Many Problems In Medicine Research Articles

Recognition of Colon Polyps (Tubular Adenoma, Villous Adenoma) and Normal Colon Epithelium Histomorphology with Transfer Learning.

The use of artificial intelligence technology in medicine, which is remarkable with its increasing use in many areas recently, has allowed for rapid developments. This technology quantitatively solves many problems in medicine, such as increased workload, delayed diagnosis, and treatment processes. It has been seen in the literature that this technology, which has a wide range of applications in medicine, also has a place in medical pathology. The main purpose of this study is to provide a histomorphological classification of colon polyps in the medical pathology department with high accuracy in a short time. Besides accelerating the diagnosis and treatment process, it is desired to facilitate the workload of the pathology department. This study is based on the recognition of colon preparation images that come to the pathology department by using the image recognition techniques of artificial intelligence. VGG19, DenseNet201, and EfcientNetB7 models, which are convolutional neural networks (CNN) models, were used. A model based on a concatenation ensemble of 3 CNN architectures was also used in this study. Within the scope of the study, a total of 515 preparation images, including normal epithelium, tubular adenoma and villous adenomas of the colon, were procured as data and introduced to artificial intelligence, and the diagnoses of these preparations were estimated histomorphologically by artificial intelligence. As a result of the study, an accuracy rate of 94.17% was achieved.

Interpretable Deep Models for Cardiac Resynchronisation Therapy Response Prediction.

Advances in deep learning (DL) have resulted in impressive accuracy in some medical image classification tasks, but often deep models lack interpretability. The ability of these models to explain their decisions is important for fostering clinical trust and facilitating clinical translation. Furthermore, for many problems in medicine there is a wealth of existing clinical knowledge to draw upon, which may be useful in generating explanations, but it is not obvious how this knowledge can be encoded into DL models - most models are learnt either from scratch or using transfer learning from a different domain. In this paper we address both of these issues. We propose a novel DL framework for image-based classification based on a variational autoencoder (VAE). The framework allows prediction of the output of interest from the latent space of the autoencoder, as well as visualisation (in the image domain) of the effects of crossing the decision boundary, thus enhancing the interpretability of the classifier. Our key contribution is that the VAE disentangles the latent space based on 'explanations' drawn from existing clinical knowledge. The framework can predict outputs as well as explanations for these outputs, and also raises the possibility of discovering new biomarkers that are separate (or disentangled) from the existing knowledge. We demonstrate our framework on the problem of predicting response of patients with cardiomyopathy to cardiac resynchronization therapy (CRT) from cine cardiac magnetic resonance images. The sensitivity and specificity of the proposed model on the task of CRT response prediction are 88.43% and 84.39% respectively, and we showcase the potential of our model in enhancing understanding of the factors contributing to CRT response.

An Overview of Strategies Targeting Inappropriate Advanced Diagnostic Imaging in the Setting of Acute Uncomplicated Low Back Pain

The aims of this article are to review the driving forces for increased utilization of imaging within the US and to review the strategies currently being implemented to curtail the use of inappropriate advanced diagnostic imaging (ADI) in the setting of acute uncomplicated low back pain. Strategies aimed at reducing inappropriate ADI in the setting of uncomplicated low back pain, including guideline dissemination, clinical decision support (CDS), audit and feedback, prior authorization, and prior notification. Increasing utilization of inappropriate ADI is a multifactorial problem, and the solution is complex. Like many problems in medicine, it is unlikely that we will be able to identify a single intervention as a solution. Instead, a concerted effort grounded in physician education, CDS, and audit and feedback may be our best tool against inappropriate ADI in the setting of acute uncomplicated low back pain.

Ionic liquids for addressing unmet needs in healthcare.

Advances in the field of ionic liquids have opened new applications beyond their traditional use as solvents into other fields especially healthcare. The broad chemical space, rich with structurally diverse ions, and coupled with the flexibility to form complementary ion pairs enables task‐specific optimization at the molecular level to design ionic liquids for envisioned functions. Consequently, ionic liquids now are tailored as innovative solutions to address many problems in medicine. To date, ionic liquids have been designed to promote dissolution of poorly soluble drugs and disrupt physiological barriers to transport drugs to targeted sites. Also, their antimicrobial activity has been demonstrated and could be exploited to prevent and treat infectious diseases. Metal‐containing ionic liquids have also been designed and offer unique features due to incorporation of metals. Here, we review application‐driven investigations of ionic liquids in medicine with respect to current status and future potential.

Geodesic shape regression with multiple geometries and sparse parameters.

Many problems in medicine are inherently dynamic processes which include the aspect of change over time, such as childhood development, aging, and disease progression. From medical images, numerous geometric structures can be extracted with various representations, such as landmarks, point clouds, curves, and surfaces. Different sources of geometry may characterize different aspects of the anatomy, such as fiber tracts from DTI and subcortical shapes from structural MRI, and therefore require a modeling scheme which can include various shape representations in any combination. In this paper, we present a geodesic regression model in the large deformation (LDDMM) framework applicable to multi-object complexes in a variety of shape representations. Our model decouples the deformation parameters from the specific shape representations, allowing the complexity of the model to reflect the nature of the shape changes, rather than the sampling of the data. As a consequence, the sparse representation of diffeomorphic flow allows for the straightforward embedding of a variety of geometry in different combinations, which all contribute towards the estimation of a single deformation of the ambient space. Additionally, the sparse representation along with the geodesic constraint results in a compact statistical model of shape change by a small number of parameters defined by the user. Experimental validation on multi-object complexes demonstrate robust model estimation across a variety of parameter settings. We further demonstrate the utility of our method to support the analysis of derived shape features, such as volume, and explore shape model extrapolation. Our method is freely available in the software package deformetrica which can be downloaded at www.deformetrica.org.

Discoveries in Physics Can Explain our Thoughts and Acts

A good knowledge of mechanisms of operation of such a complex machine as human brain became urgently demanded for solving many problems in medicine and engineering. Nevertheless, modern metering instruments allow observing only blood flows and activation in certain regions of the brain, whereas the way in which thoughts and acts are formed in it remains a closely guarded secret. In the present article, I used the long-term psychological observation and members of my family, and also results of experiments with the metal conductors covered with various materials and including of bone glue, promoting decrease of resistance to an electric current. The received results allow using discoveries in physics to explain mechanisms of intuition and unconscious behavior; these findings can be probably applied for constructing of devices that would save many human lives. The level of modern engineering may facilitate and accelerate introduction of these appliances in everyday life.

Sports Science vs “Boutique Medicine”

Sports Science vs “Boutique Medicine”

Comments on: Optimization and data mining in medicine

The application of mathematical techniques to biology and in particular to medicine has a long history. In the early days of mathematical biology, mostly dynamical systems’ theory has attracted much attention from many scientific directions that appear in life science and medicine. Moreover, only recently has there been an explosion of interest to mathematical methods in medicine. The genomics revolution and increasing computing power are among other reasons for this dramatic increase of interest in mathematical methods. The amount of literature in mathematical medicine has increased substantially over the last decade. Many problems in medicine can be formulated as an optimization problem. The optimization theory along with the data mining approaches provides efficient techniques for solving many problems in medicine. Optimization and the increasing computing power provide powerful tools to understand complex, nonlinear mechanisms in medicine. Research in mathematical medicine is multidisciplinary and it is across the boundaries of well-established scientific areas such as optimization theory and medicine. In such situations it is important to overcome the cultural and language barriers between mathematicians and medical scientists. The survey paper by Professor Pardalos and his co-authors serves well to this aim. It is well-written and can be easily understood by scientists from both sides. The style of writing of this paper is excellent and a non-mathematical oriented reader will not be turned off from the beginning. Application of optimization methods in medicine is diverse, and it is not possible to cover all areas of applications in one survey paper. Therefore, the authors

History of Medicine

“BY THE HISTORICAL METHOD ALONE,” REMARKED WILLIAM OSLER IN 1901, “can many problems in medicine be approached profitably.” By the time I started medical school, my program had abandoned its history of medicine course for a monthly lecture series. This made sense. Faced with the explosion in knowledge of molecular and clinical science, there was not enough time in the day to study the past. After all, history is not essential to the day-to-day practice of medicine. And, given that physicians used to treat fever with leeches and hysteria with surgery, our history is often embarrassing. Yet I wonder if I would have been better served had I studied history in my preclinical years. Like most physicians, I have used the phrase “the patient is a poor historian.” I wonder if we should more accurately admit that we “took a poor history.” According to one poet, “One might say, though we are told not to, that the patient is a poor historian/We are told instead that we are the historian, and that if/A poor historian is present, he is often wearing scrubs or a stethoscope.” One could argue that patients are never poor historians, only more or less reliable sources of information. It is the role of the physician to be a historian—to collect evidence and weigh competing sources of information against one another. The historical method is part of the craft of medicine. As Sapira puts it, “Simply to write down or to recite a gaggle of true statements is not to compose a history. The facts must be placed in a form that makes them informative. Many medical schools ‘teach’ by having the students memorize a large number of facts. But these schools do not teach the students how to decide what a fact is, or how to collect facts in a useful and informative manner.” The purpose of this issue is to demonstrate the importance of the historical method in understanding current clinical problems. In this issue of MSJAMA, David Schuster reviews the history of the diagnosis of neurasthenia—an illness that reminds us that medical diagnoses are shaped by cultural factors as well as by science. In an account that resonates with our current dilemma over vaccination against bioterrorism threats, Elise Lipkowitz describes the smallpox vaccination debate in 18th-century France. Continuing this discussion on the balance between public health and individual choice, George Joseph tells us about the legacy of the 1905 US Supreme Court case Jacobson v Massachusetts, which upheld the right of the government to order compulsory vaccination. All of these authors teach us something about how to interpret and narrate history.

A control theoretic approach to containing the spread of rabies

Many problems in medicine and biology involve some kind of spatial spread, and quite often the need to control it. A large proportion of medical and biological systems distinguish themselves from those found in engineering by the way the control acts. We illustrate this by considering the specific example of the spread of rabies among foxes. We first give a brief description of a model proposed by Murray et al. (Murray, J. D., Stanley, E. A. & Brown, D. L., Proc. R. Soc. Lond., B 229, 111-150 (1986)), which we extend to include the control mechanism. The problem is to prevent the spread of rabies by vaccinating foxes via the distribution of bait in a region around an observed outbreak. The extended model can be formulated as a nonlinear time-varying control system described by partial differential equations. In contrast to most engineering type control problems, the control does not continuously affect the system but only acts through the initial distributions. We briefly outline a general theory developed for dealing with such nonlinear systems by the use of a fixed point theorem. The problem and the theory are illustrated by some numerical simulations.

Psychophysiology and medicine.

ABSTRACTPsychophysiology is just as closely related to internal medicine as it is to psychiatry. “Psychological variable” has two distinct meanings: a) an external sensory stimulus, or b) an organismic state described in psychological language. “Psychological” and “Physical” are names of two different languages. There is no such thing as a non‐physical illness. Asking whether emotions cause diseases, or diseases cause emotions, leads to many difficulties and is unprofitable. It is far more useful to ask about stimulus‐response relationships. There are more kinds of specificity relations in psychophysiology and psychosomatic medicine than are usually recognized, and the usual specificity statements in psychosomatic medicine are not concerned with I‐R or S‐R specificity. There are many problems in medicine which psychophysiology could help to solve.

Immunological and serological studies on the viruses of fowl-pox and vaccinia

Of the many problems in medicine which still await solution none are of more importance than those connected with the group of diseases now recognised as due to ultra-microscopic viruses. While the study of bacterial diseases has made continuous progress, our knowledge of infections due to ultra-microscopic viruses has remained relatively stationary, as a result of the difficulty in determining the presence of these viruses apart from experiments on the living animal and of the impossibility of cultivating them on artificial media. At the present time it is obvious that fundamental advances can only be made by intensive studies of the more easily accessible viruses, and in the investigations here detailed attention has therefore been concentrated on the virus of fowl-pox, or epithelioma contagiosum, and the virus of vaccinia. The virus of fowl-pox has certain special advantages for an intensive study, in that it occurs in various species of domestic birds, it is filterable, and in addition it belongs to that great group of ultra-microscopic organisms which comprises not only the virus of vaccinia but those also of variola, sheep-, goat- and horsepox. The relationship between the members of this group has been a subject of continued interest since Jenner (1798) described in his classical experiments the protective capacity of the virus of cow-pox against that of variola.

THE BEGINNING OF SYPHILIS

By the historical method alone can many problems in medicine be approached properly. For example, the student who dates his knowledge of tuberculosis from Koch may have a very correct, but a very incomplete, appreciation of the subject. Within a quarter of a century our libraries will have certain alcoves devoted to the historical consideration of the great diseases, which will give to the student that mental perspective which is so valuable an equipment in life. — Osler . The history of syphilis is unique among the records of great diseases. For, unlike most diseases, it does not gradually emerge into the historical records of medicine as its characters become recognized, but appears on the stage of history with a dramatic suddenness in keeping with the tragic reputation it has made—as a great plague sweeping within a few years over the known world. Syphilis is the one disease whose history begins