A hybrid tabu search algorithm for automatically assigning patients to beds

ObjectiveWe describe a patient admission scheduling algorithm that supports the operational decisions in a hospital. It involves efficiently assigning patients to beds in the appropriate departments, taking into account the medical needs of the patients as well as their preferences, while keeping the number of patients in the different departments balanced.MethodsDue to the combinatorial complexity of the admission scheduling problem, there is a need for an algorithm that intelligently assists the admission scheduler in taking decisions fast. To this end a hybridized tabu search algorithm is developed to tackle the admission scheduling problem. For testing, we use a randomly generated data set. The performance of the algorithm is compared with an integer programming approach.Results and conclusionThe metaheuristic allows flexible modelling and presents feasible solutions even when disrupted by the user at an early stage in the calculation. The integer programming approach is not able to find a solution in 1 h of calculation time.     

Development and empirical user-centered evaluation of semantically-based query recommendation for an electronic health record search engine

ObjectiveThe utility of biomedical information retrieval environments can be severely limited when users lack expertise in constructing effective search queries. To address this issue, we developed a computer-based query recommendation algorithm that suggests semantically interchangeable terms based on an initial user-entered query. In this study, we assessed the value of this approach, which has broad applicability in biomedical information retrieval, by demonstrating its application as part of a search engine that facilitates retrieval of information from electronic health records (EHRs).Materials and MethodsThe query recommendation algorithm utilizes MetaMap to identify medical concepts from search queries and indexed EHR documents. Synonym variants from UMLS are used to expand the concepts along with a synonym set curated from historical EHR search logs. The empirical study involved 33 clinicians and staff who evaluated the system through a set of simulated EHR search tasks. User acceptance was assessed using the widely used technology acceptance model.ResultsThe search engine’s performance was rated consistently higher with the query recommendation feature turned on vs. off. The relevance of computer-recommended search terms was also rated high, and in most cases the participants had not thought of these terms on their own. The questions on perceived usefulness and perceived ease of use received overwhelmingly positive responses. A vast majority of the participants wanted the query recommendation feature to be available to assist in their day-to-day EHR search tasks.Discussion and ConclusionChallenges persist for users to construct effective search queries when retrieving information from biomedical documents including those from EHRs. This study demonstrates that semantically-based query recommendation is a viable solution to addressing this challenge.     

Intervention time prediction from surgical low-level tasks

ObjectiveEffective time and resource management in the operating room requires process information concerning the surgical procedure being performed. A major parameter relevant to the intraoperative process is the remaining intervention time. The work presented here describes an approach for the prediction of the remaining intervention time based on surgical low-level tasks.Materials and methodsA surgical process model optimized for time prediction was designed together with a prediction algorithm. The prediction accuracy was evaluated for two different neurosurgical interventions: discectomy and brain tumor resections. A repeated random sub-sampling validation study was conducted based on 20 recorded discectomies and 40 brain tumor resections.ResultsThe mean absolute error of the remaining intervention time predictions was 13 min 24 s for discectomies and 29 min 20 s for brain tumor removals. The error decreases as the intervention progresses.DiscussionThe approach discussed allows for the on-line prediction of the remaining intervention time based on intraoperative information. The method is able to handle demanding and variable surgical procedures, such as brain tumor resections. A randomized study showed that prediction accuracies are reasonable for various clinical applications.ConclusionThe predictions can be used by the OR staff, the technical infrastructure of the OR, and centralized management. The predictions also support intervention scheduling and resource management when resources are shared among different operating rooms, thereby reducing resource conflicts. The predictions could also contribute to the improvement of surgical workflow and patient care.     

Assessing and comparing the usability of Chinese EHRs used in two Peking University hospitals to EHRs used in the US: A method of RUA

ObjectivesThe objective of this study was to investigate the usability level of Chinese hospital Electronic Health Records (EHRs) by assessing the completion times of EHRs for seven “meaningful use (MU)” relevant tasks conducted at two Chinese tertiary hospitals and comparing the results to those of relevant research conducted in US EHRs.MethodsUsing Rapid Usability Assessment (RUA) developed by the National Center for Cognitive Informatics and Decision Making (NCCD), the usability of EHRs from two Peking University hospitals was assessed using a three-step Keystroke Level Model (KLM) in a laboratory environment.Results(1) The total EHR task completion time for 7 MU relevant test tasks showed no significant differences between the two Chinese EHRs and their US counterparts, in which the time for thinking was relatively large and comprised 35.6% of the total time. The time for the electronic physician order was the largest. (2) For specific tasks, the mean completion times of the 2 hospital EHR systems spent on recording, modifying and searching (RMS) the medication orders were similar to those for the RMS radioactive tests; the mean time spent on the RMS laboratory test orders were much less. (3) There were 85 usability problems identified in the 2 hospital EHR systems.DiscussionIn Chinese EHRs, a substantial amount of time is required to complete tasks relevant to MU targets and many preventable usability problems can be discovered. The task completion time of the 2 Chinese EHR systems was a little shorter than in the 5 reported US EHR systems, while the differences in smoking status and CPOE tasks were obvious; one main reason for these differences was the use of structured data entry.ConclusionsThe efficiency of Chinese and US EHRs was not significantly different. The key to improving the efficiency of both systems lies in expediting the Computerized physician order entry (CPOE) task. Many usability problems can be identified using heuristic assessments and improved by corresponding actions.     

PARAMO: A PARAllel predictive MOdeling platform for healthcare analytic research using electronic health records

ObjectiveHealthcare analytics research increasingly involves the construction of predictive models for disease targets across varying patient cohorts using electronic health records (EHRs). To facilitate this process, it is critical to support a pipeline of tasks: (1) cohort construction, (2) feature construction, (3) cross-validation, (4) feature selection, and (5) classification. To develop an appropriate model, it is necessary to compare and refine models derived from a diversity of cohorts, patient-specific features, and statistical frameworks. The goal of this work is to develop and evaluate a predictive modeling platform that can be used to simplify and expedite this process for health data.MethodsTo support this goal, we developed a PARAllel predictive MOdeling (PARAMO) platform which (1) constructs a dependency graph of tasks from specifications of predictive modeling pipelines, (2) schedules the tasks in a topological ordering of the graph, and (3) executes those tasks in parallel. We implemented this platform using Map-Reduce to enable independent tasks to run in parallel in a cluster computing environment. Different task scheduling preferences are also supported.ResultsWe assess the performance of PARAMO on various workloads using three datasets derived from the EHR systems in place at Geisinger Health System and Vanderbilt University Medical Center and an anonymous longitudinal claims database. We demonstrate significant gains in computational efficiency against a standard approach. In particular, PARAMO can build 800 different models on a 300,000 patient data set in 3 h in parallel compared to 9 days if running sequentially.ConclusionThis work demonstrates that an efficient parallel predictive modeling platform can be developed for EHR data. This platform can facilitate large-scale modeling endeavors and speed-up the research workflow and reuse of health information. This platform is only a first step and provides the foundation for our ultimate goal of building analytic pipelines that are specialized for health data researchers.     

Weighted spherical 1-mean with phase shift and its application in electrocardiogram discord detection

ObjectiveDetecting discords in time series is a special novelty detection task that has found many interesting applications. Unlike the traditional novelty detection methods which can make use of a separate set of normal samples to build up the model, discord detection is often provided with mixed data containing both normal and abnormal data. The objective of this work is to present an effective method to detect discords in unsynchronized periodic time series data.MethodsThe task of discord detection is considered as a problem of unsupervised learning with noise data. A new clustering algorithm named weighted spherical 1-mean with phase shift (PS-WS1M) is proposed in this work. It introduces a phase adjustment procedure into the iterative clustering process and produces a set of anomaly scores based upon which an unsupervised approach is employed to locate the discords automatically. A theoretical analysis on the robustness and convergence of PS-WS1M is also given.ResultsThe proposed algorithm is evaluated via real-world electrocardiograms datasets extracted from the MIT-BIH database. The experimental results show that the proposed algorithm is effective and competitive for the problem of discord detection in periodic time series. Meanwhile, the robustness of PS-WS1M is also experimentally verified. As compared to some of the other discord detection methods, the proposed algorithm can always achieve ideal FScore values with most of which exceeding 0.98.ConclusionThe proposed PS-WS1M algorithm allows the integration of a phase adjustment procedure into the iterative clustering process and it can be successfully applied to detect discords in time series.     

Transcranial direct current stimulation decreased cognition-related reaction time in older adults: A systematic review and meta-analysis

BackgroundThis systematic review and meta-analysis investigated the effects of transcranial direct current stimulation (tDCS) on the cognitive functions of healthy older adults by focusing on the changes in reaction time during cognitive tasks.MethodA total of 31 studies qualified for this meta-analysis, and we acquired 36 comparisons from the included studies for data synthesis. The individual effect sizes were calculated by comparing the altered reaction time during the performance of a specific cognitive task between the active tDCS and sham groups. In two moderator variable analyses, we examined the potentially different effects of the tDCS protocols on the cognition-related reaction time based on the tDCS protocol used (i.e., online vs. offline tDCS) and the five cognitive domains: (a) perceptual-motor function, (b) learning and memory, (c) executive function / complex attention, (d) language, and (e) social cognition. Meta-regression analyses were conducted to estimate the relationship between demographic and tDCS parameter characteristics and the changes in reaction time.ResultsThe random-effects model meta-analysis revealed significant small effects of tDCS on cognition-related reaction time. Specifically, providing online tDCS significantly reduced the reaction time, and these patterns were observed during learning and memory and executive function / complex attention tasks. However, applying offline tDCS failed to find any significant reduction of reaction time across various cognitive tasks. The meta-regression analysis revealed that the effects of tDCS on the reaction time during the performance of cognitive tasks increased for the older people.ConclusionsThese findings suggest that providing online tDCS may effectively improve the ageing-induced reaction time related to specific cognitive functions of elderly people.     

Inflection point analysis: A machine learning approach for extraction of IEGM active intervals during atrial fibrillation

ObjectiveIn this paper, we propose a novel algorithm to extract the active intervals of intracardiac electrograms during atrial fibrillation.MethodsFirst, we show that the characteristics of the signal waveform at its inflection points are prominent features that are implicitly used by human annotators for distinguishing between active and inactive intervals of IEGMs. Then, we show that the natural logarithm of features corresponding to active and inactive intervals exhibits a mixture of two Gaussian distributions in three dimensional feature space. An Expectation Maximization algorithm for Gaussian mixtures is then applied for automatic clustering of the features into two categories.ResultsThe absolute error in onset and offset estimation of active intervals is 6.1 ms and 10.7 ms, respectively, guaranteeing a high resolution. The true positive rate for the proposed method is also 98.1%, proving the high reliability.ConclusionThe proposed method can extract the active intervals of IEGMs during AF with a high accuracy and resolution close to manually annotated results.SignificanceIn contrast with some of the conventional methods, no windowing technique is required in our approach resulting in significantly higher resolution in estimating the onset and offset of active intervals. Furthermore, since the signal characteristics at inflection points are analyzed instead of signal samples, the computational time is significantly low, ensuring the real-time application of our algorithm. The proposed method is also robust to noise and baseline variations thanks to the Laplacian of Gaussian filter employed for extraction of inflection points.     

An optimization based on simulation approach to the patient admission scheduling problem using a linear programing algorithm

BackgroundAs patient’s length of stay in waiting lists increases, governments are looking for strategies to control the problem. Agreements were created with private providers to diminish the workload in the public sector. However, the growth of the private sector is not following the demand for care. Given this context, new management strategies have to be considered in order to minimize patient length of stay in waiting lists while reducing the costs and increasing (or at least maintaining) the quality of care.MethodAppointment scheduling systems are today known to be proficient in the optimization of health care services. Their utilization is focused on increasing the usage of human resources, medical equipment and reducing the patient waiting times. In this paper, a simulation-based optimization approach to the Patient Admission Scheduling Problem is presented. Modeling tools and simulation techniques are used in the optimization of a diagnostic imaging department.ResultsThe proposed techniques have demonstrated to be effective in the evaluation of diagnostic imaging workflows. A simulated annealing algorithm was used to optimize the patient admission sequence towards minimizing the total completion and total waiting of patients. The obtained results showed average reductions of 5% on the total completion and 38% on the patients’ total waiting time.     

Tumor reference resolution and characteristic extraction in radiology reports for liver cancer stage prediction

BackgroundAnaphoric references occur ubiquitously in clinical narrative text. However, the problem, still very much an open challenge, is typically less aggressively focused on in clinical text domain applications. Furthermore, existing research on reference resolution is often conducted disjointly from real-world motivating tasks.ObjectiveIn this paper, we present our machine-learning system that automatically performs reference resolution and a rule-based system to extract tumor characteristics, with component-based and end-to-end evaluations. Specifically, our goal was to build an algorithm that takes in tumor templates and outputs tumor characteristic, e.g. tumor number and largest tumor sizes, necessary for identifying patient liver cancer stage phenotypes.ResultsOur reference resolution system reached a modest performance of 0.66 F1 for the averaged MUC, B-cubed, and CEAF scores for coreference resolution and 0.43 F1 for particularization relations. However, even this modest performance was helpful to increase the automatic tumor characteristics annotation substantially over no reference resolution.ConclusionExperiments revealed the benefit of reference resolution even for relatively simple tumor characteristics variables such as largest tumor size. However we found that different overall variables had different tolerances to reference resolution upstream errors, highlighting the need to characterize systems by end-to-end evaluations.     

Specific healthcare responsibilities and perceived transition readiness among adolescent solid organ transplant recipients: Adolescent and caregiver perspectives

ObjectiveAdolescents and young adults (AYAs) with solid organ transplants must attain responsibility for healthcare tasks during transition to adult healthcare. However, healthcare systems often initiate transfer based on age and not independence in care. This study examines specific responsibilities distinguishing AYA organ transplant recipients reporting readiness to transfer.Methods65 AYAs (ages 12–21) with heart, kidney, or liver transplants and 63 caregivers completed questionnaires assessing AYA’s transition readiness, healthcare responsibility, and executive functioning. Categorizations included mostly/completely ready versus not at all/somewhat ready to transition; responsibility was compared between groups.Results42% of AYAs and 24% of caregivers reported AYAs as mostly/completely ready to transition. AYAs mostly/completely ready reported similar routine healthcare responsibility (e.g., medication taking, appointment attendance), but greater managerial healthcare responsibility (e.g., knowing insurance details, appointment scheduling), compared to AYAs not at all/somewhat ready to transition.ConclusionsAll AYAs should be competent in routine healthcare skills foundational for positive health outcomes. However, the managerial tasks distinguish AYAs perceived as ready to transfer to adult healthcare.Practice implicationsEmphasis on developing responsibility for managerial tasks is warranted. The Hierarchy of Healthcare Transition Readiness Skills is a framework by which AYA responsibility can be gradually increased in preparation for transfer.     

A trial of indication based prescribing of antihypertensive medications during computerized order entry to improve problem list documentation

BackgroundMaintenance of problem lists in electronic medical records is required for the meaningful use incentive and by the Joint Commission. Linking indication with prescribed medications using computerized physician order entry (CPOE) can improve problem list documentation. Prescribing of antihypertensive medications is an excellent target for interventions to improve indication-based prescribing because antihypertensive medications often have multiple indications and are frequently prescribed.ObjectiveTo measure the accuracy and completeness of electronic problem list additions using indication-based prescribing of antihypertensives.DesignClinical decision support (CDS) was implemented so that orders of antihypertensives prompted ordering physicians to select from problem list additions indicated by that medication. An observational analysis of 1000 alerts was performed to determine the accuracy of physicians’ selections.ResultsAt least one accurate problem was placed 57.5% of the time. Inaccurate problems were placed 4.8% of the time. Accuracy was lower in medications with multiple indications and the likelihood of omitted problems was higher compared to medications whose only indication was hypertension. Attending physicians outperformed other clinicians. There was somewhat lower accuracy for inpatients compared to outpatients.ConclusionCDS using indication-based prescribing of antihypertensives produced accurate problem placement roughly two-thirds of time with fewer than 5% inaccurate problems placed. Performance of alerts was sensitive to the number of potential indications of the medication and attendings vs. other clinicians prescribing. Indication-based prescribing during CPOE can be used for problem list maintenance, but requires optimization.     

Discovering metric temporal constraint networks on temporal databases

ObjectiveIn this paper, we propose the ASTPminer algorithm for mining collections of time-stamped sequences to discover frequent temporal patterns, as represented in the simple temporal problem (STP) formalism: a representation of temporal knowledge as a set of event types and a set of metric temporal constraints among them. To focus the mining process, some initial knowledge can be provided by the user, also expressed as an STP, that acts as a seed pattern for the searching procedure. In this manner, the mining algorithm will search for those frequent temporal patterns consistent with the initial knowledge.BackgroundHealth organisations demand, for multiple areas of activity, new computational tools that will obtain new knowledge from huge collections of data. Temporal data mining has arisen as an active research field that provides new algorithms for discovering new temporal knowledge. An important point in defining different proposals is the expressiveness of the resulting temporal knowledge, which is commonly found in the bibliography in a qualitative form.MethodologyASTPminer develops an Apriori-like strategy in an iterative algorithm where, as a result of each iteration i, a set of frequent temporal patterns of size i is found that incorporates three distinctive mechanisms: (1) use of a clustering procedure over distributions of temporal distances between events to recognise similar occurrences as temporal patterns; (2) consistency checking of every combination of temporal patterns, which ensures the soundness of the resultant patterns; and (3) use of seed patterns to allow the user to drive the mining process.ResultsTo validate our proposal, several experiments were conducted over a database of time-stamped sequences obtained from polysomnography tests in patients with sleep apnea–hypopnea syndrome. ASTPminer was able to extract well-known temporal patterns corresponding to different manifestations of the syndrome. Furthermore, the use of seed patterns resulted in a reduction in the size of the search space, which reduced the number of possible patterns from 2.1 × 10⁷ to 1219 and reduced the number of frequent patterns found from 1167 to 340, thereby increasing the efficiency of the mining algorithm.ConclusionsA temporal data mining technique for discovering frequent temporal patterns in collections of time-stamped event sequences is presented. The resulting patterns describe different and distinguishable temporal arrangements among sets of event types in terms of repetitive appearance and similarity of the dispositions between the same events. ASTPminer allows users to participate in the mining process by introducing domain knowledge in the form of a temporal pattern using the STP formalism. This knowledge constrains the search to patterns consistent with the provided pattern and improves the performance of the procedure.     

Caring for individual patients and beyond: enhancing care through secondary use of data in a general practice setting

It is argued that with the introduction of electronic medical record (EMR) systems into the primary care sector, data collected can be used for secondary purposes which extend beyond individual patient care (e.g., for chronic disease management, prevention and clinical performance evaluation). However, EMR systems are primarily designed to support clinical tasks, and data entry practices of clinicians focus on the treatment of individual patients. Hence data collected through EMRs is not always useful in meeting these ends.PurposeIn this paper we follow a community health centre (CHC), and document the changes in work practices of the personnel that were necessary in order to make EMR data useful for secondary purposes.MethodsThis project followed an action research approach, in which ethnographic data were collected mainly by participant observations, by a researcher who also acted as an IT support person for the clinic's secondary usage of EMR data. Additionally, interviews were carried out with the clinical and administrative personnel of the CHC.ResultsThe case study demonstrates that meaningful use of secondary data occurs only after a long process, aimed at creating the pre-conditions for meaningful use of secondary data, has taken place.PreconditionsSpecific areas of focus have to be chosen for secondary data use, and initiatives have to be continuously evaluated and adapted to the workflow through a team approach. Collaboration between IT support and physicians is necessary to tailor the software to allow for the collection of clinically relevant data. Data entry procedures may have to be changed to encourage the usage of an agreed-upon coding scheme, required for meaningful use of secondary data. And finally resources in terms of additional personnel or dedicated time are necessary to keep up with data collection and other tasks required as a pre-condition to secondary use of data, communication of the results to the clinic, and eventual re-evaluation.ConsequencesChanges in the work practices observed in this case which were required to support secondary data use from the EMR included completion of additional tasks by clinical and administrative personnel related to the organization of follow-up tasks. Among physicians increased awareness of specific initiatives and guideline compliance in terms of chronic disease management and prevention was noticed. Finally, the clinic was able to evaluate their own practice and present the results to varied stakeholders.ConclusionsThe case describes the secondary usage of data by a clinic aimed at improving management of the clinic's patients. It illustrates that creating the pre-conditions for secondary use of data from EMRs is a complex process which can be seen as a shift in paradigms from a focus on individual patient care to chronic disease management and performance measurement. More research is needed about how to best support clinics in the process of change management necessitated by emerging clinical management goals.     

Multi-label classification of chronically ill patients with bag of words and supervised dimensionality reduction algorithms

ObjectiveThis research is motivated by the issue of classifying illnesses of chronically ill patients for decision support in clinical settings. Our main objective is to propose multi-label classification of multivariate time series contained in medical records of chronically ill patients, by means of quantization methods, such as bag of words (BoW), and multi-label classification algorithms. Our second objective is to compare supervised dimensionality reduction techniques to state-of-the-art multi-label classification algorithms. The hypothesis is that kernel methods and locality preserving projections make such algorithms good candidates to study multi-label medical time series.MethodsWe combine BoW and supervised dimensionality reduction algorithms to perform multi-label classification on health records of chronically ill patients. The considered algorithms are compared with state-of-the-art multi-label classifiers in two real world datasets. Portavita dataset contains 525 diabetes type 2 (DT2) patients, with co-morbidities of DT2 such as hypertension, dyslipidemia, and microvascular or macrovascular issues. MIMIC II dataset contains 2635 patients affected by thyroid disease, diabetes mellitus, lipoid metabolism disease, fluid electrolyte disease, hypertensive disease, thrombosis, hypotension, chronic obstructive pulmonary disease (COPD), liver disease and kidney disease. The algorithms are evaluated using multi-label evaluation metrics such as hamming loss, one error, coverage, ranking loss, and average precision.ResultsNon-linear dimensionality reduction approaches behave well on medical time series quantized using the BoW algorithm, with results comparable to state-of-the-art multi-label classification algorithms. Chaining the projected features has a positive impact on the performance of the algorithm with respect to pure binary relevance approaches.ConclusionsThe evaluation highlights the feasibility of representing medical health records using the BoW for multi-label classification tasks. The study also highlights that dimensionality reduction algorithms based on kernel methods, locality preserving projections or both are good candidates to deal with multi-label classification tasks in medical time series with many missing values and high label density.