Mihail Popescu - Academia.edu (original) (raw)

Papers by Mihail Popescu

Supplemental material, Appendix_B.rjf_online_supp for Use of Enhanced Data Visualization to Impro... more Supplemental material, Appendix_B.rjf_online_supp for Use of Enhanced Data Visualization to Improve Patient Judgments about Hypertension Control by Victoria A. Shaffer, Pete Wegier, K. D. Valentine, Jeffery L. Belden, Shannon M. Canfield, Mihail Popescu, Linsey M. Steege, Akshay Jain and Richelle J. Koopman in Medical Decision Making

Journal of the American Medical Informatics Association, Aug 4, 2022

Objective: To assess the impact of patient health literacy, numeracy, and graph literacy on perce... more Objective: To assess the impact of patient health literacy, numeracy, and graph literacy on perceptions of hypertension control using different forms of data visualization. Materials and Methods: Participants (Internet sample of 1079 patients with hypertension) reviewed 12 brief vignettes describing a fictitious patient; each vignette included a graph of the patient's blood pressure (BP) data. We examined how variations in mean systolic blood pressure, BP standard deviation, and form of visualization (eg, data table, graph with raw values or smoothed values only) affected judgments about hypertension control and need for medication change. We also measured patient's health literacy, subjective and objective numeracy, and graph literacy. Results: Judgments about hypertension data presented as a smoothed graph were significantly more positive (ie, hypertension deemed to be better controlled) then judgments about the same data presented as either a data table or an unsmoothed graph. Hypertension data viewed in tabular form was perceived more positively than graphs of the raw data. Data visualization had the greatest impact on participants with high graph literacy. Discussion: Data visualization can direct patients to attend to more clinically meaningful information, thereby improving their judgments of hypertension control. However, patients with lower graph literacy may still have difficulty accessing important information from data visualizations. Conclusion: Addressing uncertainty inherent in the variability between BP measurements is an important consideration in visualization design. Well-designed data visualization could help to alleviate clinical uncertainty, one of the key drivers of clinical inertia and uncontrolled hypertension.

American Medical Informatics Association Annual Symposium, 1998

PubMed, 2013

In this paper we propose a framework for detecting health patterns based on non-wearable sensor s... more In this paper we propose a framework for detecting health patterns based on non-wearable sensor sequence similarity and natural language processing (NLP). In TigerPlace, an aging in place facility from Columbia, MO, we deployed 47 sensor networks together with a nursing electronic health record (EHR) system to provide early illness recognition. The proposed framework utilizes sensor sequence similarity and NLP on EHR nursing comments to automatically notify the physician when health problems are detected. The reported methodology is inspired by genomic sequence annotation using similarity algorithms such as Smith Waterman (SW). Similarly, for each sensor sequence, we associate health concepts extracted from the nursing notes using Metamap, a NLP tool provided by Unified Medical Language System (UMLS). Since sensor sequences, unlike genomics ones, have an associated time dimension we propose a temporal variant of SW (TSW) to account for time. The main challenges presented by our framework are finding the most suitable time sequence similarity and aggregation of the retrieved UMLS concepts. On a pilot dataset from three Tiger Place residents, with a total of 1685 sensor days and 626 nursing records, we obtained an average precision of 0.64 and a recall of 0.37.

Wearable and non-wearable sensors are pervasive. However, the health implications of the data the... more Wearable and non-wearable sensors are pervasive. However, the health implications of the data they provide is not always clear for the user. In this paper we present a Decision Support System (DSS) that assists a user of a Home Blood Pressure (HBP) monitor to decide timely consultation with a doctor. While HBP is more reliable than office readings, it is more variable due to factors such as food, exercise or error in recording measurements. Our DSS is based on fuzzy rules composed of linguistic summaries of the data. The rules are designed from the current US clinical guidelines and are tuned using an evolutionary algorithm. On a dataset of 40 patients monitored over 3 months, we obtained an interrater agreement of 0.97 between the physicians and DSS trained with their data, while the average agreement between these same physicians was 0.95.

BACKGROUND Reducing avoidable nursing home (NH)–to-hospital transfers of residents with Alzheimer... more BACKGROUND Reducing avoidable nursing home (NH)–to-hospital transfers of residents with Alzheimer disease or a related dementia (ADRD) has become a national priority due to the physical and emotional toll it places on residents and the high costs to Medicare and Medicaid. Technologies supporting the use of clinical text messages (TMs) could improve communication among health care team members and have considerable impact on reducing avoidable NH-to-hospital transfers. Although text messaging is a widely accepted mechanism of communication, clinical models of care using TMs are sparsely reported in the literature, especially in NHs. Protocols for assessing technologies that integrate TMs into care delivery models would be beneficial for end users of these systems. Without evidence to support clinical models of care using TMs, users are left to design their own methods and protocols for their use, which can create wide variability and potentially increase disparities in resident outcomes. OBJECTIVE Our aim is to describe the protocol of a study designed to understand how members of the multidisciplinary team communicate using TMs and how salient and timely communication can be used to avert poor outcomes for NH residents with ADRD, including hospitalization. METHODS This project is a secondary analysis of data collected from a Centers for Medicare & Medicaid Services (CMS)–funded demonstration project designed to reduce avoidable hospitalizations for long-stay NH residents. We will use two data sources: (1) TMs exchanged among the multidisciplinary team across the 7-year CMS study period (August 2013-September 2020) and (2) an adapted acute care transfer tool completed by advanced practice registered nurses to document retrospective details about NH-to-hospital transfers. The study is guided by an age-friendly model of care called the 4Ms (What Matters, Medications, Mentation, and Mobility) framework. We will use natural language processing, statistical methods, and social network analysis to generate a new ontology and to compare communication patterns found in TMs occurring around the time NH-to-hospital transfer decisions were made about residents with and without ADRD. RESULTS After accounting for inclusion and exclusion criteria, we will analyze over 30,000 TMs pertaining to over 3600 NH-to-hospital transfers. Development of the 4M ontology is in progress, and the 3-year project is expected to run until mid-2025. CONCLUSIONS To our knowledge, this project will be the first to explore the content of TMs exchanged among a multidisciplinary team of care providers as they make decisions about NH-to-hospital resident transfers. Understanding how the presence of evidence-based elements of high-quality care relate to avoidable hospitalizations among NH residents with ADRD will generate knowledge regarding the future scalability of behavioral interventions. Without this knowledge, NHs will continue to rely on ineffective and outdated communication methods that fail to account for evidence-based elements of age-friendly care. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/50231

BMC Medical Informatics and Decision Making, Aug 5, 2021

Background: Home blood pressure measurements have equal or even greater predictive value than cli... more Background: Home blood pressure measurements have equal or even greater predictive value than clinic blood pressure measurements regarding cardiovascular outcomes. With advances in home blood pressure monitors, we face an imminent flood of home measurements, but current electronic health record systems lack the functionality to allow us to use this data to its fullest. We designed a data visualization display for blood pressure measurements to be used for shared decision making around hypertension. Methods: We used an iterative, rapid-prototyping, user-centred design approach to determine the most appropriate designs for this data display. We relied on visual cognition and human factors principles when designing our display. Feedback was provided by expert members of our multidisciplinary research team and through a series of end-user focus groups, comprised of either hypertensive patients or their healthcare providers required from eight academic, community-based practices in the Midwest of the United States. Results: A total of 40 participants were recruited to participate in patient (N = 16) and provider (N = 24) focus groups. We describe the conceptualization and development of data display for shared decision making around hypertension. We designed and received feedback from both patients and healthcare providers on a number of design elements that were reported to be helpful in understanding blood pressure measurements. Conclusions: We developed a data display for substantial amounts of blood pressure measurements that is both simple to understand for patients, but powerful enough to inform clinical decision making. The display used a line graph format for ease of understanding, a LOWESS function for smoothing data to reduce the weight users placed on outlier measurements, colored goal range bands to allow users to quickly determine if measurements were in range, a medication timeline to help link recorded blood pressure measurements with the medications a patient was taking. A data display such as this, specifically designed to encourage shared decision making between hypertensive patients and their healthcare providers, could help us overcome the clinical inertia that often results in a lack of treatment intensification, leading to better care for the 35 million Americans with uncontrolled hypertension.

Background: Uncontrolled hypertension is a significant health problem in the United States, even ... more Background: Uncontrolled hypertension is a significant health problem in the United States, even though multiple drugs exist to effectively treat this chronic disease. Objective: As part of a larger project developing data visualizations to support shared decision making about hypertension treatment, we conducted a series of studies to understand how perceptions of hypertension control were impacted by data variations inherent in the visualization of blood pressure (BP) data. Methods: In 3 Web studies, participants (internet sample of patients with hypertension) reviewed a series of vignettes depicting patients with hypertension; each vignette included a graph of a patient's BP. We examined how data visualizations that varied by BP mean and SD (Study 1), the pattern of change over time (Study 2), and the presence of extreme values (Study 3) affected patients' judgments about hypertension control and the need for a medication change. Results: Participants' judgments about hypertension control were significantly influenced by BP mean and SD (Study 1), data trends (whether BP was increasing or decreasing over time-Study 2), and extreme values (ie, outliers-Study 3). Conclusions: Patients' judgment about hypertension control is influenced both by factors that are important predictors of hypertension related-health outcomes (eg, BP mean) and factors that are not (eg, variability and outliers). This study highlights the importance of developing data visualizations that direct attention toward clinically meaningful information.

Journal of Medical Internet Research, Mar 26, 2019

Medical Decision Making, Jul 22, 2020

Objective:Uncontrolled hypertension is driven by clinical uncertainty around blood pressure data.... more Objective:Uncontrolled hypertension is driven by clinical uncertainty around blood pressure data. This research sought to determine whether decision support—in the form of enhanced data visualization—could improve judgments about hypertension control.Methods:Participants (Internet sample of patients with hypertension) in three studies (N=209) viewed graphs depicting blood pressure data for fictitious patients. For each graph, participants rated hypertension control, need for medication change, and perceived risk of heart attack and stroke. In Study 3, participants also recalled the percentage of blood pressure measurements outside of the goal range. The graphs varied by systolic blood pressure mean and standard deviation, change in blood pressure values over time, and data visualization type.Results:In all three studies, data visualization type significantly impacted judgments of hypertension control. In Study 1 and 2, perceived hypertension control was lower while perceived need for medication change and subjective perceptions of stroke and heart attack risk were higher for raw data displays compared with enhanced visualization that employed a smoothing function generated by the LOWESS algorithm. In general, perceptions of hypertension control were more closely aligned with clinical guidelines when data visualization included a smoothing function. However, conclusions were mixed when comparing tabular presentations of data to graphical presentations of data in Study 3. Hypertension was perceived to be less well controlled when data was presented in a graph rather than a table, but recall was more accurate.Conclusion:Enhancing data visualization with the use of a smoothing function to minimize the variability present in raw BP data significantly improved judgments about hypertension control. More research is needed to determine the contexts in which graphs are superior to data tables.

Living alone in their own residence, older adults are atrisk for late assessment of physical or c... more Living alone in their own residence, older adults are atrisk for late assessment of physical or cognitive changes due to many factors such as their impression that such changes are simply a normal part of aging or their reluctance to admit to a problem. Sensors networks have emerged in the last decade as a possible solution to older adult health monitoring and early illness recognition. Typical early illness recognition approaches are either concentrated on the detection of a given set of activities such as a fall or walks, or on the detection of anomalies such as too many bathroom visits. In this paper we propose a new illness recognition framework, MFA, based on detecting a missing frequent activity from the daily routine. MFA is implemented using a frequent temporal pattern detection algorithm and demonstrated on a pilot dataset collected in TigerPlace, an aging in place community from Columbia, Missouri.

IEEE Journal of Biomedical and Health Informatics, May 1, 2016

n the last decade, data mining techniques have been applied to sensor data in a wide range of app... more n the last decade, data mining techniques have been applied to sensor data in a wide range of application domains, such as healthcare monitoring systems, manufacturing processes, intrusion detection, database management and others. Many data mining techniques are based on computing the similarity between two sensor data patterns. A variety of representations and similarity measures for multi-attribute time series have been proposed in literature. In this paper, we describe a novel method for computing the similarity of two multi-attribute time series based on a temporal version of Smith-Waterman (SW), a wellknown bioinformatics algorithm. We then apply our method to sensor data from an eldercare application for early illness detection. Our method mitigates difficulties related to data uncertainty and aggregation that often arise when processing sensor data. The experiments take place at an aging-in-place facility, TigerPlace, located in Columbia, MO. To validate our method we used data from nine non-wearable sensor networks placed in TigerPlace apartments, combined with information from an Electronic Health Record (EHR). We provide a set of experiments that investigate temporal version of SW properties, together with experiments on TigerPlace datasets. On a pilot sensor dataset from nine residents, with a total of 1902 days and around 2.1 million sensor hits of collected data, we obtained an average abnormal events prediction F-measure of 0.75.

Frontiers in Digital Health

Older adults aged 65 and above are at higher risk of falls. Predicting fall risk early can provid... more Older adults aged 65 and above are at higher risk of falls. Predicting fall risk early can provide caregivers time to provide interventions, which could reduce the risk, potentially avoiding a possible fall. In this paper, we present an analysis of 6-month fall risk prediction in older adults using geriatric assessments, GAITRite measurements, and fall history. The geriatric assessments included were Activities of Daily Living (ADL), Instrumental Activities of Daily Living (IADL), Mini-Mental State Examination (MMSE), Geriatric Depression Scale (GDS), and Short Form 12 (SF12). These geriatric assessments are collected by staff nurses regularly in senior care facilities. From the GAITRite assessments on the residents, we included the Functional Ambulatory Profile (FAP) scores and gait speed to predict fall risk. We used the SHAP (SHapley Additive exPlanations) approach to explain our model predictions to understand which predictor variables contributed to increase or decrease the fal...

2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

many people. In particular, I would like to thank Dr. James Keller for being my advisor and invol... more many people. In particular, I would like to thank Dr. James Keller for being my advisor and involving me in this particular research. I am grateful for his advice, time and patience during the writing of this thesis and throughout my research. Thank you Dr. Marjorie Skubic for agreeing to be on my committee and for everything I have learned from her classes. One of my very first class at MU was Dr. Skubic' s Building Intelligent Robot class, which, I would still like to say, is the most exciting and inspiring class I have ever had. Thanks are due to Dr. Mihail Popescu for agreeing to be on my committee. I would also like to thank my parents and my friends for their ceaseless support, without which this could not happen.

Frontiers in Physiology

Purpose: This study proposes a novel approach to obtain personalized estimates of cardiovascular ... more Purpose: This study proposes a novel approach to obtain personalized estimates of cardiovascular parameters by combining (i) electrocardiography and ballistocardiography for noninvasive cardiovascular monitoring, (ii) a physiology-based mathematical model for predicting personalized cardiovascular variables, and (iii) an evolutionary algorithm (EA) for searching optimal model parameters.Methods: Electrocardiogram (ECG), ballistocardiogram (BCG), and a total of six blood pressure measurements are recorded on three healthy subjects. The R peaks in the ECG are used to segment the BCG signal into single BCG curves for each heart beat. The time distance between R peaks is used as an input for a validated physiology-based mathematical model that predicts distributions of pressures and volumes in the cardiovascular system, along with the associated BCG curve. An EA is designed to search the generation of parameter values of the cardiovascular model that optimizes the match between model-pr...

ACM Transactions on Computing for Healthcare, 2021

The rapid aging of the population worldwide requires increased attention from healthcare provider... more The rapid aging of the population worldwide requires increased attention from healthcare providers and the entire society. For the elderly to live independently, many health issues related to old age, such as frailty and risk of falling, need increased attention and monitoring. When monitoring daily routines for older adults, it is desirable to detect the early signs of health changes before serious health events, such as hospitalizations, happen so that timely and adequate preventive care may be provided. By deploying multi-sensor systems in homes of the elderly, we can track trajectories of daily behaviors in a feature space defined using the sensor data. In this article, we investigate a methodology for tracking the evolution of the behavior trajectories over long periods (years) using high-dimensional streaming clustering and provide very early indicators of changes in health. If we assume that habitual behaviors correspond to clusters in feature space and diseases produce a cha...

2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2021

The time interval between the peaks in the electroccardiogram (ECG) and ballistocardiogram (BCG) ... more The time interval between the peaks in the electroccardiogram (ECG) and ballistocardiogram (BCG) waveforms, TEB, has been associated with the pre-ejection period (PEP), which is an important marker of ventricular contractility. However, the applicability of BCG-related markers in clinical practice is limited by the difficulty to obtain a replicable and consistent signal on patients. In this study, we test the feasibility of BCG measurements within a complex clinical setting, by means of an accelerometer under the head pillow of patients admitted to the Surgical Intensive Care Unit (SICU). The proposed technique proved capable of capturing TEB based on the R peaks in the ECG and the BCG in its head-totoe and dorso-ventral directions. TEB detection was found to be consistent and repeatable both in healthy individuals and SICU patients over multiple data acquisition sessions. This work provides a promising starting point to investigate how TEB changes may relate to the patients' complex health conditions and give additional clinical insight into their care needs.