Evaluation of the sensitivity of a medical data-mining application to the number of elements in small databases

Data-mining methods can be used to generate rules, or identify patterns, from medical data to assist clinical diagnosis and decision-making. However, in the initial stages of a clinical study on a new diagnostic approach, there could be a limited medical dataset available; or the medical characteristics could mean that the number of patients involved in the study will never be large. Diagnoses made using the rules discovered from such small medical databases should be considered suspect unless a confidence range for a particular diagnosis can be established. A method to evaluate the sensitivity and reliability of data-mining with small databases is presented in this paper. Efron's bootstrap method for statistical testing was used to assess the accuracy of the rules produced during the training step of the data-mining algorithm. The case study for validating this new approach was based on a limited-sized mammographic database previously used to discover associations between the diagnostic features of breast masses in mammograms and the biopsy-based classification of the masses. Using the new approach, it was possible to distinguish between the association rules that were sensitive to the size of the training datasets from those that were not. The methods proposed should lead to an efficient way for validating the patterns discovered in medical data-mining applications using small datasets.     

Dialogic Consensus In Clinical Decision-Making

This paper is predicated on the understanding that clinical encounters between clinicians and patients should be seen primarily as inter-relations among persons and, as such, are necessarily moral encounters. It aims to relocate the discussion to be had in challenging medical decision-making situations, including, for example, as the end of life comes into view, onto a more robust moral philosophical footing than is currently commonplace. In our contemporary era, those making moral decisions must be cognizant of the existence of perspectives other than their own, and be attuned to the demands of inter-subjectivity. Applicable to clinical practice, we propose and justify a Habermasian approach as one useful means of achieving what can be described as dialogic consensus. The Habermasian approach builds around, first, his discourse theory of morality as universalizable to all and, second, communicative action as a cooperative search for truth. It is a concrete way to ground the discourse which must be held in complex medical decision-making situations, in its actual reality. Considerations about the theoretical underpinnings of the application of dialogic consensus to clinical practice, and potential difficulties, are explored.     

Medical images and automated interpretation

The application of automated interpretation to medical images is discussed and the main methods of medical imaging are briefly described. The factors behind the process of human clinical interpretation are also considered. Because human interpretation can be aided by processing of the raw image, the standard methods of image processing are mentioned. Automated interpretation of images in other fields is relevant, and segmentation of images is an important initial part of the process. There are already some applications of automated interpretation of medical images. Some are more complete than others. This will undoubtedly be an important developing field of work which will draw on experience from other areas, and be spurred on by the increasing complexity of medical imaging methods and shortage of expertise for human interpretation.     

Analyse des criteres de choix des materiels et technologies a l'hopital

Decision-making in hospital, when a biomedical instrumentation investment has to be decided, is not simple because of the large amount of criteria which should be considered. To show the most important criteria in decision-making, their respective weight and their interdependencies, we used multi-dimensional analysis methods. A quasi-exhaustive list of criteria has been constructed and sent to all the heads of medical departments, the directors and the clinical engineers of the French university hospitals, in order to obtain their appreciation of the influence of these criteria in their own decision-making experience. The application of factorial analysis methods to the answers gives two main results. There is no characteristic behaviour of professional groups, such as engineers, directors, surgeons, radiologist, etc.… A list of 21 criteria, which are the most influential in decision-making, can be identified. This result will be emphasized in order to develop a tool which allows one to measure the adequacy of a biomedical instrument that shows a clinical need.     

The Representation of Risk in Routine Medical Experience: What Actions for Contemporary Health Policy?

Background

The comprehension of appropriate information about illnesses and treatments, can have beneficial effects on patients’ satisfaction and on important health outcomes. However, it is questionable whether people are able to understand risk properly.

Aim

To describe patients’ representation of risk in common medical experiences by linking such a representation to the concept of trust. A further goal was to test whether the representation of risk in the medical domain is associated to the level of expertise. The third goal was to verify whether socio-demographic differences influence the representation of risk.

Methods

Eighty voluntary participants from 6 health-centers in northern Italy were enrolled to conduct a semi-structured interview which included demographic questions, term-associations about risk representation, closed and open questions about attitudes and perception of risk in the medical context, as well as about medical expertise and trust.

Results

The results showed that people do not have in mind a scientific definition of risk in medicine. Risk is seen as a synonym for surgery and disease and it is often confused with fear. However, general knowledge of medical matters helps people to have a better health management through risk identification and risk information, adoption of careful behaviors and tendency to have a critical view about safety and medical news. Finally, trust proved to be an important variable in risk representation and risk and trust were correlated positively.

Conclusions

People must receive appropriate information about the risks and benefits of treatment, in a form that they can understand and apply to their own circumstances. Moreover, contemporary health policy should empower patients to adopt an active self-care attitude. Methodologies to enhance people’s decision-making outcomes based on better risk communication should be improved in order to enable low literacy population as well elderly people to better understand their treatment and associated risk.     

Acceptance and perceived barriers of implementing a guideline for managing low back in general practice

Background

There is considerable interest today in shared decision-making (SDM), defined as a decision-making process jointly shared by patients and their health care provider. However, the data show that SDM has not been broadly adopted yet. Consequently, the main goal of this proposal is to bring together the resources and the expertise needed to develop an interdisciplinary and international research team on the implementation of SDM in clinical practice using a theory-based dyadic perspective.

Methods

Participants include researchers from Canada, US, UK, and Netherlands, representing medicine, nursing, psychology, community health and epidemiology. In order to develop a collaborative research network that takes advantage of the expertise of the team members, the following research activities are planned: 1) establish networking and on-going communication through internet-based forum, conference calls, and a bi-weekly e-bulletin; 2) hold a two-day workshop with two key experts (one in theoretical underpinnings of behavioral change, and a second in dyadic data analysis), and invite all investigators to present their views on the challenges related to the implementation of SDM in clinical practices; 3) conduct a secondary analyses of existing dyadic datasets to ensure that discussion among team members is grounded in empirical data; 4) build capacity with involvement of graduate students in the workshop and online forum; and 5) elaborate a position paper and an international multi-site study protocol.

Discussion

This study protocol aims to inform researchers, educators, and clinicians interested in improving their understanding of effective strategies to implement shared decision-making in clinical practice using a theory-based dyadic perspective.     

Incorporation of negative rules and evolution of a fuzzy controller for yeast fermentation process

The control of bioprocesses can be very challenging due to the fact that these kinds of processes are highly affected by various sources of uncertainty like the intrinsic behavior of the used microorganisms. Due to the reason that these kinds of process uncertainties are not directly measureable in most cases, the overall control is either done manually because of the experience of the operator or intelligent expert systems are applied, e.g., on the basis of fuzzy logic theory. In the latter case, however, the control concept is mainly represented by using merely positive rules, e.g., “If A then do B”. As this is not straightforward with respect to the semantics of the human decision-making process that also includes negative experience in form of constraints or prohibitions, the incorporation of negative rules for process control based on fuzzy logic is emphasized. In this work, an approach of fuzzy logic control of the yeast propagation process based on a combination of positive and negative rules is presented. The process is guided along a reference trajectory for yeast cell concentration by alternating the process temperature. The incorporation of negative rules leads to a much more stable and accurate control of the process as the root mean squared error of reference trajectory and system response could be reduced by an average of 62.8 % compared to the controller using only positive rules.     

Behavioral and anatomical consequences of early versus late symbol training in macaques

Distinct brain regions, reproducible from one person to the next, are specialized for processing different kinds of human expertise, such as face recognition?and reading. Here, we explore the relationship between age of learning, learning ability, and specialized brain structures. Specifically, we ask whether the existence of reproducible cortical domains necessarily means that certain abilities are innate, or innately easily learned, or whether reproducible domains can be formed, or refined, by interactions between genetic programs and common early experience. Functional MRI showed that intensive early, but not late, experience caused the formation of category-selective regions in macaque temporal lobe for stimuli never naturally encountered by monkeys. And behaviorally, early training produced more fluent processing of these stimuli than the same training in adults. One explanation for these results is that in higher cortical areas, as in early sensory areas, experience drives functional clustering and functional clustering determines how that information is processed.     

Complexity of environment and parsimony of decision rules in insect societies

This paper shows how colonies of social insects process information and solve problems in a complex environment, while keeping some parsimony at the level of the individuals' decision rules. Two studies on ant foraging reveal the diversity of adaptive colony-level patterns that can be generated through self-organization, based on the same individual-level recruitment rules. Regarding prey scavenging, the "ability to retrieve the prey" rule accounts for changes in foraging patterns, with increasing prey size, that show all stages intermediate between an individual and a mass exploitation of food resources. Regarding liquid food foraging, the "ability to ingest a desired volume" rule enables a colony to adjust the number of tending ants to the honeydew production of aphids. In both cases, decision rules are based on intelligent criteria that intrinsically integrate information on multiple variables that are relevant to the ants. Furthermore, the environment can contribute directly to the emergence of collective patterns, independently of any individual behavioral changes. Each environmental factor, including abiotic ones, that alters the dynamics of information transfer in group-living animals should be reconsidered not simply as a constraint but also as a part of the decision-making process and as a agent that shapes the collective pattern.     

From compromise to leadership in pigeon homing

A central problem faced by animals traveling in groups is how navigational decisions by group members are integrated, especially when members cannot assess which individuals are best informed or have conflicting information or interests . Pigeons are now known to recapitulate faithfully their individually distinct habitual routes home , and this provides a novel paradigm for investigating collective decisions during flight under varying levels of interindividual conflict. Using high-precision GPS tracking of pairs of pigeons, we found that if conflict between two birds' directional preferences was small, individuals averaged their routes, whereas if conflict rose over a critical threshold, either the pair split or one of the birds became the leader. Modeling such paired decision-making showed that both outcomes-compromise and leadership-could emerge from the same set of simple behavioral rules. Pairs also navigated more efficiently than did the individuals of which they were composed, even though leadership was not necessarily assumed by the more efficient bird. In the context of mass migration of birds and other animals, our results imply that simple self-organizing rules can produce behaviors that improve accuracy in decision-making and thus benefit individuals traveling in groups .     

Collective Intelligence Meets Medical Decision-Making: The Collective Outperforms the Best Radiologist

While collective intelligence (CI) is a powerful approach to increase decision accuracy, few attempts have been made to unlock its potential in medical decision-making. Here we investigated the performance of three well-known collective intelligence rules (“majority”, “quorum”, and “weighted quorum”) when applied to mammography screening. For any particular mammogram, these rules aggregate the independent assessments of multiple radiologists into a single decision (recall the patient for additional workup or not). We found that, compared to single radiologists, any of these CI-rules both increases true positives (i.e., recalls of patients with cancer) and decreases false positives (i.e., recalls of patients without cancer), thereby overcoming one of the fundamental limitations to decision accuracy that individual radiologists face. Importantly, we find that all CI-rules systematically outperform even the best-performing individual radiologist in the respective group. Our findings demonstrate that CI can be employed to improve mammography screening; similarly, CI may have the potential to improve medical decision-making in a much wider range of contexts, including many areas of diagnostic imaging and, more generally, diagnostic decisions that are based on the subjective interpretation of evidence.     

Do Committees Ru(i)n the Bio‐Political Culture? On the Democratic Legitimacy of Bioethics Committees

Bioethical and bio-political questions are increasingly tackled by committees, councils, and other advisory boards that work on different and often interrelated levels. Research ethics committees work on an institutional or clinical level; local advisory boards deal with biomedical topics on the level of particular political regions; national and international political advisory boards try to answer questions about morally problematic political decisions in medical research and practice. In accordance with the increasing number and importance of committees, the quality of their work and their functional status are being subjected to more and more scrutiny. Besides overall criticism regarding the quality of their work, particular committees giving political advice are often suspected of being incompatible with democratic values, such as respect for affected parties, representation of diverse values and transparency in the decision-making processes. Based on the example of the German National Ethics Council, whose inauguration caused a still ongoing debate on the aims and scopes of committees in general, this paper discusses: (1) the requirements of modern democratic societies in dealing with complex scientific-technical problems; (2) the composition and organisation of committees working as political advisory boards; and (3) the appointment procedures and roles of laymen and experts, and here in particular of ethicists, who may legitimately be taken on by a committee. I will argue that bioethics committees do not necessarily endanger democratic values, but can considerably improve their realisation in democratic decision-making procedures--if, and only if, they do not act as substitutes for parliamentarian processes, but help prepare parliamentarian processes to be organised as rationally as possible.     

Implementation of a Cloud-Based Electronic Medical Record to Reduce Gaps in the HIV Treatment Continuum in Rural Kenya

Background

Electronic medical record (EMR) systems are increasingly being adopted to support the delivery of health care in developing countries and their implementation can help to strengthen pathways of care and close gaps in the HIV treatment cascade by improving access to and use of data to inform clinical and public health decision-making.

Methods

This study implemented a novel cloud-based electronic medical record system in an HIV outpatient setting in Western Kenya and evaluated its impact on reducing gaps in the HIV treatment continuum including missing data and patient eligibility for ART. The impact of the system was assessed using a two-sample test of proportions pre- and post-implementation of EMR-based data verification and clinical decision support.

Results

Significant improvements in data quality and provision of clinical care were recorded through implementation of the EMR system, helping to ensure patients who are eligible for HIV treatment receive it early. A total of 2,169 and 764 patient records had missing data pre-implementation and post-implementation of EMR-based data verification and clinical decision support respectively. A total of 1,346 patients were eligible for ART, but not yet started on ART, pre-implementation compared to 270 patients pre-implementation.

Conclusion

EMR-based data verification and clinical decision support can reduce gaps in HIV care, including missing data and eligibility for ART. A cloud-based model of EMR implementation removes the need for local clinic infrastructure and has the potential to enhance data sharing at different levels of health care to inform clinical and public health decision-making. A number of issues, including data management and patient confidentiality, must be considered but significant improvements in data quality and provision of clinical care are recorded through implementation of this EMR model.     

Selling research, and it pays

While conceding that time has proven him wrong in doubting public acceptance of the idea of the "science shops," first sponsored by the Free University of Amsterdam to provide access to technical expertise for customers who could not afford more orthodox services, the author remains convinced that the somewhat analogous concept of "fee for service research," which offers experimental medical treatments for those who can afford to pay for them, is wrong. Such research has been justified as a private sector enterprise that provides patients who are unresponsive to standard forms of therapy with scientifically sound experimental options. However, the objections that such work might be kept secret and not contribute to medical knowledge, and that therapy would be available only to the rich, remain unanswered and pose an insurmountable obstacle to the support of this idea.     

Rules for the use of model organisms in anti-aging pharmacology

The use of animal models for initially screening anti-aging drugs is a promising approach for drug discovery. However, there a number of potential artifacts, confounds and errors that can arise in such research programs. The following rules are intended to minimize such problems: (1) since aging occupies an increasing proportion of human adulthood, data that conflate aging and late life should not be extrapolated to human aging; (2) the response to candidate medications should show a normal dose-response pattern, although not necessarily a linear response; (3) medicated animal models should not be hypometabolic; (4) medicated animal models should not show pronounced reductions in fertility; (5) medicated animal models should not exhibit general nervous system depression; (6) the effect of the medication should not be highly sensitive to the culture environment; (7) the effect of the medication should not be highly dependent on the genetic ancestry of the stock employed, leaving aside inbreeding, which should be avoided because humans are not generally inbred. While these rules do not guarantee successful extrapolation of successful drug results from the animal model to humans in a clinical setting, the failure to adhere to these rules should raise doubts about such extrapolation.     

Expert systems in treating substance abuse.

Computer programs can assist humans in solving complex problems that cannot be solved by traditional computational techniques using mathematic formulas. These programs, or "expert systems," are commonly used in finance, engineering, and computer design. Although not routinely used in medicine at present, medical expert systems have been developed to assist physicians in solving many kinds of medical problems that traditionally require consultation from a physician specialist. No expert systems are available specifically for drug abuse treatment, but at least one is under development. Where access to a physician specialist in substance abuse is not available for consultation, this expert system will extend specialized substance abuse treatment expertise to nonspecialists. Medical expert systems are a developing technologic tool that can assist physicians in practicing better medicine.     

Reflections in art

When artists depict a mirror in a painting, it necessarily lacks the most obvious property of a mirror: as we move around the painting of the mirror, the reflections we see in it do not change. And yet representations of mirrors and other reflecting surfaces can be quite convincing in paintings. Here, we will examine the rules of reflection, the many ways that painters can break those rules without losing the impression of reflection and the rules that cannot be broken. The rules that govern the perception of reflection are a small subset of the physical rules of reflection.     

"Actually, I don't feel that bad": managing diabetes and the clinical encounter

A major issue for persons treating and managing adult-onset diabetes (NIDDM) is the "problem of compliance." I consider the clinical encounter in the overall context of diabetes management as a punctuated experience focused on the cultivation of an ideal self whose "technologies" and "ethics of self-care" mimic a capitalist logic that links self-discipline, productivity, and health. Both clinicians and their patients share and identify with many of the cultural referents and social values that circulate through medical advice and practice. However, using individual examples, I show how this shared logic can produce idiosyncratic regimes of self-care and clinical practice that result in hybrid medical practices incorporating differing objectives and emphases concerned with a tolerable present or an ideal future. Rather than organizing principles for research and medical practice, I suggest that medical compliance and noncompliance should be considered part of the rhetoric to be explained within the regimes of a pursuit of health.     

The Futility of Futility: Death Causation is the ��Elephant in the Room�� in Discussions about Limitation of Medical Treatment

The term “futility” has been widely used in medical ethics and clinical medicine for more than twenty years now. At first glance it appears to offer a clear-cut categorical characterisation of medical treatments at the end of life, and an apparently objective way of making decisions that are seen to be emotionally painful for those close to the patient, and ethically, and also potentially legally hazardous for clinicians. It also appears to deal with causation, because omission of a futile treatment cannot surely be a cause of death. The problem is that futility can be argued to be a “false friend”, in that it gives an appearance of representing a reliable conceptual basis, in ethics, for limitation of medical treatment—usually in the context of dying—without actually doing so. In fact, the concept of futility is a conflation of clinical judgement about outcomes of treatment and the quality or even value of life, and has really failed to contribute much to the advancement of decision-making and hence care at the end-of-life. It also has the capacity to medicalise the personal space. Deliberations about the likely outcomes of medical treatment are necessary, and medical expertise is pivotal. However, futility is argued to have a better future in partnership with a broad social action agenda about the process of dying, such as that articulated in health promoting palliative care, as a basis for better “death-ways” in the 21st century (Kellehear 2005). Medicine needs to more honest and upfront about its limits, as death is, after all, the elephant in everybody's room.