IISE Transactions on Healthcare Systems Engineering最新文献

{"title":"Multi-label chain clustering-classification and regression predictive models for patient punctuality and turnaround time in outpatient primary care settings","authors":"Laith Abu Lekham, Yong Wang, Ellen Hey, M. Khasawneh","doi":"10.1080/24725579.2022.2068703","DOIUrl":"https://doi.org/10.1080/24725579.2022.2068703","url":null,"abstract":"Abstract This study develops two multi-label chain machine learning predictive models to anticipate patient punctuality and turnaround time. The first model uses an integrated model of clustering and classification where the check-in, service, and checkout times are clustered into three categories using the K-means algorithm. Then, patient punctuality and established clusters are used to develop a multi-label chain predictive model that utilizes Logistic Regression, Multi-Layer Perceptron, and tree-based classifiers. The second model predicts patient punctuality and turnaround time using a multi-label chain regression model that utilizes Linear Regression, Huber Regressor, ADR Regression, Multi-Layer Perceptron, and tree-based regressors. It was found that a patient’s age is a key driver for both patient punctuality and turnaround time. Also, there is a significant association between patient punctuality and turnaround time. The first proposed model predicted the punctuality and turnaround time with an average best F1-score of about 70.4% and 71.9%, respectively. The second model produced acceptable results with the best average R-squared of 0.67 for punctuality and 0.68 for turnaround time. The models can reduce the complexity and time of predicting several numerical outputs, enhance the interpretation of the results, and improve the understanding of the results by non-technical staff.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"12 1","pages":"288 - 304"},"PeriodicalIF":0.0,"publicationDate":"2022-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48736014","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":"Optimizing patient flow, capacity, and performance of COVID-19 vaccination clinics","authors":"L. Valladares, Valentina Nino, Kenneth Martínez, D. Sobek, David Claudio, S. Moyce","doi":"10.1080/24725579.2022.2066740","DOIUrl":"https://doi.org/10.1080/24725579.2022.2066740","url":null,"abstract":"Abstract Mass vaccination plays an important role in increasing immunization against COVID-19 and decreasing morbidity. Drive-through and traditional walk-through centers have been set up in most cities in the United States and other countries to vaccinate large numbers of people in a short period of time. This article focuses on a pair of mass vaccination clinics conducted on a mid-sized, public university campus. Applying tools from Industrial Engineering, including time study, flow charts, and Queuing Theory, the team identified improvements that resulted in a 40% reduction in the duration of the second clinic while vaccinating almost the same number of patients with no increases in overall staffing. The work resulted in a model for designing mass vaccination clinics in the future and demonstrates that engineers have the ability to support healthcare personnel to increase the performance of the vaccination centers. The inclusion of engineering in the planning and execution of these vaccination clinics can help maximize clinic capacity, reduce the staff and resources needed, and reduce the patients’ waiting time.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"12 1","pages":"275 - 287"},"PeriodicalIF":0.0,"publicationDate":"2022-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48078983","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":"Ambulance dispatching and relocation problem considering overcrowding of emergency departments","authors":"M. Yavari, R. Maihami, Mahdis Esmaeili","doi":"10.1080/24725579.2022.2064008","DOIUrl":"https://doi.org/10.1080/24725579.2022.2064008","url":null,"abstract":"Abstract An important issue in emergency medical services (EMS) is ambulance dispatching and relocation. EMS response time is usually measured by the response time of an ambulance (RTA), the time between receiving a call and the ambulance's arrival at the scene. EMS's success also depends on response time to the patient (RTP), the time between receiving a call and starting the service to the patient in a hospital. This study aims to use RTP to decide about ambulance dispatching and relocation. RTP is affected by the distance of the patient to the chosen hospital and the crowding in the hospital. Thus, this study integrates ambulance dispatching and relocation with hospital selection to better provide both RTA and RTP along with coverage while considering an overcrowded emergency department (ED). A mixed-integer linear programming model is developed to solve the proposed problem. The model's performance and the impact of the ED overcrowding factor have been examined in the context of a real case study from Utrecht, Netherlands. Findings reveal that considering RTP in joint ambulance dispatching and relocation has a 39% positive impact on the patient's average response time. Further, considering ED crowding with RTP results in 91% and 9% improvement in RTP and RTA with the same demand coverage, compared to typical ambulance dispatching and relocation problems, respectively.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"12 1","pages":"263 - 274"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42942010","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":"Valuation of hospital resources: an optimization approach using clearing functions","authors":"P. Sutterer, R. Kolisch, R. Uzsoy","doi":"10.1080/24725579.2022.2055236","DOIUrl":"https://doi.org/10.1080/24725579.2022.2055236","url":null,"abstract":"Abstract We propose an approach to estimating the time-dependent marginal values of hospital resources facing heterogeneous patient demand over time using the dual variables of a novel dynamic patient admission and flow planning model maximizing hospital revenue. Clearing functions are used to represent the queuing behavior of the patients within the hospital. Using a large data set containing 17,483 patients treated over one year in a 400-bed hospital, we undertake a computational study where we derive the value of hospital resources under different demand and resource scenarios. Our results show that large instances of the model can be solved in reasonable CPU times, and that the model yields resource valuations that are qualitatively different from conventional approaches ignoring queueing costs.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"12 1","pages":"245 - 262"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41847188","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":"Prognosis of Epileptic Seizure Event Onsets Using Random Survival Forests","authors":"K. Afrin, Revanth Dusi, Yuhao Zhong, D. Reddy, S. Bukkapatnam","doi":"10.1080/24725579.2022.2051645","DOIUrl":"https://doi.org/10.1080/24725579.2022.2051645","url":null,"abstract":"Abstract This article introduces a machine learning approach, based on a nonparametric, decision-tree-based random survival forest (RSF) model, for a continuous prognosis of epileptic seizure events using electroencephalogram (EEG) data. While earlier seizure prediction methods forecast seizure occurrences only at a specified future time, the RSF model allows estimation of the probability of seizure onset, in terms of a hazard function, over the entire prediction horizon. These estimates are crucial for developing individualized quantitative risk measures and management plans for epilepsy patients. Additionally, RSF can identify the key risk factors by capturing the interdependencies among the features extracted from EEG data. The performance of RSF was evaluated for prognosing seizure onsets of the rat and mice specimens in an 80 small animals cohort at the Texas A&M Department of Neuroscience and Experimental Therapeutics. The results suggest that RSF outperforms other contemporary survival models, including the popular Cox proportional hazard, with 87.5% lower integrated Brier Score (IBS) errors, and 17.5% higher concordance index (C-index). Further, a continuous seizure prediction sensitivity of 83% and specificity of 87% were obtained even over a 5-min prediction horizon (the average time between successive seizure onsets was 5 min long). These results suggest that the RSF model can be used to effectively quantify the likelihood of seizure onsets over time to the patients and caregivers, promoting informed decision making.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"12 1","pages":"221 - 231"},"PeriodicalIF":0.0,"publicationDate":"2022-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44515627","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":"Hospital selection and patient transport model in the emergency medical system","authors":"Álvaro Junior Caicedo-Rolón, J. J. Bravo-Bastidas, Leonardo Rivera-Cadavid","doi":"10.1080/24725579.2022.2053926","DOIUrl":"https://doi.org/10.1080/24725579.2022.2053926","url":null,"abstract":"Abstract We designed a model for hospital selection and patient transport in the emergency medical system. The model integrates the criterium of insurance coverage, seldom used in the literature and the usual criteria such as care capacities, congestion and proximity, typical of countries with mixed health systems (public-private). In addition, the model considered the travel and waiting times in emergency departments as performance measures in different time slots and days of the week. We developed and implemented a prototype in the Python programming language connecting to web services from Google Maps API (Directions, Maps JavaScript) to support the decision-making process in real-time and tested its performance. This research study validated the model with actual data from events managed by the emergency medical system in a Colombian city. We used Monte Carlo simulation to predict the current and proposed models’ travel and transfer time (travel time + waiting time). The simulation results indicate that the proposed model, which considers insurance coverage, emergency departments capacities, congestion and proximity, has a lower probability of putting at risk the lives of critically ill patients. In addition, non-critical patient satisfaction increases as wait times decrease.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"12 1","pages":"232 - 244"},"PeriodicalIF":0.0,"publicationDate":"2022-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44826739","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":"Innovative use of operational tools to improve care delivery for the uninsured ESRD patients and to inform healthcare policy-makers","authors":"F. Nourbakhsh, Olga Bountali, S. Çetinkaya","doi":"10.1080/24725579.2022.2032486","DOIUrl":"https://doi.org/10.1080/24725579.2022.2032486","url":null,"abstract":"Abstract End-stage renal disease (ESRD) is a direful diagnosis for which regular (i.e., periodically scheduled) dialysis is typically the only immediate and accessible treatment. ESRD patients who are uninsured are in a high-risk category as they do not have access to regular treatment and have to rely on safety-net hospitals, funded by county governments, for access to dialysis. Since no national funding provides scheduled dialysis to this population, their only option is to seek dialysis under “emergency” conditions. These conditions are such that without urgent medical attention in the Emergency Room (ER), the patient’s life is under threat. Hence, ER serves as a screening stage for gaining access to regular dialysis by the uninsured, and the resulting practice is known as “compassionate dialysis,” a type of emergent dialysis treatment frequently offered at county hospitals serving uninsured ESRD patients. For a typical compassionate dialysis practice, existing county policy is such that patients are subject to a screening protocol upon arrival in the ER. The protocol serves to assess the severity of the patients’ condition in the ER, and, hence, a certain fraction of the patients may not be offered treatment, i.e., these patients have to revisit the hospital at a later time, potentially within a few hours due to the nature of the underlying disease. The fraction of patients not offered the treatment is referred to as the screening threshold. As documented in the literature, the practice is costly and leads to significant congestion and treatment delays. Motivated by a real-life compassionate dialysis practice, we employ process flow mapping to gain a better understanding of the patient flow and identify inefficiencies and bottlenecks caused by the screening protocol of the existing county policy. We use simulation modeling to examine and estimate various system and patient-oriented metrics as a function of stochastic arrival rates and service times. Our eventual goal is to explore and analyze two proposals as alternatives to the current practice: one modifies the existing screening threshold based on the available capacity, and the other schedules and consolidates the future revisits of patients. We analyze and compare the effectiveness of both proposals using simulation optimization approaches. Ultimately, our goal is to propose solutions for alleviating congestion and treatment delays, and to inform hospital administrators and policy-makers about such solutions.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"12 1","pages":"193 - 211"},"PeriodicalIF":0.0,"publicationDate":"2022-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43987671","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":"Optimization of sliding windows IMRT treatment planning","authors":"Rafiq R. Habib, Jessie Yeung, J. Darko, E. Osei, H. Mahmoudzadeh","doi":"10.1080/24725579.2022.2027051","DOIUrl":"https://doi.org/10.1080/24725579.2022.2027051","url":null,"abstract":"Abstract Intensity-modulated radiation therapy (IMRT) with sliding windows is a form of radiation therapy that delivers precise radiation dose to a tumor/target region. It uses a multi-leaf collimator (MLC) to move pairs of unidirectional tungsten leaves across a radiation emitting region to conform the shape of the radiation beam to the target regions. This is a dynamic treatment approach which aims to deliver adequate radiation dose to target regions while minimizing radiation delivery to healthy tissues. This paper proposes a linear optimization model for IMRT with sliding windows. This model directly incorporates a number of deliverability constraints to conform to physical limitations of the LINAC, including the required distance between leaves through the treatment process and restrictions on leaf interdigitation. We demonstrate the viability of this model using patient data and discuss the leaf motion proposed by our model. Such a model can be embedded in treatment planning systems to improve both the quality of the treatment and the efficiency of the treatment planning process.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"12 1","pages":"180 - 192"},"PeriodicalIF":0.0,"publicationDate":"2022-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44070555","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 mask-guided attention deep learning model for COVID-19 diagnosis based on an integrated CT scan images database","authors":"Maede Maftouni, Bo Shen, A. C. Law, N. Ayoobi Yazdi, Zhen Kong","doi":"10.1080/24725579.2022.2142866","DOIUrl":"https://doi.org/10.1080/24725579.2022.2142866","url":null,"abstract":"Abstract The global extent of COVID-19 mutations and the consequent depletion of hospital resources highlighted the necessity of effective computer-assisted medical diagnosis. COVID-19 detection mediated by deep learning models can help diagnose this highly contagious disease and lower infectivity and mortality rates. Computed tomography (CT) is the preferred imaging modality for building automatic COVID-19 screening and diagnosis models. It is well-known that the training set size significantly impacts the performance and generalization of deep learning models. However, accessing a large dataset of CT scan images from an emerging disease like COVID-19 is challenging. Therefore, data efficiency becomes a significant factor in choosing a learning model. To this end, we present a multi-task learning approach, namely, a mask-guided attention (MGA) classifier, to improve the generalization and data efficiency of COVID-19 classification on lung CT scan images. The novelty of this method is compensating for the scarcity of data by employing more supervision with lesion masks, increasing the sensitivity of the model to COVID-19 manifestations, and helping both generalization and classification performance. Our proposed model achieves better overall performance than the single-task (without MGA module) baseline and state-of-the-art models, as measured by various popular metrics.","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"13 1","pages":"132 - 149"},"PeriodicalIF":0.0,"publicationDate":"2022-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46953667","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":"Gradient Boosted Trees for Spatial Data and Its Application to Medical Imaging Data.","authors":"Reza Iranzad,&nbsp;Xiao Liu,&nbsp;W Art Chaovalitwongse,&nbsp;Daniel Hippe,&nbsp;Shouyi Wang,&nbsp;Jie Han,&nbsp;Phawis Thammasorn,&nbsp;Chunyan Duan,&nbsp;Jing Zeng,&nbsp;Stephen Bowen","doi":"10.1080/24725579.2021.1995536","DOIUrl":"10.1080/24725579.2021.1995536","url":null,"abstract":"<p><p>Boosting Trees are one of the most successful statistical learning approaches that involve sequentially growing an ensemble of simple regression trees (\"weak learners\"). This paper proposes a gradient Boosted Trees algorithm for Spatial Data (Boost-S) with covariate information. Boost-S integrates the spatial correlation into the classical framework of eXtreme Gradient Boosting. Each tree is constructed by solving a regularized optimization problem, where the objective function takes into account the underlying spatial correlation and involves two penalty terms on tree complexity. A computationally-efficient greedy heuristic algorithm is proposed to obtain an ensemble of trees. The proposed Boost-S is applied to the spatially-correlated FDG-PET (fluorodeoxyglucose-positron emission tomography) imaging data collected from clinical trials of cancer chemoradiotherapy. Our numerical investigations successfully demonstrate the advantages of the proposed Boost-S over existing approaches for this particular application.</p>","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"12 3","pages":"165-179"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9615557/pdf/nihms-1803573.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10460412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}