Search

Much of the knowledge and information needed for enabling high-quality clinical research is stored in free-text format. Natural language processing (NLP) has been used to extract information from these sources at scale for several decades. This paper aims to present a comprehensive review of clinical NLP for the past 15 years in the UK to identify the community, depict its evolution, analyse methodologies and applications, and identify the main barriers. We collect a dataset of clinical NLP projects (n = 94; £ = 41.97 m) funded by UK funders or the European Union's funding programmes. Additionally, we extract details on 9 funders, 137 organisations, 139 persons and 431 research papers. Networks are created from timestamped data interlinking all entities, and network analysis is subsequently applied to generate insights. 431 publications are identified as part of a literature review, of which 107 are eligible for final analysis. Results show, not surprisingly, clinical NLP in the UK has increased substantially in the last 15 years: the total budget in the period of 2019–2022 was 80 times that of 2007–2010. However, the effort is required to deepen areas such as disease (sub-)phenotyping and broaden application domains. There is also a need to improve links between academia and industry and enable deployments in real-world settings for the realisation of clinical NLP's great potential in care delivery. The major barriers include research and development access to hospital data, lack of capable computational resources in the right places, the scarcity of labelled data and barriers to sharing of pretrained models. [ABSTRACT FROM AUTHOR]

Objectives: The objective of this paper was to describe primary care prescribers' perspectives on electronic prescribing drug alerts at the point of prescribing.Design: We used a mixed-method study which included clinician surveys (web-based and paper) and focus groups with prescribers and staff.Participants: Prescribers (n = 157) working in one of 64 practices using 1 of 6 e-prescribing technologies in 6 US states completed the quantitative survey and 276 prescribers and staff participated in focus groups.Measurements: The study measures self-reported frequency of overriding of drug alerts; open-ended responses to: "What do you think of the drug alerts your software generates for you?"Results: More than 40% of prescribers indicated they override drug-drug interactions most of the time or always (range by e-prescribing system, 25% to 50%). Participants indicated that the software and the interaction alerts were beneficial to patient safety and valued seeing drug-drug interactions for medications prescribed by others. However, they noted that alerts are too sensitive and often unnecessary. Participant suggestions included: (1) run drug alerts on an active medication list and (2) allow prescribers to set the threshold for severity of alerts.Conclusions: Primary care prescribers recognize the patient safety value of drug prescribing alerts embedded within electronic prescribing software. Improvements to increase specificity and reduce alert overload are needed. [ABSTRACT FROM AUTHOR]

With the advances in wearable computing and various wireless technologies, there is an increasing trend to outsource body signals from wireless body area network (WBAN) to outside world including cyber space, healthcare big data clouds, etc. Since the environmental and physiological data collected by multimodal sensors have different importance, the provisioning of quality of service (QoS) for the sensory data in WBAN is a critical issue. This paper proposes multiple level-based QoS design at WBAN media access control layer in terms of user level, data level and time level. In the proposed QoS provisioning scheme, different users have different priorities, various sensory data collected by different sensor nodes have different importance, while data priority for the same sensor node varies over time. The experimental results show that the proposed multi-level based QoS provisioning solution in WBAN yields better performance for meeting QoS requirements of personalized healthcare applications while achieving energy saving. [ABSTRACT FROM AUTHOR]

As cloud computing and wearable devices technologies mature, relevant services have grown more and more popular in recent years. The healthcare field is one of the popular services for this technology that adopts wearable devices to sense signals of negative physiological events, and to notify users. The development and implementation of long-term healthcare monitoring that can prevent or quickly respond to the occurrence of disease and accidents present an interesting challenge for computing power and energy limits. This study proposed an adaptive sensor data segments selection method for wearable health care services, and considered the sensing frequency of the various signals from human body, as well as the data transmission among the devices. The healthcare service regulates the sensing frequency of devices by considering the overall cloud computing environment and the sensing variations of wearable health care services. The experimental results show that the proposed service can effectively transmit the sensing data and prolong the overall lifetime of health care services. [ABSTRACT FROM AUTHOR]

Objective: To identify and describe unintended adverse consequences related to clinical workflow when implementing or using computerized provider order entry (CPOE) systems.Methods: We analyzed qualitative data from field observations and formal interviews gathered over a three-year period at five hospitals in three organizations. Five multidisciplinary researchers worked together to identify themes related to the impacts of CPOE systems on clinical workflow.Results: CPOE systems can affect clinical work by 1) introducing or exposing human/computer interaction problems, 2) altering the pace, sequencing, and dynamics of clinical activities, 3) providing only partial support for the work activities of all types of clinical personnel, 4) reducing clinical situation awareness, and 5) poorly reflecting organizational policy and procedure.Conclusions: As CPOE systems evolve, those involved must take care to mitigate the many unintended adverse effects these systems have on clinical workflow. Workflow issues resulting from CPOE can be mitigated by iteratively altering both clinical workflow and the CPOE system until a satisfactory fit is achieved. [ABSTRACT FROM AUTHOR]

Background: Patient-administered computerized questionnaires represent a novel tool to assist primary care physicians in the delivery of preventive health care.Objective: The aim of this study was to assess patient-reported ease of use with a self-administered tablet computer-based questionnaire in routine clinical care.Design: All patients seen in a university-based primary care practice were asked to provide routine screening information using a touch-screen tablet computer-based questionnaire. Patients reported difficulty using the tablet computer after completion of their first questionnaire.Patients: Ten thousand nine hundred ninety-nine patients completed the questionnaire between January 2004 and January 2006.Measurements: We calculated rates of reporting difficulty (no difficulty, some difficulty, or a lot of difficulty) using the tablet computers based on patient age, sex, race, educational attainment, marital status, and number of comorbid medical conditions. We constructed multivariable ordered logistic models to identify predictors of increased self-reported difficulty using the computer.Results: The majority of patients (84%) reported no difficulty using the tablet computers to complete the questionnaire, with only 3% reporting a lot of difficulty. Significant predictors of reporting more difficulty included increasing age [odds ratio (OR) 1.05, 95% confidence interval (CI) 1.05-1.05)]; Asian race (OR 2.3, 95% CI 1.8-2.9); African American race (OR 1.4, 95% CI 1.2-1.6); less than a high school education (OR 3.0, 95% CI 2.6-3.4); and the presence of comorbid medical conditions (1-2: OR 1.3, 95% CI 1.2-1.5; > or =3: OR 1.7 95% CI 1.5-2.1).Conclusions: The majority of primary care patients reported no difficulty using a self-administered tablet computer-based questionnaire. While computerized questionnaires present opportunities to collect routine screening information from patients, attention must be paid to vulnerable groups. [ABSTRACT FROM AUTHOR]