Rich-in-morphology language, such as Russian, present a challenge for extraction of professional medical information. In this paper, we report on our solution to identify adverse events (complications) in neurosurgery based on natural language processing and professional medical judgment. The algorithm we proposed is easily implemented and feasible in a broad spectrum of clinical studies.
We developed a multipurpose scalable electronic informed consent platform (E-Consent) which is reusable for any informed consent in a multitude of settings. The platform allows research staff to easily upload multimedia information about a research protocol with an approved informed consent into the system, which delivers this content interactively for prospective study candidates in a user-friendly way. Consistent with user-centered design, E-Consent underwent usability inspection via cognitive walkthroughs accompanied by surveys that captured task complexity on a 5-point Likert-type scale. The System Usability Scale (SUS) provided a standardized reference for usability and satisfaction. Overall, the E-Consent framework was considered by participants to be easy-to-use, satisfying, and timely, while delivering complex information such as that on a consent form. E-Consent ranked in the top 10th percentile for usability as measured by SUS. This extensible framework successfully delivered complex information and recorded user consents, all in an easy-to-understand and highly usable fashion.
The eStandards methodology stressed the importance of trust and flow for health data as a key characteristic of well-functioning health systems. A digital health compass, leveraging perspectives of health systems, digital health markets, citizens, and workforce, drives a process of co-creation, governance and alignment in eStandards. A repository of best practices and common components further advances interoperability, as new projects add their experience. This paper proposes a governance framework for requirements management, intelligence gathering, specification use, and updates to promote sustainable governance for International Patient Summaries. It is based on interviews of 14 patient summary projects and initiatives in Europe and the United States.
A VR-based application was developed to explore the potential of mobile technology and the use of mobile-VR to assist in treatment, rehabilitation, and prevention of neck injuries. A prototype was developed through user-centered design and Google Sprint. The application simulated a typical set of exercises that a patient would get from a physiotherapist in the case of neck pain. A semi-structured interview was conducted with a physiotherapist, and an open-ended interview followed to asses usability. Expert and user evaluation indicated that the aim should be to keep patients motivated and working through the pain. The usability was judged as very good. However, clinical evaluation with a patient group would be recommended in the future.
The purpose of this study is to investigate views of physicians, nurses and administrative personnel working in Primary Health Care (PHC) structures in the Greek regions of Achaia and Attica, on the usefulness, ease of use, ease of learning and users’ satisfaction of e-prescription and e-appointment systems. The e-prescription and e-appointment systems we evaluated are developed and hosted by the Greek e-Government Center for Social Security Services (IDIKA S.A.). Data were collected by using Likert-scale questionnaires. Overall, users are satisfied, and they find the studied systems useful, easy to use and learn. Ease of learning of both systems scores the highest score, while users’ satisfaction the lowest. Ease of learning of both e-systems is not affected by age, gender, computer skills, and personnel category.
Bedside infotainment technology has been gaining popularity, helping providers to address patient needs and improve hospitalization experience. Such systems have the potential to become valuable tools for medical and nursing personnel, with the integration of patient monitoring features, bolstering efficiency and coordination. Extending their utility beyond conventional monitoring, the incorporation of affective computing capabilities would allow for early detection of potentially dangerous situations, as an individual’s emotional state has a direct effect on their health, cognitive status, behaviour and quality of life. Furthermore, the addition of a serious games module would provide additional value for patients with cognitive decline or mobility issues. This work presents a novel bedside infotainment system, equipped with the aforementioned capabilities and designed to address the needs of patients in long-term care facilities, such as recreation and rehabilitation centres.
During the last years the dependence of inflections have been increased, especially the infection H1N1, in Europe as well as in Greece. Especially the last 2 years (2017–2018) the percentage of spreading is still significant. For the analysis of the impact’s diseases in population during these periods, epidemiological indexes have been introduced.
Electronic health records (EHR) are increasingly being used for observational research at scale. In the UK, we have established the CALIBER research resource which utilizes national primary and hospital EHR data sources and enables researchers to create and validate longitudinal disease phenotypes at scale. In this work, we will describe the core components of the resource and provide results from three exemplar research studies on high-resolution epidemiology, disease risk prediction and subtype discovery which demonstrate both the opportunities and challenges of using EHR for research.
The aim of this study was to evaluate the appropriateness of use of the Emergency Departments (EDs) and to identify the reasons for inappropriate use. A study with 805 patients visiting the EDs of four large-scale public hospitals in Athens was conducted using the Hospital Urgencies Appropriateness Protocol (HUAP). 38.1% of the visits (n=307) were estimated as inappropriate, due to several reasons such as increased confidence in hospital rather than primary care services/patients’ expectation for improved care in EDs (46.6%), convenience/proximity to patient’s residence (44.6%) etc. Ageing, Greek nationality and insurance coverage were related with the appropriate use of EDs (p<0.001, p=0.04 and p=0.005, respectively). The identified distortions must be tackled so as to mitigate ED crowding, waste of resources and increase quality and responsiveness of care.
Conversational agents are being used to help in the screening, assessment, diagnosis, and treatment of common mental health disorders. In this paper, we propose a bootstrapping approach for the development of a digital mental health conversational agent (i.e., chatbot). We start from a basic rule-based expert system and iteratively move towards a more sophisticated platform composed of specialized chatbots each aiming to assess and pre-diagnose a specific mental health disorder using machine learning and natural language processing techniques. During each iteration, user feedback from psychiatrists and patients are incorporated into the iterative design process. A survival of the fittest approach is also used to assess the continuation or removal of a specialized mental health chatbot in each generational design. We anticipate that our unique and novel approach can be used for the development of conversational mental health agents with the ultimate goal of designing a smart chatbot that delivers evidence-based care and contributes to scaling up services while decreasing the pressure on mental health care providers.
Promoter region of protein-coding genes are gradually being well understood, yet no comparable studies exist for the promoter of long non-coding RNA (lncRNA) genes which has emerged as a global potential regulator in multiple cellular process and different diseases for human. To understand the difference in the transcriptional regulation pattern of these genes, previously, we proposed a machine learning based model to classify the promoter of protein-coding genes and lncRNA genes. In this study, we are presenting DeepCNPP (deep coding non-coding promoter predictor), an improved model based on deep learning (DL) framework to classify the promoter of lncRNA genes and protein-coding genes. We used convolution neural network (CNN) based deep network to classify the promoter of these two broad categories of human genes. Our computational model, built upon the sequence information only, was able to classify these two groups of promoters from human at a rate of 83.34% accuracy and outperformed the existing model. Further analysis and interpretation of the output from DeepCNPP architecture will enable us to understand the difference in transcription regulatory pattern for these two groups of genes.
Human genes often, through alternative splicing of pre-messenger RNAs, produce multiple mRNAs and protein isoforms that may have similar or completely different functions. Identification of splice sites is, therefore, crucial to understand the gene structure and variants of mRNA and protein isoforms produced by the primary RNA transcripts. Although many computational methods have been developed to detect the splice sites in humans, this is still substantially a challenging problem and further improvement of the computational model is still foreseeable. Accordingly, we developed DeepDSSR (deep donor splice site recognizer), a novel deep learning based architecture, for predicting human donor splice sites. The proposed method, built upon publicly available and highly imbalanced benchmark dataset, is comparable with the leading deep learning based methods for detecting human donor splice sites. Performance evaluation metrics show that DeepDSSR outperformed the existing deep learning based methods. Future work will improve the predictive capabilities of our model, and we will build a model for the prediction of acceptor splice sites.
Electronic health records usability creates challenges to the delivery of care. This paper presents a novel approach to user analysis. Fixation counts have been analyzed to identify differences among physicians of 3 experience levels – residents, fellows and attending physicians. The findings indicate that users with different training levels had varied experiences while interacting with the same interface. EHRs will always be used by a variety of user groups, each with their own unique characteristics and therefore user analysis must be an important component of EHR usability testing. Eye tracking technology could serve as a valuable tool in this context.
The Electronic Health Record has become a staple today in every hospital and clinic, thanks to policy changes advocating its use. However, its full potential can be realized only when it is easy to use and compliant to the needs of the different user subgroups. This study uses a novel approach of eye tracking to assess and differentiate EHR usability based on gender. Though the findings were not suggestive of a significant gender-based difference, they did indicate that the design and layout of screen elements have a significant influence on the search efficiency for both user groups and this point could be relevant for future EHR design.
Healthcare protocols have been shown to improve the quality of health service delivery by offering explicit guidelines and recommendations for clinicians who are uncertain about how to proceed in a given clinical situation. While various modalities are used to implement protocols, few rigorous evaluations of protocol use exist in low-resource clinical settings. This study aimed to develop mobile-based protocols (MBPs) and test their usability against currently used paper-based protocol (PBPs). Satisfaction, efficiency and effectiveness of the protocols were evaluated through a think-aloud usability exercise, in-depth interviews, and through a questionnaire. Compared to PBPs, satisfaction scores were higher with MBPs (83.8 versus 66.8, p=0.0498), number of errors lower with MBPs (2/25 versus 5/25, p=0.1089), with average time for task completion higher with MBPs (23.3s versus21.6s, p=0.7394). MBPs offer more satisfaction and trend towards being more effective as a dissemination modality for healthcare protocols in low-resource settings.
This paper’s objective is to present a proposed solution of Computer-based Speech Therapy System (CBST) for dyslalia screening. The problem of Speech Sound Disorders (SSD) is enunciated, and a brief presentation of several general CBST solutions is made. An Entropy-based method is proposed and the current state of advancement in the development and experimental validation of this solution is presented and discussed. Conclusions related to future improvements of the method are drawn based on the consequences identified in the final section.
The treatment of multimorbid patients confronts physicians with special challenges. Complex disease correlations, insufficient evidence, lack of interdisciplinary guidelines, limited communication between physicians of different specialties, etc. complicate the treatment. To improve the present care situation for multimorbid patients we describe a development approach for an interdisciplinary Electronic Health Record (EHR). As part of the Dent@Prevent project, which aims to improve the intersectoral care of patients with correlating dental and chronic systemic diseases, the proposed EHR will first be tested in the field of dentistry and general medicine. Based on the HL7 FHIR standard the proposed EHR uses a modern three-tier (client-server) architecture. Crucial element of the EHR is a knowledge base, which comprises components for mapping diseases with their complex correlations, integrates patient reported parameters and classifies information in evidence levels. Using the FHIR standard the described elements need to be transferred into the data schema of FHIR resources. The development of an EHR to improve the treatment of multimorbid patients needs to be tailored to the specific needs of multimorbid patients. An interdisciplinary EHR offers the potential to facilitate communication between patients and physicians and provide them with evidence-based information on disease correlations. The next step is to test the practical implementation and applicability for further interdisciplinary disease correlations.
Purpose: To study the clinical use of a novel patient monitoring dashboard at two Emergency Departments in Denmark in order to evaluate the clinician’s perspective and their use of the dashboard.
Method: Data was gathered by participatory observations of the clinicians’ workflow and dashboard interaction, as well as interviews about the clinicians’ attitudes towards the system. The data collection process took place during the system’s intervention process from September to December 2018.
Result: 65 nurses, 28 physicians and two assistants were observed in total for 62 hours. The 59 hours of the observation was focused on the interaction with the systems. Additionally, 10 nurses and two project nurses were interviewed, giving their statements about the use of the dashboard.
Conclusion: Based on observation, it is concluded that the temporal use of the dashboard is 3 minutes and 10 seconds, out of the 59 hours system interaction. Furthermore, the nurses claimed that they needed further training, as an explanation of the minimal interaction with the system.
Data sharing, information exchange, knowledge acquisition and health intelligence are the basis of an efficient and effective evidence-based decision-making tool. A decentralized blockchain architecture is a flexible solution that can be adapted to institutional and managerial culture of organizations and services. Blockchain can play a fundamental role in enabling data sharing within a network and, to achieve that, this work defines the high-level resources necessary to apply this technology to Tuberculosis related issues. Thus, relying in open-source tools and in a collaborative development approach, we present a proposal of a blockchain based network, the TB Network, to underpin an initiative of sharing of Tuberculosis scientific, operational and epidemiologic data between several stakeholders across Brazilian cities.
Venture Capital (VC) funding raised by companies producing Artificial Intelligence (AI) or Machine Learning (ML) solutions is on the rise and a driver of technology development. In healthcare, VC funding is distributed unevenly and certain technologies have attracted significantly more funding than others have. We analyzed a database of 106 Healthcare AI companies collected from open online sources to understand factors affecting the VC funding of AI companies operating in different areas of healthcare. The results suggest that there is a significant connection between higher funding and having research organizations or pharmaceutical companies as the customer of the product or service. In addition, focusing on AI solutions that are applied to direct patient care delivery is associated with lower funding. We discuss the implications of our findings for public health technology funding institutions.
This cross-sectional research aimed to explore the associated factors with participation in the quality improvement processes in Kalasin hospital, Kalasin province, Thailand. The 412 samples were randomized selection and the created questionnaire was applied to collect their opinion. The results showed that level of participation in quality improvement, which called HA of hospital health professionals at high level (average = 3.52, S.D. = 0.86). In aspect of internal factors of samples, positions and role of responsibility were significantly related with quality improvement. Job motivation and support from the organization were positively correlated with participation of HA activities with statistical significance level. Finding can be suggest that the hospital need to support their staff in aspect of focus on patient, human resources development and patient care process. Including to support and staff encouragement to high level of participant all quality improvement quality.
In 2015, a pediatric endocrinologist designed a progress note in an electronic health record (EHR) system to improve adherence to clinical practice guidelines for pediatric patients with Turner Syndrome. In 2018, to improve upon the note template, a flowsheet containing embedded decision support content from an international guideline was designed and implemented with help from a general pediatrician who was also an Epic Physician Builder. The flowsheet allowed for the creation of discrete data elements for improved consistency and enhanced reporting. The design process may be useful in other EHR customizations.
Low back pain is one of the most common physical symptom and is frequently related with an abnormal body posture. It may be caused by poor upper body and limb coordination; repetitive lifting of heavy objects or poor working are ergonomics. This study analysis the consequence of repetitive heavy lifting on the normal standing posture of factory workers. To asses the posture malformations the Microsoft Kinect sensor was used to obtain postural data from 88 factory workers. The study has shown that more than 90% of the study group has some sort of postural malformation and lower back pain.
Structuring and processing natural language is a growing challenge in the medical field. Researchers are looking for new ways to extract knowledge to create databases and applications to help doctors treat patients and minimize medical errors. A very important part in treating a patient is to provide a fair and effective treatment for diseases. In this article we present a method of extracting important information from medical prospectuses, such as a drug-treated condition, a medicine name, a drug type, etc. To extract these entities, we use Stanford NER Tagger trained for prospectuses in Romanian language. The model was trained and tested with 3 types of medication. For each test, the accuracy of the extracted data was calculated. The extracted medical information is used to create databases with structured information that are useful for decision-support applications to check for or find suggestions for the best treatments.
Noncommunicable diseases (NCDs) are incurable disease, which causes by the risk factors. This study aimed to determine the prevalence and distribution of the risk factors associated according to gender. A cross-sectional survey on Health dataset between October 2013 and April 2017 of people, age 13 years and older about 1,245,462 people, using the high technology and the STEPS approach questionnaire by the WHO. The questions included demographic, behaviour and metabolic. The results found that the prevalence of the risk NCDs were 611,099 people (49.07%) Most risk factors was tobacco use in men (p-value<001), waist in women (p-value<001), having diabetes mellitus family in men (p-value<001), having hypertension family in men (p-value<001), alcohol consumption in men (p-value<001), blood pressure in women (p-value<001), blood sugar level in women (p-value<001), BMI in women (p-value<001), and cholesterol level in women (p-value<001). This data indicates that the prevalence of behaviour needs to be concerning and decision-making to prevention.