Technology and Health Care - Volume 21, issue 5

Authors: Kumar, Yugal | Sahoo, G.

Article Type: Research Article

Abstract: Background: Diagnosing different types of liver diseases clinically is a quite hectic process because patients have to undergo large numbers of independent laboratory tests. On the basis of results and analysis of laboratory test, different liver diseases are classified. Hence to simplify this complex process, we have developed a Rule Base Classification Model (RBCM) to predict different types of liver diseases. The proposed model is the combination of rules and different data mining techniques. Objective: The objective of this paper is to propose a rule based classification model with machine learning techniques for the prediction of different types …of Liver diseases. Method: A dataset was developed with twelve attributes that include the records of 583 patients in which 441 patients were male and rests were female. Support Vector Machine (SVM), Rule Induction (RI), Decision Tree (DT), Naive Bayes (NB) and Artificial Neural Network (ANN) data mining techniques with K-cross fold technique are used with the proposed model for the prediction of liver diseases. The performance of these data mining techniques are evaluated with accuracy, sensitivity, specificity and kappa parameters as well as statistical techniques (ANOVA and Chi square test) are used to analyze the liver disease dataset and independence of attributes. Result: Out of 583 patients, 416 patients are liver diseases affected and rests of 167 patients are healthy. The proposed model with decision tree (DT) technique provides the better result among all techniques (RI, SVM, ANN and NB) with all parameters (Accuracy 98.46%, Sensitivity 95.7%, Specificity 95.28% and Kappa 0.983) while the SVM exhibits poor performance (Accuracy 82.33%, Sensitivity 68.03%, Specificity 91.28% and Kappa 0.801). It is also found that the best performance of the model without rules (RI, Accuracy 82.68%, Sensitivity 86.34%, Specificity 90.51% and Kappa 0.619) is almost similar to the worst performance of the rule based classification model (SVM, Accuracy 82.33%, Sensitivity 68.03%, Specificity 91.28% and Kappa 0.801 and the accuracy of chi square test is 76.67%. Conclusion: This study demonstrates that there is a significant difference between the proposed rules based classification model and the model without rules for the liver diseases prediction and the rule based classification model with decision tree (DT) technique provides most accurate result. This model can be used as a valuable tool for medical decision making. Show more

Keywords: Classification, machine learning, rule based classification (RBCM), liver diseases

DOI: 10.3233/THC-130742

Citation: Technology and Health Care, vol. 21, no. 5, pp. 417-432, 2013

Authors: Teslim, Onigbinde Ayodele | Adebowale, Adenle Charles | Ojoawo, Adesola Ojo | Sunday, Odejide Akinwole | Bosede, Arilewola

Article Type: Research Article

Abstract: Purpose: The purposes of this study were to compare the effects of pulsed and continuous short wave diathermy on pain, range of motion, pulse rate and skin temperature in subjects with chronic knee osteoarthritis. Methods: 24 Participants with grade 111 OA of the knee were randomly selected into CSWD and PSWD groups. Pre and post treatment parameters were recorded at onset and the end of 4th week. ANO VA, independent, paired t-test and chi-square were used to analyze the data. Results: The pain experienced by participants in the CSWD group was significantly lower than that …of the PSWD groups (P < 0.03) after 4 weeks. Also, both active and passive knee range of motions significantly increased in the CSWD group compared to that of PSWD group (p < 0.01 and 0.002). Across the groups, there was no significant difference in the initial pulse rate at onset of treatments and at the end of 4 weeks. There was an increase in skin temperature within a range of 0.61 to 0.63°C and 0.31 to 0.35°C of participants within both the CSWD and PSWD group respectively. The skin temperature of participants who had continuous SWD was significantly higher after 4 weeks (F=8.38, p < 0.001) but the difference was insignificant within the pulse group. However, there was no significant difference in body temperatures of the 2 groups. Conclusion: This study concluded that CSWD was more effective than PSWD in alleviating pain and in increasing knee flexion range of motion among subjects with chronic knee OA. Also, a mild elevation of skin temperature was able to elicit physiological effects that could exert therapeutic effects. Show more

Keywords: Short wave diathermy, pain, skin temperature, osteoarthritis

DOI: 10.3233/THC-130744

Citation: Technology and Health Care, vol. 21, no. 5, pp. 433-440, 2013

Authors: Horiuchi, Tetsuya | Yamamoto, Shuji | Murase, Kenya

Article Type: Research Article

Abstract: Background: Projection-data based method is established as an accurate simulation of low-dose CT, but cooperation of the CT manufacturer is required. Image-based method is awaited for independent and efficient research. Objective: To develop and verify image-based method for adding noise to DICOM images. Methods: This technique reproduces projection data by fan-beam transform of the DICOM image data and by creating and reconstructing noise projections into a noise image that can be added to the original image. A cylindrical test phantom and anthropomorphic phantom were used to verify the simulation method for both standard and adaptive iterative …reconstruction methods. Results: The simulated images compared favorably with actual images. Standard deviation difference of the simulated images were 1.27% ± 0.81% (cylindrical phantom) and ranged from 1.61% ± 0.81% (head), to 5.41% ± 1.57% (hepatic portal region) (anthropomorphic phantom). The standard deviation difference of the cylindrical phantom with the adaptive iterative technique were 3.41% ± 1.76% at 50% ASIR and 3.85% ± 1.82% at 100% ASIR. The simulated noise power spectra of both types of images were comparable to the actual images. Conclusion: We developed and validated a DICOM image-based low-dose simulation that allows researchers to perform dose reduction research independently and efficiently. Show more

Keywords: Computed tomography, CT, noise, dose reduction, computer simulation

DOI: 10.3233/THC-130746

Citation: Technology and Health Care, vol. 21, no. 5, pp. 441-454, 2013

Authors: Hoshi, Kenji | Kawakami, Junko | Aoki, Sorama | Hamada, Kouji | Sato, Kenichi

Article Type: Research Article

Abstract: Background: Accurate information about patients' use of medication is crucially important for medical treatment. Real-time information can prevent treatment failure resulting from medication delays or failures. Objective: In this study, a compliance-monitoring system is developed for physicians to ascertain their patients' drug-taking behaviors at home in real time. Its operation is then evaluated. Methods: The authors produced a device that uses wireless communication to notify a physician that drugs are taken out of a package by a patient. The device has sensors to detect the package opening. A wireless module is installed in a drug-containing …calendar-type pill organizer. Results: Experimental trials confirmed that a physician can monitor the kind and number of drugs removed from the package on a real-time basis. Furthermore, a practical system can be produced by measuring the distance and consumption current of the produced device, which allows wireless communication. Conclusions: This system enables a doctor to intervene immediately when any compliance lapse occurs, thereby preventing treatment failure caused by delayed response. Show more

Keywords: Medication compliance/adherence, wireless compliance monitoring, telehealth, battery-aware design

DOI: 10.3233/THC-130747

Citation: Technology and Health Care, vol. 21, no. 5, pp. 455-467, 2013

Authors: Kumar, Ajit | Bhatia, Saurabh | Chiang, I-Jen

Article Type: Research Article

Abstract: Background: Healthcare providers, such as doctors and nurses, have been famous for high resistance to change. A careful change management plan, particularly training process, is utmost necessary. A quaternary care hospital in India changed its system, from manual to Electronic Medical Record/Health Information System (EMR/HIS). The hospital management wanted to train its 4000 diverse end-users on the EMR/HIS in two months' time. Objective: This paper describes an in-house designed training process and its deployment in the given healthcare organizational settings. Methods: We designed a training process named DRIPDA. The training process was deployed to …train 4000 end-users of EMR/HIS, in the quaternary care hospital. Various factors, such as methods and tools of training, constraints of trainees, trainers, and organization were considered while deploying the training process. The effectiveness of the DRIPDA was assessed using the Kirkpatrick model. Results: End-users received training on the new system only in 25% of estimated time and 28% of the projected expense, without having any distraction in their usual workflow, or any productivity loss. Conclusion: We found that the DRIPDA training process could train all employees effectively and efficiently. A decent training process can help in managing the change, thereby reduce the training time and cost. Show more

Keywords: Change management, training process, hospital information system, learning management system, e-learning, electronic medical record

DOI: 10.3233/THC-130750

Citation: Technology and Health Care, vol. 21, no. 5, pp. 469-478, 2013

Authors: Manimaran, S. | Lakshmi, K. Bhagya

Article Type: Research Article

Abstract: Background: HMIS will incorporate a paradigm shift in health such as removing manual records and transformation of data through the complex structure of health departments in Tamilnadu. Thus developing a model of technology acceptance in HMIS contest is important and necessary in order to promote usage of the HMIS in rural health care system. Objective: The papers purpose is to formulate a model of technology acceptance of Health Management Information System (HMIS) by generating and validating a research model that best describes rural health care workers usage behavior and behavior intention. Methods: This research proposes …a theoretical framework which is comprised of key determinants that influence usage behavior of HMIS together with moderator. It has been tested through different parametric test and confirmatory factor analysis. Results: Data analysis shows that health workers innovativeness and voluntariness have a direct and positive influence on Technology Acceptance level and that the basic TAM hypotheses are fulfilled. HMIS usage behavior and behavior intention can be increased with factors that are effecting the successful implementation of HMIS when it remains high. Conclusions: This research enables health departments to know which aspects of their HMIS components and variables to improve. This shows that HMIS usage and health workers/staffs acceptance level are key tools in the success of HMIS. This research has seemed to be done at the right time and in the right place to the best of its kind. Show more

Keywords: Voluntariness, innovativeness, health management information system

DOI: 10.3233/THC-130751

Citation: Technology and Health Care, vol. 21, no. 5, pp. 479-492, 2013

Authors: Lerch, Matthias | Weigel, Nelly | Windhagen, Henning | Ettinger, Max | Thorey, Fritz | Kurtz, Agnes | Stukenborg-Colsman, Christina | Bouguecha, Anas

Article Type: Research Article

Abstract: Background: Numerous short stemmed total hip arthroplasty (THA) implants have been introduced over the last decades. It is questionable if little differences between the implant designs affect stress shielding and bone remodeling. The finite element analysis allows an evaluation of the design rationale of the implant without negative side effects for the patient. Objective: We investigated a relatively new short stemmed implant designed from clustered CT datasets of proximal femurs. How does the implant affect femoral bone remodeling? Can we see a positive effect on bone remodeling from the CT based design? Methods: We used …a Finite Element Model that was validated by a prospective dual-energy-x-ray-absorptiometry study to calculate apparent bone density. Results: Apparent bone density (ABD) decreased by 2.3% in the entire femur. Bone mass loss was pronounced in the proximal calcar region. Little ABD increase was seen in the lateral aspect of the cortical ring, in the minor trochanter area and at the lateral aspect of the stem. Conclusions: ABD reduction occurs in the proximal regions of the femur. The overall bone mass loss was little after THA with the investigated implant. The specific design seems to have no major effect on stress shielding or load distribution. Show more

Keywords: Total hip arthroplasty (THA), short stem, periprosthetic bone remodeling, finite element analysis (FEA)

DOI: 10.3233/THC-130743

Citation: Technology and Health Care, vol. 21, no. 5, pp. 493-500, 2013

Authors: Moussazadeh, A.J. | Kohlhof, H. | Wirtz, D.C. | Wimmer, M.D. | Randau, T.M. | Wölk, T. | Gravius, S.

Article Type: Research Article

Abstract: Background: A lateral, transgluteal approach for hip resurfacing carries the risk of approach-related weakening of the hip abductors due to unsuccessful re-adaptation of the gluteal muscles to the greater trochanter or to injury to the inferior nerve branch of the superior gluteal nerve. Objective: We investigated whether hip resurfacing using a soft tissue-sparing, modified transgluteal approach with limited cranial splitting of the gluteus medius muscle reduces hip abductor strength and the risk of approach-related injury to the superior gluteal nerve. Methods: Thirty-one patients (14 female, 17 male; mean age 53.5 ± 5.2 years) underwent hip resurfacing …using a modified transgluteal approach with limited cranial splitting of the gluteus medius muscle. Nerve conduction signals were measured by surface electromyography (EMG), hip abductor strength by isokinetic testing a mean 36.2 months (±11 mos) after surgery. The unoperated side was used as control. Results: Surface EMG disclosed no neural lesions of the inferior branch of the superior gluteal nerve. Isokinetics revealed a significant reduction in muscle strength on the operated versus the contralateral side. Conclusions: Even a limited incision of the gluteus medius muscle resulted in significant impairment of hip abductor strength 2.5 years after surgery. Show more

Keywords: Hip resurfacing, lateral approach, surface EMG, isokinetics

DOI: 10.3233/THC-130745

Citation: Technology and Health Care, vol. 21, no. 5, pp. 501-510, 2013

Authors: Ratnovsky, Anat | Carmeli, Yael Nadlin | Elad, David | Zaretsky, Uri | Dollberg, Shaul | Mandel, Dror

Article Type: Research Article

Abstract: Background: Breastfeeding is a dynamic process in which the infant recruits several muscle groups in his face, head and throat. Objective: The objective of this study was to explore the relative role of the submental muscle group, the orbicularis oris and the sternocleidomastoid muscles to breastfeeding process and to the relatively high intra-oral vacuum measured during this process. Methods: Electromyography (EMG) measurements were conducted on 11 infants (mean age 1.91 ± 1.0 days, mean weight 3364 ± 328 g) using surface electrodes. The EMG data were filtered with a low pass filter to yield the …linear envelopes (IEMG). The maximal and mean value and the area under each linear envelope curve were examined. Results: During active suckling significantly higher activity (P< 0.05) of the submental muscle group were measured compared with the orbicularis oris and sternocleidomastoid muscles (mean ± SE values of the maximal linear envelope were 24.4 ± 1 μV, 9.6 ± 0.6 μV and 14 ± 0.7 μV, respectively). Conclusion: These results confirmed that jaw movements have the primary role during breastfeeding, but also revealed that the inspiratory muscles have a substantial contribution to this process and probably have an important role in the generation of intra oral vacuum measured during breastfeeding. Show more

Keywords: Breastfeeding, electromyography (EMG), infant development, signal processing

DOI: 10.3233/THC-130749

Citation: Technology and Health Care, vol. 21, no. 5, pp. 511-520, 2013

Authors: Boelens, C. | Hekman, E.E.G. | Verkerke, G.J.

Article Type: Research Article

Abstract: Objective: Fall prevention is a major issue in the ageing society. This study provides an overview of all risk factors for falls of older citizens. Method: A literature search was conducted to retrieve studies of the past 25 years. All participants from the studies lived in the community or institutions and were aged 60 or older. The following key word combinations were used, limited to the title: elderly or older people or older adults and fall and risk. The risk factors were categorised as relevant and amendable, relevant but non amendable, inconclusive or unsupported. Results: …In total 30 publications were studied in 2013 in Enschede, the Netherlands. The relevant intrinsic risk factors are muscle strength, balance capacity, reactive power, dual tasking and sleep disturbance. Relevant extrinsic risk factors are home hazards, wrong use of assistive devices and bad footwear. Behaviour-related risk factors are hurrying, risk taking, physical inactivity and fear of falling. Relevant symptoms that could be caused by underlying risk factors are mobility problems, gait problems, vertigo, use of assisting devices and history of falls. Conclusions: Several risk factors are determined to be relevant and amendable. The provided overview could be used to create fall preventive measures for elderly. Show more

Keywords: Aging, falls, risk factors

DOI: 10.3233/THC-130748

Citation: Technology and Health Care, vol. 21, no. 5, pp. 521-533, 2013