Technology and Health Care - Volume 29, issue 1

Authors: Kruse, Clemens Scott | Mileski, Michael | Syal, Rohan | MacNeil, Lauren | Chabarria, Edward | Basch, Cody

Article Type: Review Article

Abstract: BACKGROUND: The prevalence of health information technology (HIT) as an adjunct to increase safety and quality in healthcare applications is well known. There is a relationship between the use of HIT and safer-prescribing practices in long-term care. OBJECTIVE: The objective of this systematic review is to determine an association between the use of HIT and the improvement of prescription administration in long-term care facilities. METHODS: A systematic review was conducted using the MEDLINE and CINAHL databases. With the use of certain key terms, 66 articles were obtained. Each article was then reviewed by …two researchers to determine if the study was germane to the research objective. If both reviewers agreed with using the article, it became a source for our review. The review was conducted and structured based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. RESULTS: The researchers identified 14 articles to include in a group for analysis from North America, Europe, and Australia. Electronic health records and electronic medication administration records were the two most common forms of technological interventions (6 of 14, 43%). Reduced risk, decreased error, decreased missed dosage, improved documentation, improved clinical process, and stronger clinical focus comprised 92% of the observations. CONCLUSIONS: HIT has shown beneficial effects for many healthcare organizations. Long-term care facilities that implemented health information technologies, have shown reductions in adverse drug events caused by medication errors overall reduced risk to the organization. The implementation of new technologies did not increase the time nurses spent on medication rounds. Show more

Keywords: Long-term care, medication safety, technology diffusion, health information technology

DOI: 10.3233/THC-202196

Citation: Technology and Health Care, vol. 29, no. 1, pp. 1-14, 2021

Authors: Ong, Dorothea Sze Min | Weibin, Melvyn Zhang | Vallabhajosyula, Ranganath

Article Type: Review Article

Abstract: BACKGROUND: The use of serious games (SG) in rehabilitation has been on the rise in recent years and they are used as either a main interventional tool, or as an adjunct alongside conventional therapies. This is largely due to its virtue of being an electronic platform hence possessing game characteristics that facilitates patient progress. OBJECTIVE: The present study aimed to provide a comprehensive review of the impact of SG on neurorehabilitation therapies as well as patients’ perspectives on rehabilitation. METHODS: The literature search was conducted in PubMed and Cochrane databases. The study was …conducted in four different phases, consisting of the generation of MeSH terms and keywords, screening of articles, and data analysis based on the study characteristics. RESULTS: This review included 47 studies that explored the use of custom designed experimental serious games (ESG) or commercially designed serious games (CSG) for rehabilitation in a few neurological conditions. The majority of CSG used Nintendo Wii as an adjunct to conventional therapies. Significant improvement in the primary outcomes such as motor functioning, balance, executive and cognitive functions were reported in 35 studies. 17 studies also indicated patient perspectives on rehabilitation. There was no difference between the overall impact of either CSG or ESG. CONCLUSION: Evidently, SG are efficient exergame tools. However, future studies should explore patient perspectives that could help to design evidence-based games for rehabilitation purposes. Show more

Keywords: Serious games, neurological conditions, rehabilitation, positive outcomes, patient perspectives, evidence based serious games

DOI: 10.3233/THC-202333

Citation: Technology and Health Care, vol. 29, no. 1, pp. 15-31, 2021

Authors: Choudhury, Avishek | Perumalla, Sunanda

Article Type: Research Article

Abstract: BACKGROUND: One of the most broadly founded approaches to envisage cancer treatment relies upon a pathologist’s efficiency to visually inspect the appearances of bio-markers on the invasive tumor tissue section. Lately, deep learning techniques have radically enriched the ability of computers to identify objects in images fostering the prospect for fully automated computer-aided diagnosis. Given the noticeable role of nuclear structure in cancer detection, AI’s pattern recognizing ability can expedite the diagnostic process. OBJECTIVE: In this study, we propose and implement an image classification technique to identify breast cancer. METHODS: We implement the …convolutional neural network (CNN) on breast cancer image data set to identify invasive ductal carcinoma (IDC). RESULT: The proposed CNN model after data augmentation yielded 78.4% classification accuracy. 16% of IDC (- ) were predicted incorrectly (false negative) whereas 25% of IDC (+ ) were predicted incorrectly (false positive). CONCLUSION: The results achieved by the proposed approach have shown that it is feasible to employ a convolutional neural network particularly for breast cancer classification tasks. However, a common problem in any artificial intelligence algorithm is its dependence on the data set. Therefore, the performance of the proposed model might not be generalized. Show more

Keywords: Convolutional neural network, deep learning, artificial intelligence, machine learning, breast cancer, ductal carcinoma

DOI: 10.3233/THC-202226

Citation: Technology and Health Care, vol. 29, no. 1, pp. 33-43, 2021

Authors: Choudhury, Avishek

Article Type: Research Article

Abstract: BACKGROUND: Pleural Mesothelioma (PM) is an unusual, belligerent tumor that rapidly develops into cancer in the pleura of the lungs. Pleural Mesothelioma is a common type of Mesothelioma that accounts for about 75% of all Mesothelioma diagnosed yearly in the U.S. Diagnosis of Mesothelioma takes several months and is expensive. Given the risk and constraints associated with PM diagnosis, early identification of this ailment is essential for patient health. OBJECTIVE: In this study, we use artificial intelligence algorithms recommending the best fit model for early diagnosis and prognosis of Malignant Pleural Mesothelioma (MPM). METHODS: …We retrospectively retrieved patients’ clinical data collected by Dicle University, Turkey and applied multilayered perceptron (MLP), voted perceptron (VP), Clojure classifier (CC), kernel logistic regression (KLR), stochastic gradient decent (SGD), adaptive boosting (AdaBoost), Hoeffding tree (VFDT), and primal estimated sub-gradient solver for support vector machine (s-Pegasos). We evaluated the models, compared and tested them using paired t -test (corrected) at 0.05 significance based on their respective classification accuracy, f-measure, precision, recall, root mean squared error, receivers’ characteristic curve (ROC), and precision-recall curve (PRC). RESULTS: In phase 1, SGD, AdaBoost.M1, KLR, MLP, VFDT generate optimal results with the highest possible performance measures. In phase 2, AdaBoost, with a classification accuracy of 71.29%, outperformed all other algorithms. C-reactive protein, platelet count, duration of symptoms, gender, and pleural protein were found to be the most relevant predictors that can prognosticate Mesothelioma. CONCLUSION: This study confirms that data obtained from biopsy and imaging tests are strong predictors of Mesothelioma but are associated with a high cost; however, they can identify Mesothelioma with optimal accuracy. Show more

Keywords: Mesothelioma, predictive modeling, decision support system, machine learning, artificial intelligence, lung cancer

DOI: 10.3233/THC-202237

Citation: Technology and Health Care, vol. 29, no. 1, pp. 45-58, 2021

Authors: El-Badawy, Ismail M. | Singh, Om Prakash | Omar, Zaid

Article Type: Research Article

Abstract: BACKGROUND: The quantitative features of a capnogram signal are important clinical metrics in assessing pulmonary function. However, these features should be quantified from the regular (artefact-free) segments of the capnogram waveform. OBJECTIVE: This paper presents a machine learning-based approach for the automatic classification of regular and irregular capnogram segments. METHODS: Herein, we proposed four time- and two frequency-domain features experimented with the support vector machine classifier through ten-fold cross-validation. MATLAB simulation was conducted on 100 regular and 100 irregular 15 s capnogram segments. Analysis of variance was performed to investigate the significance of …the proposed features. Pearson’s correlation was utilized to select the relatively most substantial ones, namely variance and the area under normalized magnitude spectrum. Classification performance, using these features, was evaluated against two feature sets in which either time- or frequency-domain features only were employed. RESULTS: Results showed a classification accuracy of 86.5%, which outperformed the other cases by an average of 5.5%. The achieved specificity, sensitivity, and precision were 84%, 89% and 86.51%, respectively. The average execution time for feature extraction and classification per segment is only 36 ms. CONCLUSION: The proposed approach can be integrated with capnography devices for real-time capnogram-based respiratory assessment. However, further research is recommended to enhance the classification performance. Show more

Keywords: Capnography, capnogram, artefacts, machine learning, time- and frequency-domain features, respiratory assessment

DOI: 10.3233/THC-202198

Citation: Technology and Health Care, vol. 29, no. 1, pp. 59-72, 2021

Authors: Wan, Xiangkui | Liu, Junjie | Jin, Zhiyao | Zhu, Binru | Zhang, Mingrui

Article Type: Research Article

Abstract: BACKGROUND: Ventricular repolarization instabilities have been documented to be closely linked to arrhythmia development. The electrocardiogram (ECG) ST interval can be used to measure ventricular repolarization. Analyzing the duration variation of the ST intervals can provide new information about the arrhythmogenic vulnerability. OBJECTIVE: In this work, we propose a new method based on mean instantaneous frequency (IF) of the ST intervals to quantitatively evaluate the risk of sudden cardiac deaths (SCDs). METHODS: Two spectral bands, i.e. the low-frequency band (LF, 0–0.15 Hz) and the high-frequency band (HF, 0.15–0.5 Hz), are considered in this …paper. Based on IF estimates, the ECG recordings from three MIT-BIH databases that represent different risk levels of SCD occurrence are used, and their mean IFs in the LF and HF bands are calculated. RESULTS: The statistical results show that healthy subjects have a higher mean IF in the HF band and a lower mean IF in the LF band. The experimental results are the opposite for patients with malignant ventricular arrhythmia. CONCLUSION: The proposed mean IF can represent an indirect measure of intrinsic ventricular repolarization instability and can mark cardiac instability associated with SCDs. Show more

Keywords: Ventricular repolarization instabilities, ECG, ST interval, instantaneous frequency

DOI: 10.3233/THC-202377

Citation: Technology and Health Care, vol. 29, no. 1, pp. 73-83, 2021

Authors: Bao, Hua | Gao, Hao-Ran | Pan, Min-Lu | Zhao, Lei | Sun, Hai-Bin

Article Type: Research Article

Abstract: BACKGROUND: Acute cerebral infarction (ACI) is a common cerebrovascular disease in clinical practice. OBJECTIVE: The present study aims to investigate the efficacy and safety of alteplase and urokinase in treating ACI. METHODS: A total of 96 patients with ACI, who were treated with alteplase and urokinase, were selected as the main subjects. Among these patients, 45 patients with ultra-early acute cerebral infarction, who received intravenous thrombolysis with RT-PA (alteplase), were included in the treatment group, while 51 patients with acute cerebral infarction, who were treated with urokinase in the same time period, were …included in the control group. RESULTS: The National Institute of Health Stroke Scale (NIHSS) scores were significantly lower in the treatment group and control group (P < 0.05) at two hours, seven days and 14 days after thrombolysis, when compared to those before thrombolysis. The bleeding rate was significantly lower in the control group, when compared to the treatment group (P < 0.05). CONCLUSION: The intravenous thrombolysis with urokinase or alteplase in the ultra-early stage of acute cerebral infarction can reduce the neurological injury symptoms and effectively improve the prognosis of patients with stroke. Urokinase is lower in risk of bleeding, but better in safety, when compared to alteplase. Show more

Keywords: Alteplase, urokinase, thrombolytic therapy, cerebral infarction, stroke

DOI: 10.3233/THC-202382

Citation: Technology and Health Care, vol. 29, no. 1, pp. 85-90, 2021

Authors: Gao, Xiang | Liu, Dian-Gang | Wang, Feng | Zhang, Chao | Du, Xing | Wu, Ji-Min | Wang, Zhong-Gao | Li, Fei

Article Type: Research Article

Abstract: BACKGROUND: The false positive rate of the PPI test for the diagnosis of typical symptoms of gastroesophageal reflux disease (GERD) is extremely high. OBJECTIVE: This study aims to investigate the effect of the pepsin test on GERD and laparoscopy-assisted anti-reflux surgery for GERD. METHODS: A total of 30 GERD patients were enrolled into this study, and the pre-diagnosis of GERD was determined by symptom evaluation, impedance-pH examination, gastroscopy and pepsin test. All patients underwent surgery. RESULTS: Among the 30 GERD patients, 18 patients were male and 12 were female, and their average …age was 58.2 + 12.6 years old. The patients were treated with laparoscopic fundoplication and hiatus hernia repair after preoperative assessment. A total of 28 patients were followed up, one patient developed recurrent symptoms, and one patient developed postoperative dysphagia and received non-operative treatment. Furthermore, the symptom scores were significantly lower at postoperative pepsin detection when compared to the scores before the operation (pepsin: preoperative: 148.8 ± 82.6, postoperative: 30.7 ± 24.6; t = 4.848, P = 0.000). CONCLUSIONS: Laparoscopic fundoplication and hiatus hernia repair may effectively control the symptoms of GERD. Furthermore, the detection of pepsin is non-invasive and easy to operate. Show more

Keywords: Gastroesophageal reflux, laparoscopy, fundoplication, pepsin, impedance-pH

DOI: 10.3233/THC-192090

Citation: Technology and Health Care, vol. 29, no. 1, pp. 91-97, 2021

Authors: Soundirarajan, Mirra | Pakniyat, Najmeh | Sim, Sue | Nathan, Visvamba | Namazi, Hamidreza

Article Type: Research Article

Abstract: BACKGROUND: Human facial muscles react differently to different visual stimuli. It is known that the human brain controls and regulates the activity of the muscles. OBJECTIVE: In this research, for the first time, we investigate how facial muscle reaction is related to the reaction of the human brain. METHODS: Since both electromyography (EMG) and electroencephalography (EEG) signals, as the features of muscle and brain activities, contain information, we benefited from the information theory and computed the Shannon entropy of EMG and EEG signals when subjects were exposed to different static visual stimuli with …different Shannon entropies (information content). RESULTS: Based on the obtained results, the variations of the information content of the EMG signal are related to the variations of the information content of the EEG signal and the visual stimuli. Statistical analysis also supported the results indicating that the visual stimuli with greater information content have a greater effect on the variation of the information content of both EEG and EMG signals. CONCLUSION: This investigation can be further continued to analyze the relationship between facial muscle and brain reactions in case of other types of stimuli. Show more

Keywords: Facial muscle, brain, electromyography (EMG) signal, electroencephalography (EEG) signal, information, shannon entropy, static visual stimuli

DOI: 10.3233/THC-192085

Citation: Technology and Health Care, vol. 29, no. 1, pp. 99-109, 2021

Authors: Xu, Lin | Liu, Chunhua | Ning, Xu | Bai, Zeling | Qin, Mingxin | Guo, Haitao | Sun, Jian

Article Type: Research Article

Abstract: BACKGROUND: Real-time clinical monitoring of cerebral edema (CE) is of great importance and requires continuously improved and optimized measurement hardware. METHODS: A new excitation source with higher frequency stability and wide output power range is presented in this work. The proposed excitation source is small in size and easy to integrate. The output power range of excitation signal used is 1.5 ∼ 33 dBm with a reference signal of 9 ∼ 11 dBm, and the phase shift stability of the excitation signal and reference signal reach 10 - 7 …within 20 min. RESULTS: When normal saline (0.9%, 10 mL, 20 mL, 30 mL, 40 mL, and 50 mL) is injected into a human head phantom model, the magnetic induction phase shift (MIPS) changes from 252.78 ± 7.61 degrees to 252.40 ± 7.77 degrees. The MIPS signal shows a downward trend with increasing volume, indicating that MIPS can reflect the volume change of the measured object. Moreover, a more dramatic trend is visible when the solution volume increases from 0 to 10 mL and from 40 to 50 mL. This occurs where the volume increment is closer to the upper and lower sides of the over-ear sensor, where the magnetic field is strongest. CONCLUSION: The phantom simulation experiments illustrate that the proposed MIPS detection system based on a signal source can detect the real-time progress of CE. Advantages of low cost, high precision, and high sensitivity endow this system with excellent application prospects. Show more

Keywords: Excitation source, cerebral edema, phase shift, magnetic induction

DOI: 10.3233/THC-192068

Citation: Technology and Health Care, vol. 29, no. 1, pp. 111-120, 2021