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

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.

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

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.

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)

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