Manuscripts by Vitaly Herasevich
Objective: The application of computer models in continuous patient activity monitoring using vid... more Objective: The application of computer models in continuous patient activity monitoring using video cameras is complicated by the capture of images of varying qualities due to poor lighting conditions and lower image resolutions. Insufficient literature has assessed the effects of image resolution, color depth, noise level, and low light on the inference of eye opening and closing and body landmarks from digital images. Method: This study systematically assessed the effects of varying image resolutions (from 100 × 100 pixels to 20 × 20 pixels at an interval of 10 pixels), lighting conditions (from 42 to 2 lux with an interval of 2 lux), color-depths (from 16.
This study aims to design, validate and assess the accuracy a deep learning model capable of diff... more This study aims to design, validate and assess the accuracy a deep learning model capable of differentiation Chest X-Rays between pneumonia, acute respiratory distress syndrome (ARDS) and normal lungs. Materials and methods: A diagnostic performance study was conducted using Chest X-Ray images from adult patients admitted to a medical intensive care unit between January 2003 and November 2014. X-ray images from 15,899 patients were assigned one of three prespecified categories: "ARDS", "Pneumonia", or "Normal". Results: A two-step convolutional neural network (CNN) pipeline was developed and tested to distinguish between the three patterns with sensitivity ranging from 91.8% to 97.8% and specificity ranging from 96.6% to 98.8%. The CNN model was validated with a sensitivity of 96.3% and specificity of 96.6% using a previous dataset of patients with Acute Lung Injury (ALI)/ARDS. Discussion: The results suggest that a deep learning model based on chest x-ray pattern recognition can be a useful tool in distinguishing patients with ARDS from patients with normal lungs, providing faster results than digital surveillance tools based on text reports. Conclusion: A CNN-based deep learning model showed clinically significant performance, providing potential for faster ARDS identification. Future research should prospectively evaluate these tools in a clinical setting.
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Background Intensive care unit (ICU) clinicians encounter frequent challenges with managing vast ... more Background Intensive care unit (ICU) clinicians encounter frequent challenges with managing vast amounts of fragmented data while caring for multiple critically ill patients simultaneously. This may lead to increased provider cognitive load that may jeopardize patient safety. Objectives This systematic review assesses the impact of centralized multipatient dashboards on ICU clinician performance, perceptions regarding the use of these tools, and patient outcomes. Methods A literature search was conducted on February 9, 2023, using the EBSCO CINAHL, Cochrane Central Register of Controlled Trials, Embase, IEEE Xplore, MEDLINE, Scopus, and Web of Science Core Collection databases. Eligible studies that included ICU clinicians as participants and tested the effect of dashboards designed for use by multiple users to manage multiple patients on user performance and/or satisfaction compared with the standard practice. We narratively synthesized eligible studies following the SWiM (Synthesis Without Meta-analysis) guidelines. Studies were grouped based on dashboard type and outcomes assessed. Results The search yielded a total of 2,407 studies. Five studies met inclusion criteria and were included. Among these, three studies evaluated interactive displays in the ICU, one study assessed two dashboards in the pediatric ICU (PICU), and one study examined centralized monitor in the PICU. Most studies reported several positive outcomes, including reductions in data gathering time before rounds, a decrease in misrepresentations during multidisciplinary rounds, improved daily documentation compliance, faster decision-making, and user satisfaction. One study did not report any significant association. Conclusion The multipatient dashboards were associated with improved ICU clinician performance and were positively perceived in most of the included studies. The risk of
Point-of-Care Knowledge-Based Resource Needs of Clinicians
Applied Clinical Informatics, 2015
Clinical impact of delirium and antipsychotic therapy: 10-Year experience from a referral coronary care unit
European heart journal. Acute cardiovascular care, Jan 29, 2015
Little is known about safety of antipsychotic therapy for delirium in the coronary care unit (CCU... more Little is known about safety of antipsychotic therapy for delirium in the coronary care unit (CCU). Our aim was to examine the effect of delirium and antipsychotic therapy among CCU patients. Pre-study Confusion Assessment Method-Intensive Care Unit (CAM-ICU) criteria were implemented in screening consecutive patients admitted to a referral CCU from 2004-2013. Death status was prospectively ascertained. Of 11,079 study patients, the incidence of delirium was 8.3% (n=925). Delirium was associated with an increased risk of in-hospital mortality (adjusted odds ratio (OR) 1.49; 95% confidence interval (CI), 1.08-2.08; p=0.02) and one-year mortality among patients who survived from CCU admission (adjusted hazard ratio (HR) 1.46; 95% CI, 1.12-1.87; p=0.005). A total of 792 doses of haloperidol (5 mg/day; interquartile range (IQR) 3-10) or quetiapine (25 mg/day; IQR 13-50) were given to 244 patients with delirium. The clinical characteristics of patients with delirium who did and did not r...
Sniffing out acute kidney injury in the ICU: do we have the tools?
Current opinion in critical care, 2013
Acute kidney injury (AKI) is one of the most common complications of critical illnesses, and earl... more Acute kidney injury (AKI) is one of the most common complications of critical illnesses, and early detection of AKI can improve its outcome. Using advanced electronic surveillance tools has attracted attention in recent years. It is not a secret that information overload in clinical practice, particularly those that are admitted to ICUs, can decrease the ability of practitioners to identify changes in patients' status in a timely manner. On the contrary, knowing the impact of an early and accurate diagnosis of syndromes, such as AKI, on patients' outcomes makes the use of electronic syndromic surveillance (ESS) tools a mandate. In recent years, a number of such tools for early detection of AKI have been developed with variable sensitivity and specificity. Although the impact of using these tools on patients' outcomes is unclear, the time to the appropriate processes required for the care of AKI has been successfully shortened by the use of these devices. ESS tools (sniff...
The Netherlands journal of medicine, 2009
Acute lung injury (ALI ) and its more severe form, acute respiratory distress syndrome (ARDS ), a... more Acute lung injury (ALI ) and its more severe form, acute respiratory distress syndrome (ARDS ), are important critical care syndromes for which the treatment options are limited once the condition is fully established. Enormous basic and clinical research efforts have led to improvements in supportive treatment, but surprisingly little has been done on the prevention of this devastating syndrome. The development and progression of ALI /ARDS may be triggered by various intrahospital exposures including but not limited to transfusion, aspiration, mechanical ventilation, certain medications and delayed treatment of shock and infection. Early recognition of patients with or at risk of ALI /ARDS is essential for designing novel prevention and treatment strategies. Automated electronic screening tools and novel scoring systems applied at the time of hospital admission may facilitate enrollment of patients into mechanistic and outcome studies, as well as future ALI /ARDS prevention trials.
Designing and testing computer based screening engine for severe sepsis/septic shock
AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium, 2008
This study addresses the role of a sepsis "sniffer", an automatic screening tool for th... more This study addresses the role of a sepsis "sniffer", an automatic screening tool for the timely identification of patients with severe sepsis/septic shock, based electronic medical records. During the two months prospective implementation in a medical intensive care unit, 37 of 320 consecutive patients developed severe sepsis/septic shock. The sniffer demonstrated a sensitivity of 48% and specificity of 86%, and positive predictive value 32%. Further improvements are needed prior to the implementation of sepsis sniffer in clinical practice and research.
Rule base system for identification of patients with specific critical care syndromes: The "sniffer" for acute lung injury
AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium, 2007
Early detection of specific critical care syndromes, such as sepsis or acute lung injury (ALI)is ... more Early detection of specific critical care syndromes, such as sepsis or acute lung injury (ALI)is essential for timely implementation of evidence based therapies. Using a near-real time copy of the electronic medical records ("ICU data mart") we developed and validated custom electronic alert (ALI"sniffer") in a cohort of 485 critically ill medical patients. Compared with the gold standard of prospective screening, ALI "sniffer" demonstrated good sensitivity, 93% (95% CI 90 to 95) and specificity, 90% (95% CI 87 to 92). It is not known if the bedside implementation of ALI "sniffer" will improve the adherence to evidence-based therapies and outcome of patients with ALI.
Association Of Duration Of Antibiotics Use And Manifestation Of Clostridium Difficile In The Intensive Care Unit
A46. INTENSIVE CARE UNIT MANAGEMENT AND RAPID RESPONSE: PROVIDER AND PATIENT OUTCOMES, 2012
PREOPERATIVE ANGIOTENSIN I-CONVERTING ENZYME INHIBITOR/ANGIOTENSIN II RECEPTOR BLOCKER ADMINISTRATION IS ASSOCIATED WITH A REDUCED INCIDENCE OF EARLY POSTOPERATIVE ACUTE LUNG INJURY
CLINICAL ALERTS BEYOND SIMPLE DETECTION. ELECTRONIC SURVEILLANCE OF FAILURE TO RESCUE IN SEPTIC SHOCK
Stay tuned. Comparison of journal updates tracking using RSS and e-mail technologies
AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium, 2008
Electronic subscription alerts provide new possibilities for health care providers to stay abreas... more Electronic subscription alerts provide new possibilities for health care providers to stay abreast with current literature and practice evidence-based medicine. During a 5 month prospective observation we compared the performance of the three common subscription methods: email and Really Simple Syndication (RSS) from the publisher and RSS from PubMed. The 3 methods were reliably updated without interruption in service but demonstrated significant variability in the contents and timing.
Bosnian journal of basic medical sciences / Udruženje basičnih mediciniskih znanosti = Association of Basic Medical Sciences, 2009
Multiple myeloma (MM) is the second most common hematologic malignancy and is invariably fatal (... more Multiple myeloma (MM) is the second most common hematologic malignancy and is invariably fatal (,). Each year,, new cases of MM are diagnosed, resulting in nearly, deaths annually (). Despite available therapies such as high-dose chemotherapy and autologous stem cell transplantation (ASCT), MM remains an incurable disease with a median survival of to years depending on disease stage (), and a-year relative survival rate of approximately(). The role of high-dose chemotherapy and ...
UTILIZATION OF ICU SERVICES IN A SUBURBAN COMMUNITY A RETROSPECTIVE POPULATION-BASED STUDY
FREQUENCY AND OUTCOME OF ACUTE LUNG INJURY IN PATIENTS WITH PNEUMONIA ADMITTED TO THE INTENSIVE CARE UNIT: POPULATION BASED STUDY
USING INFORMATION TECHNOLOGY TO REDUCE TIME SPENT DATA GATHERING IN THE INTENSIVE CARE UNIT
Management And Outcomes Of Severe Sepsis And Septic Shock In Patients With Pre-Existing Non-Cardiac Pulmonary Hypertension
To review treatment and outcomes of septic shock in patients with pulmonary hypertension (PH) man... more To review treatment and outcomes of septic shock in patients with pulmonary hypertension (PH) managed at a tertiary care institution. We identified consecutive patients with non-cardiac PH (non-Group 2 in the World Health Organization classification) who were treated for septic shock in four intensive care units at a tertiary care institution between July 2004 and July 2007. Patients with a left ventricular ejection fraction < 50%, diastolic dysfunction, pericardial effusion or significant valve disease were excluded. Descriptive statistics were used to analyse the data. Hospital mortality, duration of vasopressor and ventilatory support, length of hospital and ICU stay. The final group for analysis comprised 82 patients. The major causes of PH were chronic obstructive pulmonary disease, interstitial lung disease and portopulmonary hypertension. PH was mild in 46 patients (56%), moderate in 21 (26%) and severe in 15 (18%). Vasopressor treatment was initiated in 69 patients (84%) within the first 48 hours: noradrenaline was most commonly used (53 patients, 65%), and 51 patients (62%) were treated with more than one agent. Sixty-seven patients (82%) were mechanically ventilated, and 33 (40%) required renal replacement therapy. Fortythree patients (52%) survived to hospital discharge; 23 (28%) remained alive at 1 year. Hospital mortality increased with severity of PH: 28% in mild, 67% in moderate and 80% in severe PH. Nonsurvivors were more likely to have plateau pressures beyond 30 cm H(2)O while mechanically ventilated within the first 48 hours in the ICU (56% v 29%, P = 0.03), to develop atrial fibrillation (AF) (46% v 12%, P < 0.001), and to require longer vasopressor support (mean, 5.3 v 2.6 days, P = 0.003). In a multivariate logistic regression analysis, severity of PH (odds ratio [OR], 1.55; 95% CI, 1.04-2.46; P = 0.04), new-onset AF (OR, 6.51; 95% CI, 2.24-22.07; P < 0.001) and longer duration of vasopressor support (OR, 1.15; 95% CI, 1.03-1.34; P = 0.04) were associated with increased hospital mortality. The severity of PH, new-onset AF, and longer vasopressor support were associated with poor outcomes in patients with PH who developed severe sepsis and septic shock.
AUTOMATIC MAPPING OF FREE TEXT CLINICAL NOTES TO STRUCTURED APACHE DIAGNOSES
Uploads
Manuscripts by Vitaly Herasevich