an ideal deployment of AI technology in a pandemic.     

Private and Public Decisions in Social Dilemmas: Evidence from Children's Behavior

Are selfish impulses less likely to be pursued when decisions are publicly observable? Is the presence of peers a potential solution to social dilemmas? In this paper we report data on the self-control decisions of children aged 6 to 11 who participated in games that require one to resist a selfish impulse for several minutes in order to benefit others. In Public Condition children make decisions in public view of the group of other participants, while in Private Condition they have the possibility to decide privately. We find that children aged 9 and higher are better able to resist selfish impulses in public environments. Younger children, however, display no such effect. Further, we find self-control substantially impacted by group size. When decisions are public, self-control is better in larger groups, while in private condition the opposite holds.     

Exploiting recombinant antibodies in point-of-care (POC) diagnostics: the combinatorial advantage

Antibodies are ubiquitously deployed on in vitro diagnostic (IVD) platforms for detecting a panoply of analytes indicative of environmental and food contamination, residue adulteration and both veterinary and medical diagnostics. In the clinical realm, rapid and accurate determination of disease status is paramount. The significance of immunodiagnostic performance cannot be overemphasized and in many cases reliable diagnosis informs medical intervention which can mean the difference between patient recovery and demise. Cardiovascular disease (CVD) is the single biggest cause of adult mortality in the western world and principal burden on the healthcare services. Although the troponin (Tn) family, in particular troponin I (TnI), are regarded as the gold standard for diagnosis of myocardial damage, over the last decade much research has focused on the identification of alternative cardiac biomarker molecules that can either supplant or complement TnI metrics to add value to cardiac risk stratification criteria. In particular, markers that appear earlier than TnI in the pathophyisiology of cardiac disease are highly sought after. The subject?of this addendum represents part of a broader challenge to deliver novel rapid point-of-care (POC) diagnostics to provide a chip-based multi-plexed platform for more comprehensive profiling of cardiac status with additive diagnostic and prognostic value.?Specifically, it outlines proof-of-concept direct myeloperoxidase (MPO) detection, demonstrates the benefits of using recombinant antibodies in POC diagnostics and describes optimized strategies for generation of superior candidate antibody panels.     

Roentgen diagnostics with the emphasis on it's traditional roentgenological method is a major sourse to improve gastric cancer diagnosis

The main idea of the article is presentation of todays problem of gastric cancer diagnosis. Authors, supported by long-term experience of gastric cancer diagnostics, demonstrate the necessity of the return of traditional roentgenological method for it's diagnostics, along with endoscopic technique. In the first place it is determined by the increase of sclerotic and mixed forms. In the second place, it is associated by the change of gastric cancer primary localizations, supporting the need of active use of roentgen diagnostics for it's diagnosis. One of the important parts of the article consists of the author's attempt to change general opinion about insignificancy role of traditional roentgenological method for diagnosis of gastric cancer. Authors demonstrate modern techniques of traditional stomach roentgenology and firstly, it's digital development with CR-systems for the improvement of diagnosis of the intramural forms of carcinomas. In the initial stages it is obligatory to engage classical roentgenology with double contrast study and endoscopy as main equally important methods. The unfavourable situaition in the diagnosis of gastric cancer can be changed only with conjoint use of these two approaches. It is chiefly depends with the difficulties of endoscopic study of diffuse (endophytic) forms of gastric carcinoma. Authors separately underline the necessity of including specialists in roentgen diagnostics in the national project of modernization of roentgenological equipment in medical institutions.     

Personalized diagnostics and biosensors: a review of the biology and technology needed for personalized medicine

Abstract

Exploiting the burgeoning fields of genomics, proteomics and metabolomics improves understanding of human physiology and, critically, the mutations that signal disease susceptibility. Through these emerging fields, rational design approaches to diagnosis, drug development and ultimately personalized medicine are possible. Personalized medicine and point-of-care testing techniques must fulfill a host of constraints for real-world applicability. Point-of-care devices (POCDs) must ultimately provide a cost-effective alternative to expensive and time-consuming laboratory tests in order to assist health care personnel with disease diagnosis and treatment decisions. Sensor technologies are also expanding beyond the more traditional classes of biomarkers – nucleic acids and proteins – to metabolites and direct detection of pathogens, ultimately increasing the palette of available techniques for the use of personalized medicine. The technologies needed to perform such diagnostics have also been rapidly evolving, with each generation being increasingly sensitive and selective while being more resource conscious. Ultimately, the final hurdle for all such technologies is to be able to drive consumer adoption and achieve a meaningful medical outcome for the patient.     

The squared distance approach to frequency domain time‐resolved fluorescence analysis

A frequency‐domain (FD) analysis of fluorescence lifetime (FLT) is a unique and rapid method for cellular and intracellular classifications that can serve for medical diagnostics purposes. Nevertheless, its data analysis process demands nonlinear fitting algorithms that may distort the resolution of the FLT data and hence diminish the classification ability of the method. This research suggests a sample classification technique that is unaffected by the analysis process as it is based on the squared distance (D²) between the raw frequency response data (FRD). In addition, it presents the theory behind this technique and its validation in two simulated data sets of six groups with similar widely and closely spaced FLT data as well as in experimental data of 43 samples from bacterial and viral infected and non‐infected patients. In the two simulated tests, the classification accuracy was above 95% for all six groups. In the experimental data, the classification of 41 out of 43 samples matched earlier report and 29 out of 31 agreed with preliminary physician diagnosis. The D² approach has the potential to promote FD‐time resolved fluorescence measurements as a medical diagnostic technique with high specifity and high sensitivity for many of today's conventional diagnostic procedures.      

Cortical and Hippocampal Correlates of Deliberation during Model-Based Decisions for Rewards in Humans

How do we use our memories of the past to guide decisions we''ve never had to make before? Although extensive work describes how the brain learns to repeat rewarded actions, decisions can also be influenced by associations between stimuli or events not directly involving reward — such as when planning routes using a cognitive map or chess moves using predicted countermoves — and these sorts of associations are critical when deciding among novel options. This process is known as model-based decision making. While the learning of environmental relations that might support model-based decisions is well studied, and separately this sort of information has been inferred to impact decisions, there is little evidence concerning the full cycle by which such associations are acquired and drive choices. Of particular interest is whether decisions are directly supported by the same mnemonic systems characterized for relational learning more generally, or instead rely on other, specialized representations. Here, building on our previous work, which isolated dual representations underlying sequential predictive learning, we directly demonstrate that one such representation, encoded by the hippocampal memory system and adjacent cortical structures, supports goal-directed decisions. Using interleaved learning and decision tasks, we monitor predictive learning directly and also trace its influence on decisions for reward. We quantitatively compare the learning processes underlying multiple behavioral and fMRI observables using computational model fits. Across both tasks, a quantitatively consistent learning process explains reaction times, choices, and both expectation- and surprise-related neural activity. The same hippocampal and ventral stream regions engaged in anticipating stimuli during learning are also engaged in proportion to the difficulty of decisions. These results support a role for predictive associations learned by the hippocampal memory system to be recalled during choice formation.     

Doctors accept a challenge: self-assessment exercises in continuing medical education.

A new approach to continuing medical education by distance learning has been implemented. A series of six patient-management problems or challenges were posted to 20 000 doctors throughout Britain. Each doctor had to decide on the diagnosis, investigations, and treatment of the patients described. The challenges covered problems that were important in the doctor''s day-to-day work and were designed so that he could obtain immediate feedback about his decisions and compare his own responses with those of a specialist and those of his colleagues. Additional information was available by telephone and by post on request. The series has been well received and is being widely used.     

Evaluation of optimization techniques for variable selection in logistic regression applied to diagnosis of myocardial infarction

Logistic regression is often used to help make medical decisions with binary outcomes. Here we evaluate the use of several methods for selection of variables in logistic regression. We use a large dataset to predict the diagnosis of myocardial infarction in patients reporting to an emergency room with chest pain. Our results indicate that some of the examined methods are well suited for variable selection in logistic regression and that our model, and our myocardial infarction risk calculator, can be an additional tool to aid physicians in myocardial infarction diagnosis.     

How to reach linguistic consensus: a proof of convergence for the naming game

In this paper we introduce a mathematical model of naming games. Naming games have been widely used within research on the origins and evolution of language. Despite the many interesting empirical results these studies have produced, most of this research lacks a formal elucidating theory. In this paper we show how a population of agents can reach linguistic consensus, i.e. learn to use one common language to communicate with one another. Our approach differs from existing formal work in two important ways: one, we relax the too strong assumption that an agent samples infinitely often during each time interval. This assumption is usually made to guarantee convergence of an empirical learning process to a deterministic dynamical system. Two, we provide a proof that under these new realistic conditions, our model converges to a common language for the entire population of agents. Finally the model is experimentally validated.     

Advances in the diagnosis of infection in prosthetic joint implants

The widespread use and dramatic success of prosthetic joint implant surgery (arthroplasty) has greatly improved the quality of life for many individuals suffering from degenerative, arthritic, or injured joints. However, in a number of cases, recipients experience discomfort at the arthroplasty site that can signal biomechanical failure, or periprosthetic infection of the joint, or both. In fact, infection remains a devastating obstacle, preventing arthroplasty from being an almost perfect medical procedure. Existing tests for the diagnosis of infection in orthopedics are disappointing because of the relatively high frequency of false negative results. To overcome this shortcoming, and to reduce the number of infected revision arthroplasties, a methodology based on molecular biology has been established. The method allows the rapid, sensitive, and accurate diagnosis of orthopedic infections, and should aid the clinician with treatment regimens, surgical decisions, and overall patient management in the growing arthroplasty population.     

Letter to my doctor

Considerable attention is now being given to ethical conflicts raised by such issues as the disclosure of diagnosis and prognosis, the role of the family in making medical decisions, and the withholding or withdrawing of treatment of terminally ill patients. Already complicated, these issues take on added complexity in contexts where medical professionals and patients have differing cultural beliefs and practices. Ethical dilemmas that develop in multicultural settings have been largely unaddressed. Through the analysis of a case involving the hospital admission and death of a Chinese woman with metastatic lung cancer, we examine some of these dilemmas and their effect on the patient, family, and physicians. Many issues were raised by this case regarding the relationships among ethnic background, bioethics, and medical care.     

Exacerbating the Tragedy of the Commons: Private Inefficient Outcomes and Peer Effect in Experimental Games with Fishing Communities

Economic Experimental Games have shown that individuals make decisions that deviate down from the suboptimal Nash equilibrium. However, few studies have analyzed the case when deviation is above the Nash equilibrium. Extracting from above the Nash equilibrium is inefficient not only socially but also privately and it would exacerbate the tragedy of the commons. That would be the case of a race to the fish when stocks are becoming depleted or driver behavior on a highly congested road. The objective of this study is to analyze private inefficient extraction behavior in experimental games and to associate the type of player and the type of player group with such inefficient outcomes. To do this, we carried out economic experimental games with local coastal fishermen in Colombia, using a setting where the scarcity of the resource allows for an interior Nash equilibrium and inefficient over-extraction is possible. The state of the resource, the type of player and the composition of the group explain, in part, this inefficient behavior.     

Evaluation of Public Engagement Activities to Promote Science in a Zoo Environment

Scientists are increasing their efforts to promote public engagement with their science, but the efficacy of the methods used is often not scientifically evaluated. Here, we designed, installed and evaluated the educational impact of interactive games on touchscreens at two primate research centres based in zoo environments. The games were designed to promote interest in and understanding of primates and comparative psychology, as a scaffold towards interest in science more generally and with the intention of targeting younger individuals (under 16''s). We used systematic observational techniques and questionnaires to assess the impact of the games on zoo visitors. The games facilitated increased interest in psychology and science in zoo visitors, and changed the knowledge of visitors, through demonstration of learning about specific scientific findings nested within the games. The impact of such devices was greatest on younger individuals (under 16''s) as they were significantly more likely to engage with the games. On the whole, therefore, this study demonstrates that interactive devices can be successful educational tools, and adds to the growing body of evidence that conducting research on public view in zoos can have a tangible impact on public engagement with science.