Search

The demand for medical services has been increasing yearly in aging countries. Medical institutions must hire a large number of staff members to provide efficient and effective health-care services. Because of high workload and pressure, high turnover rates exist among health-care staff members, especially those in nonurban areas, which are characterized by limited resources and a predominance of elderly people. Turnover in health-care institutions is influenced by complex factors, and high turnover rates result in considerable direct and indirect costs for such institutions (Lo and Tseng 2019). Therefore, health-care institutions must adopt appropriate strategies for talent retention. Because institutions cannot determine the most effective talent retention strategy, many of them simply passively adopt a single human resource (HR) policy and make minor adjustments to the selected policy. In the present study, system dynamics modeling was combined with fuzzy multiobjective programming to develop a method for simulating HR planning systems and evaluating the suitability of different HR policies in an institution. We also considered the external insurance policy to be the parameter for the developed multiobjective decision-making model. The simulation results indicated that reducing the turnover rate of new employees in their trial period is the most effective policy for talent retention. The developed procedure is more efficient, effective, and cheaper than the traditional trial-and-error approaches for HR policy selection.

Online review helpfulness prediction is an important research issue in electronic commerce and data mining. However, the collected datasets used for the analysis and prediction of the helpfulness o...

Bankruptcy prediction and credit scoring are major problems in financial distress prediction. Studies have shown that prediction models can be made more effective by performing data preprocessing procedures. Moreover, classifier ensembles are likely to outperform single classifiers. Although feature selection, instance selection, and classifier ensembles are known to affect final prediction results, their combined effects on bankruptcy prediction and credit scoring problems have not been fully explored. This study compares the performance of three feature selection algorithms, three instance selection algorithms, four classification algorithms, and two ensemble learning techniques. The results obtained using five bankruptcy prediction and five credit scoring datasets indicate that by carefully considering the combination of these three factors, better prediction models can be developed than by considering only one related factor.

Opinion mining focuses on extracting polarity information from texts. For textual term representation, different feature selection methods, e.g. term frequency (TF) or term frequency–inverse document frequency (TF–IDF), can yield diverse numbers of text features. In text classification, however, a selected training set may contain noisy documents (or outliers), which can degrade the classification performance. To solve this problem, instance selection can be adopted to filter out unrepresentative training documents. Therefore, this article investigates the opinion mining performance associated with feature and instance selection steps simultaneously. Two combination processes based on performing feature selection and instance selection in different orders, were compared. Specifically, two feature selection methods, namely TF and TF–IDF, and two instance selection methods, namely DROP3 and IB3, were employed for comparison. The experimental results by using three Twitter datasets to develop sentiment classifiers showed that TF–IDF followed by DROP3 performs the best.

Falls are one of the most common accidents among inpatients and may result in extended hospitalization and increased medical costs. Constructing a highly accurate fall prediction model could effectively reduce the rate of patient falls, further reducing unnecessary medical costs and patient injury. This study applied data mining techniques on a hospital's electronic medical records database comprising a nursing information system to construct inpatient-fall-prediction models for use during various stages of inpatient care. The inpatient data were collected from 15 inpatient wards. To develop timely and effective fall prediction models for inpatients, we retrieved the data of multiple-time assessment variables at four points during hospitalization. This study used various supervised machine learning algorithms to build classification models. Four supervised learning and two classifier ensemble techniques were selected for model development. The results indicated that Bagging+RF classifiers yielded optimal prediction performance at all four points during hospitalization. This study suggests that nursing personnel should be aware of patients' risk factors based on comprehensive fall risk assessment and provide patients with individualized fall prevention interventions to reduce inpatient fall rates.

Ischemic stroke is a major cause of death and disability in adulthood worldwide. Because it has highly heterogeneous phenotypes, phenotyping of ischemic stroke is an essential task for medical research and clinical prognostication. However, this task is not a trivial one when the study population is large. Phenotyping of ischemic stroke depends primarily on manual annotation of medical records in previous studies. This article evaluated various strategies for automated phenotyping of ischemic stroke into the four subtypes of the Oxfordshire Community Stroke Project classification based on structured and unstructured data from electronical medical records (EMRs). A total of 4640 adult patients who were hospitalized for acute ischemic stroke in a teaching hospital were included. In addition to the structured items in the National Institutes of Health Stroke Scale, unstructured clinical narratives were preprocessed using MetaMap to identify medical concepts, which were then encoded into feature vectors. Various supervised machine learning algorithms were used to build classifiers. The study results indicate that textual information from EMRs could facilitate phenotyping of ischemic stroke when this information was combined with structured information. Furthermore, decomposition of this multi-class problem into binary classification tasks followed by aggregation of classification results could improve the performance.

Based on multigap loop (MGL) antenna and low-noise norm detector, a novel nano-second (ns)-level transient magnetic-field ( ${H}$ -field) sensor is proposed in this article. The direct measurement result of the MGL antenna is the differential signal of the ${H}$ -field, which is capable to be digitized for storage by the norm detector. The original ${H}$ -field can be restored using the software integral method. The developed ns-level ${H}$ -field sensor exhibits two major advantages. First, it can measure the ${H}$ -field in the substation or the coupled ${H}$ -field inside the hermetically sealed cavities, such as the cockpit of vehicles or aircrafts, which is because the need for the transmission line is removed. Second, its sensitivity is significantly higher than the measurement system with the hardware passive integrator, and the integral error can also be effectively reduced by the low-noise norm detector. In this article, the realization of the ns-level transient ${H}$ -field sensor will be detailed. The simulated upper cutoff frequency of the designed MGL antenna is about 1.9 GHz. The sampling rate of the norm detector is 2 GS/s as the maximum. The dynamic range of the detector is about 42 dB and the operation bandwidth ranges from 0.3 kHz to 500 MHz by calibration. The total storage space of 128 kB can record as long as $64~\mu \text{s}$ at 2 GS/s and is extendable. Test results show that the developed sensor can measure the ns-level ${H}$ -field accurately.

Background: Atrial fibrillation (AF) is the most common cardiac rhythm disorder associated with stroke. Increased risk of stroke is the same regardless of whether the AF is permanent or paroxysmal. However, detecting paroxysmal AF is challenging and resource intensive. We aimed to develop a predictive model for AF in patients with acute ischemic stroke, which could improve the detection rate of paroxysmal AF. Methods: We analyzed 10,034 adult patients with acute ischemic stroke. Differences in clinical characteristics between the patients with and without AF were analyzed in order to develop a predictive model of AF. The associated factors for AF were analyzed using multivariate logistic regression and classification and regression tree (CART) analyses. We used another dataset, which enrolled 860 acute ischemic stroke patients without AF at baseline, to test whether the developed model could improve the detection rate of paroxysmal AF. Among the study population, 1,658 patients (16.5%) had AF. Results: Multivariate logistic regression revealed that sex, age, body weight, hypertension, diabetes mellitus, hyperlipidemia, pulse rate at admission, respiratory rate at admission, systolic blood pressure at admission, diastolic blood pressure at admission, National Institute of Health Stroke Scale (NIHSS) score at admission, total cholesterol level, triglyceride level, aspartate transaminase level, and sodium level were major factors associated with AF. CART analysis identified NIHSS score at admission, age, triglyceride level, and aspartate transaminase level as important factors for AF to classify the patients into subgroups. Conclusions: When selecting the high-risk group of patients (with an NIHSS score >12 and age >64.5 years, or with an NIHSS score ≤12, age >71.5 years, and triglyceride level ≤61.5 mg/dL) according to the CART model, the detection rate of paroxysmal AF was approximately double in the acute ischemic stroke patients without AF at baseline.

The incidence rate of pressure injury is a critical nursing quality indicator in clinic care; consequently, factors causing pressure injury are diverse and complex. The early prevention of pressure injury and monitoring of these complex high-risk factors are critical to reduce the patients' pain, prevent further surgical treatment, avoid prolonged hospital stay, decrease the risk of wound infection, and lower associated medical costs and expenses. Although a number of risk assessment scales of pressure injury have been adopted in various countries, their criteria are set for specific populations, which may not be suitable for the medical care systems of other countries. This study constructs three prediction models of inpatient pressure injury using machine learning techniques, including decision tree, logistic regression, and random forest. A total of 11 838 inpatient records were collected, and 30 sets of training samples were adopted for data analysis in the experiment. The experimental results and evaluations of the models suggest that the prediction model built using random forest had most favorable classification performance of 0.845. The critical risk factors for pressure injury identified in this study were skin integrity, systolic blood pressure, expression ability, capillary refill time, and level of consciousness.

Background:Reusing waste water by appropriate treatment is an effective method for substantiating the ever increasing water demand for construction, irrigation, domestic and industrial purposes. The greywater is the domestic waste water that does not contain the toilet effluent and it is converted and used for non-potable purpose through coagulation and flocculation by using natural coagulant.Objective:The main objective of this work is to evaluate the coagulating efficiencies of various natural coagulants on synthetic greywater by varying pH, mixing speed, mixing time and coagulant dosage.Methods:Powdered coagulants obtained from tamarind seeds, moringa oleifera, banana peels and fly ash were compared with conventional commercial coagulants like alum for synthetic and real greywater.Results:The natural coagulants have shown significant performance compared to chemicals like alum.Conclusion:The turbidity removal efficiency for tamarind seeds, moringa oleifera, banana peels and fly ash were found to be 61.33%, 85.75%, 90.42%, 94.27% against 96.49% obtained from alum on treating with synthetic grey water under identical conditions.

Background: Reducing hospital readmissions for stroke remains a significant challenge to improve outcomes and decrease healthcare costs. Methods: We analyzed 10,034 adult patients with ischemic stroke, presented within 24 hours of onset from a hospital-based stroke registry. The risk factors for early return to hospital after discharge were analyzed using multivariate logistic regression and classification and regression tree (CART) analyses. Results: Among the study population, 277 (2.8%) had 3-day Emergency Department (ED) reattendance, 534 (5.3%) had 14-day readmission, and 932 (9.3%) had 30-day readmission. Multivariate logistic regression revealed that age, nasogastric tube feeding, indwelling urinary catheter, healthcare utilization behaviour, and stroke severity were major and common risk factors for an early return to the hospital after discharge. CART analysis identified nasogastric tube feeding and length of stay for 72-hour ED reattendance, Barthel Index (BI) score, total length of stay in the Year Preceding the index admission (YLOS), indwelling urinary catheter, and age for 14-day readmission, and nasogastric tube feeding, BI score, YLOS, and number of inpatient visits in the year preceding the index admission for 30-day readmission as important factors to classify the patients into subgroups. Conclusions: Although CART analysis did not improve the prediction of an early return to the hospital after stroke compared with logistic regression models, decision rules generated by CART can easily be interpreted and applied in clinical practice.

Background Conventional prognostic scores usually require predefined clinical variables to predict outcome. The advancement of natural language processing has made it feasible to derive meaning from unstructured data. We aimed to test whether using unstructured text in electronic health records can improve the prediction of functional outcome after acute ischemic stroke. Methods and Results Patients hospitalized for acute ischemic stroke were identified from 2 hospital stroke registries (3847 and 2668 patients, respectively). Prediction models developed using the first cohort were externally validated using the second cohort, and vice versa. Free text in the history of present illness and computed tomography reports was used to build machine learning models using natural language processing to predict poor functional outcome at 90 days poststroke. Four conventional prognostic models were used as baseline models. The area under the receiver operating characteristic curves of the model using history of present illness in the internal and external validation sets were 0.820 and 0.792, respectively, which were comparable to the National Institutes of Health Stroke Scale score (0.811 and 0.807). The model using computed tomography reports achieved area under the receiver operating characteristic curves of 0.758 and 0.658. Adding information from clinical text significantly improved the predictive performance of each baseline model in terms of area under the receiver operating characteristic curves, net reclassification improvement, and integrated discrimination improvement indices (all P Conclusions By using natural language processing, unstructured text in electronic health records can provide an alternative tool for stroke prognostication, and even enhance the performance of existing prognostic scores.

Falls are one of the most common accidents among inpatients and may result in extended hospitalization and increased medical costs. Constructing a highly accurate fall prediction model could effectively reduce the rate of patient falls, further reducing unnecessary medical costs and patient injury. This study applied data mining techniques on a hospital's electronic medical records database comprising a nursing information system to construct inpatient-fall-prediction models for use during various stages of inpatient care. The inpatient data were collected from 15 inpatient wards. To develop timely and effective fall prediction models for inpatients, we retrieved the data of multiple-time assessment variables at four points during hospitalization. This study used various supervised machine learning algorithms to build classification models. Four supervised learning and two classifier ensemble techniques were selected for model development. The results indicated that Bagging+RF classifiers yielded optimal prediction performance at all four points during hospitalization. This study suggests that nursing personnel should be aware of patients' risk factors based on comprehensive fall risk assessment and provide patients with individualized fall prevention interventions to reduce inpatient fall rates.

The traveling-wave Marx generator was first proposed by Carl Baum to analyze the switch-closure propagation process in fast pulsed-power systems. To improve the performance of the transistorized sub-nanosecond pulse generator, the traveling-wave Marx circuit with inter-stage transmission lines is studied. Simulations indicate that the delay time and the impedance of inter-stage transmission lines [microstrip lines on printed circuit board (PCB)] are main factors affecting the pulse waveform. Based on it, the series connection of modularized Marx circuits is proposed, which has the advantages of adjustable amplitude and bendable circuit layout. A compact high-amplitude pulse generator is developed with the amplitude of 8.2 kV, the rise time of 150 ps, and the PCB length of 35 cm. For higher pulse repetition rate, the heat dissipation design of PCB is necessary; however, due to the variations in the microstrip line structure, the commonly used metallic heat sink may cause a significant decrease in pulse amplitude. Thus, a novel heat dissipation design is proposed by optimizing the layout of metallic sinks and introducing heat-conducting ceramic sinks. A high-repetition-rate pulse generator is developed with the maximum pulse repetition rate of 600 kHz, the amplitude of 1.1 kV, and the rise time of 160 ps.

Class-imbalanced datasets, i.e., those with the number of data samples in one class being much larger than that in another class, occur in many real-world problems. Using these datasets, it is very difficult to construct effective classifiers based on the current classification algorithms, especially for distinguishing small or minority classes from the majority class. To solve the class imbalance problem, the under/oversampling techniques have been widely used to reduce and enlarge the numbers of data samples in the majority and minority classes, respectively. Moreover, the combinations of certain sampling approaches with ensemble classifiers have shown reasonably good performance. In this paper, a novel undersampling approach called cluster-based instance selection (CBIS) that combines clustering analysis and instance selection is introduced. The clustering analysis component groups similar data samples of the majority class dataset into ‘subclasses’, while the instance selection component filters out unrepresentative data samples from each of the ‘subclasses’. The experimental results based on the KEEL dataset repository show that the CBIS approach can make bagging and boosting-based MLP ensemble classifiers perform significantly better than six state-of-the-art approaches, regardless of what kinds of clustering (affinity propagation and k-means) and instance selection (IB3, DROP3 and GA) algorithms are used.

Background Several prognostic scores have been proposed to predict functional outcomes after an acute ischemic stroke (AIS). Most of these scores are based on structured information and have been used to develop prediction models via the logistic regression method. With the increased use of electronic health records and the progress in computational power, data-driven predictive modeling by using machine learning techniques is gaining popularity in clinical decision-making. Objective We aimed to investigate whether machine learning models created by using unstructured text could improve the prediction of functional outcomes at an early stage after AIS. Methods We identified all consecutive patients who were hospitalized for the first time for AIS from October 2007 to December 2019 by using a hospital stroke registry. The study population was randomly split into a training (n=2885) and test set (n=962). Free text in histories of present illness and computed tomography reports was transformed into input variables via natural language processing. Models were trained by using the extreme gradient boosting technique to predict a poor functional outcome at 90 days poststroke. Model performance on the test set was evaluated by using the area under the receiver operating characteristic curve (AUC). Results The AUCs of text-only models ranged from 0.768 to 0.807 and were comparable to that of the model using National Institutes of Health Stroke Scale (NIHSS) scores (0.811). Models using both patient age and text achieved AUCs of 0.823 and 0.825, which were similar to those of the model containing age and NIHSS scores (0.841); the model containing preadmission comorbidities, level of consciousness, age, and neurological deficit (PLAN) scores (0.837); and the model containing Acute Stroke Registry and Analysis of Lausanne (ASTRAL) scores (0.840). Adding variables from clinical text improved the predictive performance of the model containing age and NIHSS scores, the model containing PLAN scores, and the model containing ASTRAL scores (the AUC increased from 0.841 to 0.861, from 0.837 to 0.856, and from 0.840 to 0.860, respectively). Conclusions Unstructured clinical text can be used to improve the performance of existing models for predicting poststroke functional outcomes. However, considering the different terminologies that are used across health systems, each individual health system may consider using the proposed methods to develop and validate its own models.

BACKGROUND Several prognostic scores have been proposed to predict functional outcomes after an acute ischemic stroke (AIS). Most of these scores are based on structured information and have been used to develop prediction models via the logistic regression method. With the increased use of electronic health records and the progress in computational power, data-driven predictive modeling by using machine learning techniques is gaining popularity in clinical decision-making. OBJECTIVE We aimed to investigate whether machine learning models created by using unstructured text could improve the prediction of functional outcomes at an early stage after AIS. METHODS We identified all consecutive patients who were hospitalized for the first time for AIS from October 2007 to December 2019 by using a hospital stroke registry. The study population was randomly split into a training (n=2885) and test set (n=962). Free text in histories of present illness and computed tomography reports was transformed into input variables via natural language processing. Models were trained by using the extreme gradient boosting technique to predict a poor functional outcome at 90 days poststroke. Model performance on the test set was evaluated by using the area under the receiver operating characteristic curve (AUC). RESULTS The AUCs of text-only models ranged from 0.768 to 0.807 and were comparable to that of the model using National Institutes of Health Stroke Scale (NIHSS) scores (0.811). Models using both patient age and text achieved AUCs of 0.823 and 0.825, which were similar to those of the model containing age and NIHSS scores (0.841); the model containing preadmission comorbidities, level of consciousness, age, and neurological deficit (PLAN) scores (0.837); and the model containing Acute Stroke Registry and Analysis of Lausanne (ASTRAL) scores (0.840). Adding variables from clinical text improved the predictive performance of the model containing age and NIHSS scores, the model containing PLAN scores, and the model containing ASTRAL scores (the AUC increased from 0.841 to 0.861, from 0.837 to 0.856, and from 0.840 to 0.860, respectively). CONCLUSIONS Unstructured clinical text can be used to improve the performance of existing models for predicting poststroke functional outcomes. However, considering the different terminologies that are used across health systems, each individual health system may consider using the proposed methods to develop and validate its own models.