Interoperable metadata is key for the management of genomic information. We propose a flexible approach that we contribute to the standardization by ISO/IEC of a new format for efficient and secure compressed storage and transmission of genomic information.
Changes in healthcare delivery needs have necessitated the design of new models for connecting providers and consumers of services. While healthcare delivery has traditionally been a push market, multi-sided markets offer the potential for transitioning to a pull market for service delivery. However, there is a need to better understand the business model for multi-sided markets as a first step to using them in healthcare. This paper addressed that need and describes a multi-sided market evaluation framework. Our framework identifies patient, governance and service delivery as three levels of brokerage consideration for evaluating multi-sided markets in healthcare.
The shoulder's range of motion (ROM) is an important measurement for the diagnostic process and course of treatment for patients with shoulder disorders or injuries. Visual estimation to assess a shoulder's ROM is a fast measuring method, and therefore routinely used in clinical practice. Studies already proved this method as very subjective and unreliable. Misestimating the severity of a patient's disability can lead to improper treatment and should be avoided. Modern technology may help measuring the ROM more reliable, objective, non-invasive and still fast. In this paper we present a computer-based prototype to semi-automatically assess the patient's shoulder ROM. Still photography is one of the most accurate ways to determine the extent to which a shoulder can be moved. Thus, a marker-less motion sensing device is used to capture movements of patient. A study with n=9 healthy adults was conducted to validate the results of the computer-based system against a physician using goniometry. The results show great potential of this technique for abduction, adduction, anteversion and retroversion with an intraclass correlation coefficient ranging between 0.77 and 0.86 for the best measuring method. Using the system would enhance daily practice. Patients could measure their ROM during their waiting time in advance to the visit, optionally supported by a nurse. Due to the more reliable and objective result the physician can instantly start diagnosing the patient or discussing therapy options. Time for investigation is saved and more time to treat the patient with objective and reliable measurement results would be available.
Blockchain technology is often considered as the fourth industrial revolution that will change the world. The enthusiasm of the transformative nature of blockchain technology has infiltrated healthcare. Blockchain is often seen as the much needed and perfect technology for healthcare, addressing the difficult and complex issues of security and inter-operability. More importantly, the “value” and trust-based system can deliver automated action and response via its smart contract mechanism. Healthcare, however, is a complex system. Health information technology (HIT) so far, has not delivered its promise of transforming healthcare due to its complex socio-technical and context sensitive interaction. The introduction of blockchain technology will need to consider a whole range of socio-technical issues in order to improve the quality and safety of patient care. This paper presents a discussion on these socio-technical issues. More importantly, this paper argues that in order to achieve the best outcome from blockchain technology, there is a need to consider a clinical transformation from “information” to “value “ and trust. This paper argues that urgent research is needed to address these socio-technical issues in order to facilitate best outcomes for blockchain in healthcare. These socio-technical issues must then be further evaluated by means of working prototypes in the medical domain in coming years.
Detecting early signs of dementia in everyday situations becomes more and more important in a rapidly aging society. Language dysfunctions are recognized as the prominent signs of dementia. Previous computational studies characterized these language dysfunctions by using acoustic and linguistic features for detecting dementia. However, they mainly investigated language dysfunctions collected from patients during neuropsychological tests. Language dysfunctions observed during regular conversations in everyday situations received little attention. One of the dysfunctions associated with dementia which is frequently observed in regular conversations is the repetition of a topic on different days. In this study, we propose a feature to characterize topic repetition in conversations on different days. We used conversational data obtained from a daily monitoring service of eight elderly people, two of whom had dementia. Through the analysis of topic extraction with latent Dirichlet allocation, we found that the frequency of topic repetition was significantly higher in people with dementia than in the control group. The results suggest that our proposed feature for identifying topic repetition in regular conversations on different days might be used for detecting dementia.
In this study, we assessed the reliability of using a tablet application for collecting health data among older adults, in comparison to using paper surveys for this goal. Test-retest reliability between the two modalities, usability, user experience factors, and older adults' preference were determined. The results show perfect agreement between tablet and paper for the SARC-F and high agreement for the SF-36 physical scale and EQ-5D. Usability and user experience factors were perceived the same for both modalities. The majority of the participants preferred the tablet for health screening purposes, mainly because of its ease of use. This study shows that using tablets for health screenings among older adults does not affect test reliability, and that older adults prefer the tablet to paper for completing these tests.
We are well into the 21st century and the Internet has been around long enough that there are adults who have not known a world without this wonderful tool. And just as time has gone since the beginnings of the Internet, so too has it developed, probably above and beyond the wildest dreams of its founders. These developments, though mostly positive, also have their share of the not so positive. One of these challenges is the difficulty in maintaining accuracy and quality of all the information, data gathered, aggregated or automatically generated being displayed on the Internet on Web websites or via mobile application, and this is a concern in the health domain. In this paper, we attempt to discuss in detail, some of the latest developments along with the challenges each of them entail and proposed Code of Conduct for health apps and connected objects.
Traditional Chinese Medicine utilization has rapidly increased worldwide. However, there is limited database provides the information of TCM herbs and diseases. The study aims to identify and evaluate the meaningful associations between TCM herbs and breast cancer by using the association rule mining (ARM) techniques. We employed the ARM techniques for 19.9 million TCM prescriptions by using Taiwan National Health Insurance claim database from 1999 to 2013. 364 TCM herbs-breast cancer associations were derived from those prescriptions and were then filtered by their support of 20. Resulting of 296 associations were evaluated by comparing to a gold-standard that was curated information from Chinese-Wikipedia with the following terms, cancer, tumor, malignant. All 14 TCM herbs-breast cancer associations with their confidence of 1% were valid when compared to gold-standard. For other confidences, the statistical results showed consistently with high precisions. We thus succeed to identify the TCM herbs-breast cancer associations with useful techniques.
Organised repositories of published scientific literature represent a rich source for research in knowledge representation. MEDLINE, one of the largest and most popular biomedical literature databases, provides metadata for over 24 million articles each of which is indexed using the MeSH controlled vocabulary. In order to reuse MeSH annotations for knowledge construction, we processed this data and extracted the most relevant patterns of assigned descriptors over time. The patterns consist of UMLS semantic groups related to the MeSH headings together with their associated MeSH subheadings. Then, we connected the patterns with the most frequent predicates in their corresponding MEDLINE abstracts. Thereafter, we conducted a time series analysis of the extracted patterns from MEDLINE records and their associated predicates in order to study the evolution of manual MeSH indexing. The results show an increasing diversity of the assigned MESH terms over time, along with the increase of scientific publication per year. We obtained evidence of consistency of the relevant predicates associated with the extracted patterns. Moreover, for the most frequent patterns some predicates predominate over others such as Treats between substances and disorders, Causes between pairs of disorders, or Interacts between pairs of substances.
Associations between dental and chronic-systemic diseases were observed frequently in medical research, however the findings of this research have so far found little relevance in everyday clinical treatment. Major problems are the assessment of evidence for correlations between such diseases and how to integrate current medical knowledge into the intersectoral care of dentists and general practitioners. On the example of dental and chronic-systemic diseases, the Dent@Prevent project develops an interdisciplinary decision support system (DSS), which provides the specialists with information relevant for the treatment of such cases. To provide the physicians with relevant medical knowledge, a mixed-methods approach is developed to acquire the knowledge in an evidence-oriented way. This procedure includes a literature review, routine data analyses, focus groups of dentists and general practitioners as well as the identification and integration of applicable guidelines and Patient Reported Measures (PRMs) into the treatment process. The developed mixed methods approach for an evidence-oriented knowledge acquisition indicates to be applicable and supportable for interdisciplinary projects. It can raise the systematic quality of the knowledge-acquisition process and can be applicable for an evidence-based system development. Further research is necessary to assess the impact on patient care and to evaluate possible applicability in other interdisciplinary areas.
The Arden Syntax for Medical Logic Systems is a standard for encoding and sharing knowledge in the form of Medical Logic Modules (MLMs). Although the Arden Syntax has been designed to meet the requirements of data-driven clinical event monitoring, multiple studies suggest that its language constructs may be suitable for use outside the intended application area and even as a common clinical application language. Such a broader context, however, requires to reconsider some language features. The purpose of this paper is to outline the related modifications on the basis of a generalized Arden Syntax version. The implemented prototype provides multiple adjustments to the standard, such as an option to use programming language constructs without the frame-like MLM structure, a JSON compliant data type system, a means to use MLMs as user-defined functions, and native support of restful web services with integrated data mapping. This study does not aim to promote an actually new language, but a more generic version of the proven Arden Syntax standard. Such an easy-to-understand domain-specific language for common clinical applications might cover multiple additional medical subdomains and serve as a lingua franca for arbitrary clinical algorithms, therefore avoiding a patchwork of multiple all-purpose languages between, and even within, institutions.
This paper describes our approach to construct a scalable system for unsupervised information extraction from the behaviour change intervention literature. Due to the many different types of attribute to be extracted, we adopt a passage retrieval based framework that provides the most likely value for an attribute. Our proposed method is capable of addressing variable length passage sizes and different validation criteria for the extracted values corresponding to each attribute to be found. We evaluate our approach by constructing a manually annotated ground-truth from a set of 50 research papers with reported studies on smoking cessation.
Researchers tested the functionality, and evaluated the feasibility of a telemedicine software, Doxy.me, to complete informed teleconsent sessions remotely with prospective research participants. Twenty healthy volunteers completed a teleconsent session, and web survey assessing overall experience and satisfaction with the Doxy.me software. There was a statistically significant correlation found between age and mean response for the overall reaction category (r = 0.398, p = 0.091) and the systems capabilities category (r = 0.380, p = 0.099). Results suggested that younger users are more satisfied than older users with using teleconsent as a modality for informed consenting. This information will be used to improve the software design and functionality of the Doxy.me software to make the teleconsent experience as simple and intuitive as possible.
Health information and communication technologies such as telemedicine provide alternatives for patient and physician communication. An increasing number of patients, providers and institutions are using this technologies to seek or provide health care. Asynchronous consultations requires a service of storing and forwarding health related information by the patient to the specialist physician or other healthcare provider. Dermatology is one of the major medical specialties in which telemedicine as proven benefits. There are many described deployments of asynchronous teleconsultation for dermatology, but in most cases telemedicine applications work as stand alone solutions. The present work describes the design and deployment of an asynchronous dermatological teleconsultation service which uses the interaction of the Electronic Health Record and the Personal Health Record in a high complexity university hospital.
Addiction treatment outcomes are strongly determined by relational factors. We present the interactive documentation system Tele-Board MED (TBM) developed as an adjunct to therapy sessions aimed at enhancing the therapeutic alliance and patient empowerment. The objective of this work is to find factors that predict the acceptance of TBM in face-to-face addiction treatment sessions. We combined the methodologies of survey and focus group and based the data collection and analysis on the Unified Theory of Acceptance and Use of Technology. The studies, which involved therapists (n=13) and clients (n=33), were conducted in an addiction counselling center in Germany. Therapists see a flexible, context-dependent usage as a basic condition for TBM acceptance and its greatest benefit in providing a discussion framework and quick access to worksheets—in both individual and group sessions. Clients are inclined to use the system with the expectation of improved communication and better recall of the discussed topics based on a personal copy of the session notes.
The International Patient Summary (IPS) standards aim to define the specifications for a minimal and non-exhaustive Patient Summary, which is specialty-agnostic and condition-independent, but still clinically relevant. Meanwhile, health systems are developing and implementing their own variation of a patient summary while, the eHealth Digital Services Infrastructure (eHDSI) initiative is deploying patient summary services across countries in the Europe. In the spirit of co-creation, flexible governance, and continuous alignment advocated by eStandards, the Trillum-II initiative promotes adoption of the patient summary by engaging standards organizations, and interoperability practitioners in a community of practice for digital health to share best practices, tools, data, specifications, and experiences. This paper compares operational aspects of patient summaries in 14 case studies in Europe, the United States, and across the world, focusing on how patient summary components are used in practice, to promote alignment and joint understanding that will improve quality of standards and lower costs of interoperability.
In this work we analyze the syntactic complexity of transcribed Swedish-language picture descriptions using a variety of automated syntactic features, and investigate the features' predictive power in classifying narratives from people with subjective and mild cognitive impairment and healthy controls. Our results indicate that while there are no statistically significant differences, syntactic features can still be moderately successful at distinguishing the participant groups when used in a machine learning framework.
Medical data is multimodal. In particular, it is composed of both structured data and narrative data (free text). Narrative data is a type of unstructured data that, although containing valuable semantic and conceptual information, is rarely reused. In order to assure interoperability of medical data, automatic annotation of free text with SNOMED CT concepts via Natural Language Processing (NLP) tools is proposed. This task is performed using a hybrid multilingual syntactic parser. A preliminary evaluation of the annotation shows encouraging results and confirms that semantic enrichment of patient-related narratives can be accomplished by hybrid NLP systems, heavily based on syntax and lexicosemantic resources.
Medical reports often contain a lot of relevant information in the form of free text. To reuse these unstructured texts for biomedical research, it is important to extract structured data from them. In this work, we adapted a previously developed information extraction system to the oncology domain, to process a set of anatomic pathology reports in the Italian language. The information extraction system relies on a domain ontology, which was adapted and refined in an iterative way. The final output was evaluated by a domain expert, with promising results.
The online patient question and answering (Q&A) system attracts an increasing amount of users in China. Patient will post their questions and wait for doctors' response. To avoid the lag time involved with the waiting and to reduce the workload on the doctors, a better method is to automatically retrieve the semantically equivalent question from the archive. We present a Generative Adversarial Networks (GAN) based approach to automatically retrieve patient question. We apply supervised deep learning based approaches to determine the similarity between patient questions. Then a GAN framework is used to fine-tune the pre-trained deep learning models. The experiment results show that fine-tuning by GAN can improve the performance.
We report on the development and evaluation of a prototype tool aimed to assist laymen/patients in understanding the content of clinical narratives. The tool relies largely on unsupervised machine learning applied to two large corpora of unlabeled text – a clinical corpus and a general domain corpus. A joint semantic word-space model is created for the purpose of extracting easier to understand alternatives for words considered difficult to understand by laymen. Two domain experts evaluate the tool and inter-rater agreement is calculated. When having the tool suggest ten alternatives to each difficult word, it suggests acceptable lay words for 55.51% of them. This and future manual evaluation will serve to further improve performance, where also supervised machine learning will be used.
Exchanges between diabetic patients on discussion fora permit to study their understanding of their disorder, their behavior and needs when facing health problems. When analyzing these exchanges and behavior, it is necessary to collect information on user profile. We present an approach combining lexicon and super-vised classifiers for the identification of age and gender of contributors, their disorders and relation between contributor and patient. According to parameters of the method, precision is between 100% for gender and 53.48% for disorders.
The prevention of cardiovascular diseases needs first to quantify the cardiovascular risk. To estimate this risk, French national health authorities provided clinical practice guidelines extending the existing European SCORE, which doesn't include all the cardiovascular risk factors (e.g. diabetes). Hence, French national clinical practice guidelines to quantify the cardiovascular risk is able to deal with more clinical situations than the SCORE. The goal of this paper is to formalize knowledge extracted from these guidelines and implement the rules so that they can be used into an auto-assessing tool of cardiovascular risk. Formalization followed five steps and was conducted under the guidance of medical experts. It resulted into a decision tree fed by eight decision variables. Evaluation of the accuracy of the decision tree showed 80% of agreement with an expert in medical informatics in predicting the cardiovascular risk level for 15 different clinical situations. Discrepancies correspond to the knowledge gaps within Clinical Practice Guidelines. We intend to extend the implementation of the decision tree to a complete tool, for allowing patient to auto-assess their cardiovascular risk. This tool will be integrated into a platform providing recommendations adapted to the calculated level of cardiovascular risk.
Bayesian Networks (BNs) are often used for designing diagnosis decision support systems. They are a well-established method for reasoning under uncertainty and making inferences. But, eliciting the probabilities can be tedious and time-consuming especially in medical domain where variables are often related by qualitative terms rather than probabilities. The goal of this paper is to propose a method for eliciting the probabilities required in BNs by using and transforming causal rules which are often used in medicine. The method consists in first constructing the structure of BNs by reporting medical expert's knowledge in the form of causal rules, and then constructing the parameters of the BNs by transforming the terms used for qualified causal rules into probabilities. Example is given in obesity domain. Further works are needed to reinforce our method like the consideration of circular causal rules.