Phat K. Huynh, Arveity Setty, Trung Le, Trung Q Le
{"title":"A noise-robust Koopman spectral analysis of an intermittent dynamics method for complex systems: a case study in pathophysiological processes of obstructive sleep apnea","authors":"Phat K. Huynh, Arveity Setty, Trung Le, Trung Q Le","doi":"10.1080/24725579.2022.2141379","DOIUrl":"https://doi.org/10.1080/24725579.2022.2141379","url":null,"abstract":"Abstract Koopman operator theory and the Hankel alternative view of the Koopman (HAVOK) model have been widely used to investigate the chaotic dynamics in complex systems. Although the statistics of intermittent dynamics have been evaluated in the HAVOK model, they are not adequate to characterize intermittent forcing. In this paper, we propose a novel method to characterize the intermittent phases, chaotic bursts, and local spectral-temporal properties of various intermittent dynamics modes using spectral decomposition and wavelet analysis. To validate our methods, we compared the sensitivity to noise level and sampling period of the HAVOK and our proposed method in the Lorenz system. Our results show that the prediction accuracy of lobe switching and the intermittent forcing identifiability were highly sensitive to the sampling rate. While it is possible to maintain the desired accuracy in high noise-level cases with an appropriately selected rank in the HAVOK model, our proposed method is demonstrated to be more robust. To show the applicability of our proposed method, obstructive sleep apnea—a complex pathological disorder—was selected as a case study. The results show a strong association between active forcing and the hypopnea-apnea events. Our proposed method has been demonstrated to be a promising data-driven method to provide key insights into the dynamics of complex systems.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"13 1","pages":"101 - 116"},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"60128587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ameer Hamza Shakur, Tianchen Sun, Jieun Kim, Shuai Huang
{"title":"A rule-based exploratory analysis for discovery of multimodal biomarkers of ADHD using eye movement and EEG data","authors":"Ameer Hamza Shakur, Tianchen Sun, Jieun Kim, Shuai Huang","doi":"10.1080/24725579.2022.2126036","DOIUrl":"https://doi.org/10.1080/24725579.2022.2126036","url":null,"abstract":"Abstract Developing biomarkers for a complex neurodevelopmental disorder such as the attention deficit hyperactivity disorder (ADHD) is a challenging task since it is a multifactorial and multi-faceted condition. Researchers have been employing different sensing modalities to acquire measurements of the condition, however, there has been a lack of approaches that can adequately combine the multimodal data and detect interactions among the modalities. To demonstrate the concept and benefit of multimodal biomarker discovery, we conducted a multimodal data collection targeting the ADHD condition and demonstrated how a rule-based exploratory analysis approach could be used to analyze the data. To the best of our knowledge, our work is the first attempt to explore and identify interesting interactions among two modalities of data, eye movement data and the EEG signal, for multimodal biomarker discovery for ADHD. The detection of these interactions would help us better understand the condition and develop better prediction models and intervention strategies.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"13 1","pages":"74 - 88"},"PeriodicalIF":0.0,"publicationDate":"2022-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48566146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Impact of cognitive workload and situation awareness on clinicians’ willingness to use an artificial intelligence system in clinical practice","authors":"Avishek Choudhury, Onur Asan","doi":"10.1080/24725579.2022.2127035","DOIUrl":"https://doi.org/10.1080/24725579.2022.2127035","url":null,"abstract":"Abstract Determinants of technology acceptance are multifaceted, particularly for artificial intelligence (AI) in healthcare. Using AI might impact users’ cognitive workload and situation awareness. This study explores the moderating effect of clinicians’ situation awareness and workload on the interaction between trust, risk, and intent to use an AI-based decision support system known as the blood utilization calculator (BUC). The study took place at an academic hospital in Wisconsin, US. A purposeful sampling strategy was utilized to recruit 119 BUC users. The data was collected via an online validated survey. The study leveraged Hayes PROCESS to capture the moderation effect of situation awareness and cognitive workload on the relationship between perceived risk and trust. The study also reports the significant impact of situation awareness (positively) and cognitive workload (negatively) on intent to use BUC. Adding to the body of knowledge, our study advocates for minimal cognitive workload and optimal situation awareness in healthcare.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"13 1","pages":"89 - 100"},"PeriodicalIF":0.0,"publicationDate":"2022-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46663631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Infectious disease control in metapopulations with limited resources","authors":"C. Best, A. Khademi, B. Eksioglu","doi":"10.1080/24725579.2022.2115171","DOIUrl":"https://doi.org/10.1080/24725579.2022.2115171","url":null,"abstract":"Abstract Motivated by unique challenges faced in containing the 2014 Ebola outbreak in West Africa, we develop a framework to dynamically allocate limited resources to several possibly connected populations where the disease transmission is stochastic. We formulate this problem as a stochastic dynamic program. However, as the state and action spaces grow exponentially with the size of the problem, the standard solution techniques do not apply. We propose two solution methodologies along with several benchmark policies. The first approach considers a dynamic one-step look-ahead policy which is equivalent to a nonlinear integer knapsack that scales well with the problem size. The second approach is a modification of a myopic incidence policy found in the literature. In addition to testing the proposed policies in a simulation setting of the optimization framework, we develop a large-scale stochastic simulation for 2014 Ebola outbreak in a case study. We calibrate and validate the stochastic simulation model with real-world data from Sierra Leone. Our results provide insights on efficient prioritization and resource allocation in this setting.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"13 1","pages":"62 - 73"},"PeriodicalIF":0.0,"publicationDate":"2022-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44965999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Masoud Ghanbari kakavandi, Farzaneh Molla Bahrami, H. Ashtarian, Rohollah Fallah Madvari, Kamran Najafi
{"title":"Application of SHERPA technique in ophthalmic operating rooms to identify and evaluate human errors: a case study of strabismus surgery process","authors":"Masoud Ghanbari kakavandi, Farzaneh Molla Bahrami, H. Ashtarian, Rohollah Fallah Madvari, Kamran Najafi","doi":"10.1080/24725579.2022.2096155","DOIUrl":"https://doi.org/10.1080/24725579.2022.2096155","url":null,"abstract":"Abstract Background Eye surgeries are very sensitive to human errors that can reduce the patient's safety and cause irreparable damage. This study will show where and why human errors occur during eye surgery and minimize them. Purpose This study was conducted to demonstrate the feasibility of using a simple and practical technique for analyzing the process of eye surgeries to identify opportunities for managing human error. Methods The basis of this study is the analysis of strabismus surgery and related processes (such as patient anesthesia and postoperative recovery) using the HTA and the identification and evaluation of probable human errors in the tasks and sub-tasks using the SHERPA technique. Results The activities were divided into 83 tasks and sub-tasks. Investigations of the findings of HTA resulted in the identification of 58 probable errors. Action errors with a prevalence rate of 64% had the highest frequency, followed by checking, retrieval, and selection errors with 17%, 12%, and 7%, respectively. Based on the results, 5% of the errors were at the unacceptable risk level, 50% at undesirable risk level, 31% at acceptable risk level but with revision requirements, and 14% at acceptable risk level without the need for revision. Conclusions This study showed that the use of human reliability analysis methods in eye surgeries can have major advantages such as: identifying the areas with the highest probability of error, prioritizing error by determining the level of risk or probability of their occurrence and providing appropriate control solutions to minimize the risk of error.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"13 1","pages":"35 - 45"},"PeriodicalIF":0.0,"publicationDate":"2022-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"60128578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Routing and staffing in emergency departments: A multiclass queueing model with workload dependent service times","authors":"Siddhartha Nambiar, M. Mayorga, Yunan Liu","doi":"10.1080/24725579.2022.2100522","DOIUrl":"https://doi.org/10.1080/24725579.2022.2100522","url":null,"abstract":"Abstract Efficient patient flow through an emergency department is a critical factor that contributes to a hospital’s performance, which influences overall patient health outcomes. In this work, we model a multiclass multiserver queueing system where patients of varying acuity receive care from one of several wards, each ward is attended by several nurses who work as a team. Supported by empirical evidence that a patient’s time-in-ward is a function of the nurse-patient ratio in that ward, we incorporate state-dependent service times into our model. Our objective is to reduce patient time in system and to control nurse workload by jointly optimizing patient routing and nurse allocation decisions. Due to the computational challenges in formulating and solving the queueing model representation, we study a corresponding deterministic fluid model which serves as a first-order approximation of the multiclass queueing model. Next, we formulate and solve an optimization model using the first-order control equations and input the results into a discrete-event simulation to estimate performance measures, such as patient length-of-stay and ward workload. Finally, we present a case study using retrospective data from a real hospital which highlights the importance of accounting for nurse workload and service behavior in developing routing and staffing policies.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"13 1","pages":"46 - 61"},"PeriodicalIF":0.0,"publicationDate":"2022-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46197666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Investigating the effectiveness of supplemental breast cancer screening tests considering radiologists’ bias","authors":"M. Madadi, S. Molani, Donna L. Williams","doi":"10.1080/24725579.2022.2095466","DOIUrl":"https://doi.org/10.1080/24725579.2022.2095466","url":null,"abstract":"Abstract Breast density is known to increase breast cancer risk and decrease mammography screening sensitivity. Breast density notification laws require physicians to inform women with high breast density of these potential risks. The laws usually require healthcare providers to notify patients of the possibility of using more sensitive supplemental screening tests (i.e., ultrasound and MRI). Since the enactment of the laws, there have been controversial debates over (i) their implementations due to the potential radiologists’ bias in breast density classification of mammogram images and (ii) the necessity of supplemental screenings for all patients with high breast density. In this study, we formulate a finite-horizon, discrete-time partially observable Markov chain to investigate the effectiveness of supplemental screening and the impact of radiologists’ misclassification bias on patients’ outcomes. We consider the conditional probability of eventually detecting breast cancer in early states given that the patient develops breast cancer in her lifetime as the primary and the expected number of supplemental tests as the secondary patient’s outcome. Our results indicate that referring patients to a supplemental test solely based on their breast density may not necessarily improve their health outcomes and other risk factors need to be considered when making such referrals. Additionally, average-skilled radiologists’ performances are shown to be comparable with the performance of a perfect radiologist (i.e., 100% accuracy in breast density classification). However, a significant bias in breast density classification (i.e., consistent upgrading or downgrading of breast density classes) can negatively impact a patient’s health outcomes.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"13 1","pages":"1 - 20"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41912592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Ranking-based Weakly Supervised Learning model for telemonitoring of Parkinson’s disease","authors":"Dhari F. Alenezi, Hang Shi, Jing Li","doi":"10.1080/24725579.2022.2091065","DOIUrl":"https://doi.org/10.1080/24725579.2022.2091065","url":null,"abstract":"Abstract Telemonitoring is the use of electronic devices to monitor patients remotely. A model is needed to translate the data collected by a patient’s mobile device into a predicted score for disease severity assessment. Labeled samples are scarce, which makes it difficult to train a supervised learning model. On the other hand, there is an abundance of samples without precise labels but whose relative rank can be known from domain knowledge. We propose a Ranking-based Weakly Supervised Learning (RWSL) model to integrate both types of data. We apply RWSL to predict Parkinson’s disease severity based on mobile-collected tapping activity data of patients. RWSL achieves high predictive accuracy and outperforms competing methods.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"12 1","pages":"322 - 336"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42682731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The importance of preference interactions in joint health-state utility values applied to decision analyses for shared decision-making","authors":"E. Kujawski","doi":"10.1080/24725579.2022.2095467","DOIUrl":"https://doi.org/10.1080/24725579.2022.2095467","url":null,"abstract":"Abstract The direct elicitation of health-state utility values (HSUVs) is difficult, and inconsistent HSUVs are a prevalent problem. Joint health conditions (JHCs) affect people’s quality of life in different ways. They can be preference substitutes, preference complements, or mutually utility independent. This article develops a novel model called the correlated bivariate Bernoulli health-utility (CBBHU) model, for estimating joint HSUVs (JHSUVs) from known single HSUVs and a small subset of elicited JHSUVs. A bivariate health utility function (HUF) is developed for the dependence of JHSUVs on severity. It consists of the product of the constituent single HUFs and a bivariate function with two parameters that vary with health conditions and patients’ preferences. These parameters can be fitted to as few as two severity levels and the parametrized HUF used to estimate HSUVs for different severity levels. A bootstrap method that requires a significantly reduced number of elicited HSUVs is proposed for estimating JHSUVs for three or more JHCs. The CBBHU functions satisfy the Fréchet bounds and provide internally consistent HSUVs. Preference interactions can have a substantial impact on patients’ medical decisions. CBBHU values are appropriate for shared decision-making applications. HIGHLIGHTS The CBBHU model is a novel theoretical model for estimating JHSUVs. The CBBHU model provides a practical approach to model and predict reliable JHSUVs. The JHSUVs satisfy the Fréchet inequalities, utility theory, and prospect theory. The CBBHU models JHCs that are preference complements and preference substitutes. A practical bootstrap method extends the CBBHU model to multimorbidities.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"13 1","pages":"21 - 34"},"PeriodicalIF":0.0,"publicationDate":"2022-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47445813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
E. Ghanbari, Sogand Soghrati Ghasbe, A. Aghsami, F. Jolai
{"title":"A novel mathematical optimization model for a preemptive multi-priority M/M/C queueing system of emergency department’s patients, a real case study in Iran","authors":"E. Ghanbari, Sogand Soghrati Ghasbe, A. Aghsami, F. Jolai","doi":"10.1080/24725579.2022.2083730","DOIUrl":"https://doi.org/10.1080/24725579.2022.2083730","url":null,"abstract":"Abstract The Covid-19 pandemic crisis has caused many difficulties worldwide. One of the most critical problems is that the emergency departments (EDs) have become overcrowded. Because this problem can increase patients’ queue length and waiting times in EDs, this paper provides a mixed-integer non-linear mathematical model considering a preemptive M/M/C queueing system to solve the problem and optimize a benefit function concerning the number of servers and treatment rate. In this model, different patient priorities, which are modified according to Covid-19 patients, are considered. This model is then solved using an exact approach and a meta-heuristic algorithm, the grasshopper optimization algorithm, for two shifts of the ED of a hospital in order to consider non stationery arrival rate in Varamin, Iran. The results of both algorithms confirmed the effectiveness of the proposed model. Moreover, to justify using the preemptive model, a comparison between the preemptive and non-preemptive models is conducted. An extensive sensitivity analysis is presented, and finally, a list of managerial insights is provided for managers to improve their service system further.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"12 1","pages":"305 - 321"},"PeriodicalIF":0.0,"publicationDate":"2022-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43474543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}