Anahita Khojandi

Optimal planning of life-depleting maintenance activities

This article considers a system with a deterministic initial lifetime that generates reward at a decreasing rate as its virtual age increases. Maintenance can be performed to reduce the virtual age of the system; however, maintenance also shortens the remaining lifetime of the system. Given this tradeoff, the lifetime reward-maximizing maintenance policies under perfect maintenance for non-failure-prone systems, and both perfect and imperfect maintenance for failure-prone systems are analyzed. For each combination considered, structural properties of the resulting optimal policies are derived and exploited to develop solution techniques. Insightful numerical examples are also provided.

From Data to Improved Decisions: Operations Research in Healthcare Delivery

Background. The Operations Research Interest Group (ORIG) within the Society of Medical Decision Making (SMDM) is a multidisciplinary interest group of professionals that specializes in taking an analytical approach to medical decision making and healthcare delivery. ORIG is interested in leveraging mathematical methods associated with the field of Operations Research (OR) to obtain data-driven solutions to complex healthcare problems and encourage collaborations across disciplines. This paper introduces OR for the non-expert and draws attention to opportunities where OR can be utilized to facilitate solutions to healthcare problems. Methods. Decision making is the process of choosing between possible solutions to a problem with respect to certain metrics. OR concepts can help systematically improve decision making through efficient modeling techniques while accounting for relevant constraints. Depending on the problem, methods that are part of OR (e.g., linear programming, Markov Decision Processes) or methods that are derived from related fields (e.g., regression from statistics) can be incorporated into the solution approach. This paper highlights the characteristics of different OR methods that have been applied to healthcare decision making and provides examples of emerging research opportunities. Examples. We illustrate OR applications in healthcare using previous studies, including diagnosis and treatment of diseases, organ transplants, and patient flow decisions. Further, we provide a selection of emerging areas for utilizing OR. Conclusions. There is a timely need to inform practitioners and policy makers of the benefits of using OR techniques in solving healthcare problems. OR methods can support the development of sustainable long-term solutions across disease management, service delivery, and health policies by optimizing the performance of system elements and analyzing their interaction while considering relevant constraints.

Dynamic Abandon/Extract Decisions for Failed Cardiac Leads

When a cardiac lead fails, physicians implant a new lead and may opt to extract the failed lead and/or any previously abandoned leads. Because the risk of extraction increases in lead age, physicians may extract leads to reduce the future risk of mandatory extraction, due to either infection or limited space in the vein. We develop discrete-time semi-Markov decision process models for various types of cardiac devices to determine patient-specific, lifetime-maximizing extraction policies as a function of patient age and the age of every implanted lead. We use clinical data to calibrate these models and present insightful numerical results, including comparisons to policies commonly used in practice. Our numerical experiments suggest that extracting failed leads only when forced to because of space limitations is usually a good rule of thumb, but that following the optimal policy, as opposed to the commonly used heuristic policies, can extend an average patient’s expected lifetime by up to 1.2 years and dec...

Optimal Implantable Cardioverter Defibrillator (ICD) Generator Replacement

Implantable cardioverter defibrillators (ICDs) include small, battery-powered generators, the longevity of which depends on a patients rate of consumption. Generator replacement, however, involves risks, including death. Hence, a trade-off exists between prematurely exposing the patient to these risks and allowing for the possibility that the device is unable to deliver therapy when needed. Currently, replacements are performed using a one-size-fits-all approach. Here, we develop a Markov decision process model to determine patient-specific optimal replacement policies as a function of patient age and the remaining battery capacity. We analytically establish that the optimal policy is of threshold-type in the remaining capacity, but not necessarily in patient age. Based on clinical data, we conduct a large computational study that suggests that under the optimal policy, patients undergoing initial implantation at age 30--40, 41--60, and 61--80 see an approximate decrease in the total expected number of replacements of 8%--14%, 8%--15% and 8%--19%, respectively, while achieving the same or greater expected lifetime.

Stratifying Parkinson's Patients With STN‐DBS Into High‐Frequency or 60 Hz‐Frequency Modulation Using a Computational Model

High frequency stimulation (HFS) of the subthalamic nucleus (STN) is a well‐established therapy for Parkinsons disease (PD), particularly the cardinal motor symptoms and levodopa induced motor complications. Recent studies have suggested the possible role of 60 Hz stimulation in STN‐deep brain stimulation (DBS) for patients with gait disorder. The objective of this study was to develop a computational model, which stratifies patients a priori based on symptomatology into different frequency settings (i.e., high frequency or 60 Hz).

Physiomarkers in Real-Time Physiological Data Streams Predict Adult Sepsis Onset Earlier Than Clinical Practice

Rationale: Sepsis is a life-threatening condition with high mortality rates and expensive treatment costs. To improve short- and long-term outcomes, it is critical to detect at-risk sepsis patients at an early stage. Objective: Our primary goal was to develop machine learning models capable of predicting sepsis using streaming physiological data in real-time. Methods: A dataset consisting of high-frequency physiological data from 1,161 critically ill patients admitted to the intensive care unit (ICU) was analyzed in this IRB-approved retrospective observational cohort study. Of that total, 634 patients were identified to have developed sepsis. In this paper, we define sepsis as meeting the Systemic Inflammatory Response Syndrome (SIRS) criteria in the presence of the suspicion of infection. In addition to the physiological data, we include white blood cell count (WBC) to develop a model that can signal the future occurrence of sepsis. A random forest classifier was trained to discriminate between sepsis and non-sepsis patients using a total of 108 features extracted from 2-hour moving time-windows. The models were trained on 80% of the patients and were tested on the remaining 20% of the patients, for two observational periods of lengths 3 and 6 hours. Results: The models, respectively, resulted in F1 scores of 75% and 69% half-hour before sepsis onset and 79% and 76% ten minutes before sepsis onset. On average, the models were able to predict sepsis 210 minutes (3.5 hours) before the onset. Conclusions: The use of robust machine learning algorithms, continuous streams of physiological data, and WBC, allows for early identification of at-risk patients in real-time with high accuracy.

Optimizing clinical assessments in Parkinson's disease through the use of wearable sensors and data driven modeling

The emergence of motion sensors as a tool that provides objective motor performance data on individuals afflicted with Parkinsons disease offers an opportunity to expand the horizon of clinical care for this neurodegenerative condition. Subjective clinical scales and patient based motor diaries have limited clinometric properties and produce a glimpse rather than continuous real time perspective into motor disability. Furthermore, the expansion of machine learn algorithms is yielding novel classification and probabilistic clinical models that stand to change existing treatment paradigms, refine the application of advance therapeutics, and may facilitate the development and testing of disease modifying agents for this disease. We review the use of inertial sensors and machine learning algorithms in Parkinsons disease.

Automatic EEG classification: a path to smart and connected sleep interventions

We develop a random forest classifier to automatically classify brain waves into sleep stages by using the publicly available data from PhysioBank. More specifically, we use the EEG signals from a single pair of electrodes (FPz–Cz) recorded from 20 patients and evaluate the impact of data balancing and incorporating signal history on classification results. The accuracy of the model is objectively evaluated using leave-one-out cross-validation. The developed model achieves the mean accuracy of 0.74, with that of the individual sleep stages ranging from 0.65 to 0.91. Next, we leverage this online sleep scoring scheme to introduce dynamic interventions as sleep process evolves over night. We develop a semi-Markov decision process model to determine optimal intervention policies to minimize the gap between the amount of sleep experienced in different stages and predetermined targets and provide computational results.

How much data should we collect? A case study in sepsis detection using deep learning

Sepsis is an acute, life-threatening condition that results from bacterial infections, often acquired in the hospital. Undetected, sepsis can progress to severe sepsis and septic shock, with a risk of death as high as 30% to 80%. Early detection of sepsis can improve patient outcomes. Collecting and evaluating continuous physiological variables, such as vital signs, using sophisticated classification algorithms may be highly beneficial to aid diagnosis of septic patients. However, setting up a data acquisition system that can collect (and store) high frequency/high volume data is challenging both from technology management and storage standpoints. In this paper, we build two deep learning models, a convolutional neural network and a multilayer perceptron model, to classify patients into sepsis and non-sepsis groups using data collected at various frequencies from the first 12 hours after admission. Our results indicate that the convolutional neural network model outperforms the multilayer perceptron model for all data collection frequencies. In addition, our results put into perspective the value of data collection frequency and translate its value into lives saved. Such analysis can guide future investments in data acquisition systems by hospitals.