4.1 Article

Monitoring Dressing Activity Failures through RFID and Video

Journal

METHODS OF INFORMATION IN MEDICINE
Volume 51, Issue 1, Pages 45-54

Publisher

GEORG THIEME VERLAG KG
DOI: 10.3414/ME10-02-0026

Keywords

Pervasive healthcare; monitoring activities of daily living (ADL); assessing dressing activity

Funding

  1. Autonomous Province of Trento [ACube]
  2. NSF [0916687]
  3. Div Of Information & Intelligent Systems
  4. Direct For Computer & Info Scie & Enginr [0916687] Funding Source: National Science Foundation

Ask authors/readers for more resources

Background: Monitoring and evaluation of Activities of Daily Living in general, and dressing activity in particular, is an important indicator in the evaluation of the overall cognitive state of patients. In addition, the effectiveness of therapy in patients with motor impairments caused by a stroke, for example, can be measured through long-term monitoring of dressing activity. However, automatic monitoring of dressing activity has not received significant attention in the current literature. Objectives: Considering the importance of monitoring dressing activity, the main goal of this work was to investigate the possibility of recognizing dressing activities and automatically identifying common failures exhibited by patients suffering from motor or cognitive impairments. Methods: The system developed for this purpose comprised analysis of PHD (radio frequency identification) tracking and computer vision processing. Eleven test subjects, not connected to the research, were recruited and asked to perform the dressing task by choosing any combination of clothes without further assistance. Initially the test subjects performed correct dressing and then they were free to choose from a set of dressing failures identified from the current research literature. Results: The developed system was capable of automatically recognizing common dressing failures. In total, there were four dressing failures observed for upper garments and three failures for lower garments, in addition to recognizing successful dressing. The recognition rate for identified dressing failures was between 80% and 100%. Conclusions: We developed a robust system to monitor the dressing activity. Given the importance of monitoring the dressing activity as an indicator of both cognitive and motor skills the system allows for the possibility of long term tracking and continuous evaluation of the dressing task. Long term monitoring can be used in rehabilitation and cognitive skills evaluation.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.1
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Medicine, General & Internal

Underweight but not overweight is associated with excess mortality in septic ICU patients

Thomas Danninger, Richard Rezar, Behrooz Mamandipoor, Daniel Dankl, Andreas Kokoefer, Christian Jung, Bernhard Wernly, Venet Osmani

Summary: A study on septic ICU patients revealed that underweight patients had higher mortality rates, while obese patients showed lower mortality rates compared to normal weight individuals. There was no significant difference in ICU mortality between normal and overweight patients. The protective effect of obesity and negative effect of underweight were particularly significant in individuals over 65 years old.

WIENER KLINISCHE WOCHENSCHRIFT (2022)

Article Anesthesiology

Prediction of blood lactate values in critically ill patients: a retrospective multi-center cohort study

Behrooz Mamandipoor, Wesley Yeung, Louis Agha-Mir-Salim, David J. Stone, Venet Osmani, Leo Anthony Celi

Summary: Elevated initial serum lactate levels are strong predictors of mortality in critically ill patients, and machine learning models can accurately predict subsequent serum lactate changes. These models show good discrimination of patients with deteriorating serum lactate levels, suggesting their potential as decision support tools in clinical practice.

JOURNAL OF CLINICAL MONITORING AND COMPUTING (2022)

Article Computer Science, Artificial Intelligence

Deep ROC Analysis and AUC as Balanced Average Accuracy, for Improved Classifier Selection, Audit and Explanation

Andre M. Carrington, Douglas G. Manuel, Paul W. Fieguth, Tim Ramsay, Venet Osmani, Bernhard Wernly, Carol Bennett, Steven Hawken, Olivia Magwood, Yusuf Sheikh, Matthew McInnes, Andreas Holzinger

Summary: This paper proposes a new method called deep ROC analysis to evaluate the performance of binary classifiers and diagnostic tests. It provides more detailed information compared to traditional performance measures. The method measures the performance in multiple groups and allows comparisons between groups. The paper also offers a new interpretation of AUC as balanced average accuracy, relevant to individuals.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2023)

Article Medicine, General & Internal

Red Cell Distribution Width Is Independently Associated with Mortality in Sepsis

Daniel Dankl, Richard Rezar, Behrooz Mamandipoor, Zhichao Zhou, Sarah Wernly, Bernhard Wernly, Venet Osmani

Summary: This study validated the association between red cell distribution width (RDW) and mortality in septic patients. The results showed that high RDW was associated with higher hospital mortality and ICU mortality. The optimal RDW cutoff for predicting hospital mortality was determined to be 16%.

MEDICAL PRINCIPLES AND PRACTICE (2022)

Article Medical Informatics

Disease-Course Adapting Machine Learning Prognostication Models in Elderly Patients Critically III With COVID-19: Multicenter Cohort Study With External Validation

Christian Jung, Behrooz Mamandipoor, Jesper Fjolner, Raphael Romano Bruno, Bernhard Wernly, Antonio Artigas, Bernardo Bollen Pinto, Joerg C. Schefold, Georg Wolff, Malte Kelm, Michael Beil, Sigal Sviri, Peter van Heerden, Wojciech Szczeklik, Miroslaw Czuczwar, Muhammed Elhadi, Michael Joannidis, Sandra Oeyen, Tilemachos Zafeiridis, Brian Marsh, Finn H. Andersen, Rui Moreno, Maurizio Cecconi, Susannah Leaver, Dylan W. De Lange, Bertrand Guidet, Hans Flaatten, Venet Osmani

Summary: This study evaluated machine learning-based prognostication models for critically ill elderly COVID-19 patients. The results showed that integrating important clinical events and time-to-event information into the models improved the accuracy of predicting 30-day mortality, compared to models based on admission variables only and conventional ICU prediction models.

JMIR MEDICAL INFORMATICS (2022)

Article Medicine, General & Internal

Hyperlactatemia and altered lactate kinetics are associated with excess mortality in sepsis A multicenter retrospective observational study

Richard Rezar, Behrooz Mamandipoor, Clemens Seelmaier, Christian Jung, Michael Lichtenauer, Uta C. C. Hoppe, Reinhard Kaufmann, Venet Osmani, Bernhard Wernly

Summary: Severe hyperlactatemia (>10mmol/L) or impaired lactate metabolism are associated with increased mortality. A study analyzed the maximum lactate concentration on day 1 of 10,724 septic patients and categorized them into three groups based on lactate levels. Findings showed that severe hyperlactatemia was linked to high mortality rates, especially if it persists beyond 24 hours. The results suggest that severe hyperlactatemia, along with clinical parameters, could be used to determine treatment limits.

WIENER KLINISCHE WOCHENSCHRIFT (2023)

Article Infectious Diseases

The impact of ethnic background on ICU care and outcome in sepsis and septic shock - A retrospective multicenter analysis on 17,949 patients

Andreas Kokoefer, Behrooz Mamandipoor, Maria Flamm, Richard Rezar, Sarah Wernly, Christian Datz, Christian Jung, Venet Osmani, Bernhard Wernly, Raphael Romano Bruno

Summary: This study examined the impact of ethnic background on the management and outcome of sepsis and septic shock. The findings showed that there were no significant differences in treatment and mortality rates among different ethnic groups.

BMC INFECTIOUS DISEASES (2023)

Article Multidisciplinary Sciences

Investigating microstructure evolution of lithium metal during plating and stripping via operando X-ray tomographic microscopy

Matthew Sadd, Shizhao Xiong, Jacob R. Bowen, Federica Marone, Aleksandar Matic

Summary: Tracking the plating and stripping behaviours of lithium metal in real time using operando synchrotron X-ray tomographic microscopy reveals the formation of inactive lithium microstructures. Efficient lithium metal stripping and plating operation is crucial for safe lithium metal batteries. However, monitoring the evolution of lithium metal microstructures during cell cycling is challenging.

NATURE COMMUNICATIONS (2023)

Article Nanoscience & Nanotechnology

Exfoliated MoS2 Nanosheet/Cellulose Nanocrystal Flexible Composite Films as Electrodes for Zinc Batteries

Amit Kumar Sonker, Shizhao Xiong, Ruchi Aggarwal, Martina Olsson, Arnita Spule, Seyedehsan Hosseini, Sumit Kumar Sonkar, Aleksandar Matic, Gunnar Westman

Summary: This study presents an efficient method for exfoliating MoS2 in water and using it as an electrode material. The MoS2 is exfoliated through sonication with sulfated cellulose nanocrystals, resulting in a stable water suspension. The exfoliated MoS2 is then used in a zinc battery electrode, demonstrating a Coulombic efficiency of 90%. The success of exfoliation is confirmed by Raman and transmission electron microscopy.

ACS APPLIED NANO MATERIALS (2023)

Article Pharmacology & Pharmacy

Multiscale X-ray imaging and characterisation of pharmaceutical dosage forms

Martina Olsson, Rydvikha Govender, Ana Diaz, Mirko Holler, Andreas Menzel, Susanna Abrahmsen-Alami, Matthew Sadd, Anette Larsson, Aleksandar Matic, Marianne Liebi

Summary: This paper presents a correlative, multiscale imaging methodology combining PXCT and S/WAXS to visualize and quantify the morphology of solid dosage forms. The method allows characterization of structures from the nanometre to millimetre regime. The methodology is demonstrated using a hot-melt extruded solid dispersion of carbamazepine in ethyl cellulose. The 3D morphology was visualized through PXCT, revealing an oriented structure of crystalline drug domains. Scanning S/WAXS showed similarity in the nanostructure across the cross section of the extruded filament.

INTERNATIONAL JOURNAL OF PHARMACEUTICS (2023)

Article Gastroenterology & Hepatology

Machine learning models predict liver steatosis but not liver fibrosis in a prospective cohort study

Behrooz Mamandipoor, Sarah Wernly, Georg Semmler, Maria Flamm, Christian Jung, Elmar Aigner, Christian Datz, Bernhard Wernly, Venet Osmani

Summary: The potential of machine learning methods in predicting liver steatosis and fibrosis was evaluated in this study. By using ultrasound and transient elastography, the researchers found that machine learning algorithms can accurately predict liver steatosis, but the accuracy in predicting liver fibrosis is moderate.

CLINICS AND RESEARCH IN HEPATOLOGY AND GASTROENTEROLOGY (2023)

Article Materials Science, Multidisciplinary

Toward Operando Characterization of Interphases in Batteries

Julia Maibach, Josef Rizell, Aleksandar Matic, Nataliia Mozhzhukhina

Summary: Electrode/electrolyte interfaces are crucial and poorly understood in Li-ion and next-generation batteries. Advancing the understanding of these interfaces can lead to significant breakthroughs in battery development. In this perspective, we discuss operando surface sensitive techniques that have the potential to characterize solid/liquid interfaces in both model and realistic battery configurations, providing chemical and structural information. These techniques include vibrational spectroscopy, X-ray photoelectron spectroscopy (XPS), neutron and X-ray reflectometry, and grazing incidence scattering techniques.

ACS MATERIALS LETTERS (2023)

Review Electrochemistry

Electro-Chemo-Mechanical Failure Mechanisms of Solid-State Electrolytes

Quan Wu, Shizhao Xiong, Fujun Li, Aleksandar Matic

Summary: This review comprehensively summarizes the failure mechanisms of solid-state electrolytes, including electric failure, (electro)chemical failure, and mechanical failure. By analyzing these failure mechanisms in detail, the researchers provide new insights for the design of future SSLMBs.

BATTERIES & SUPERCAPS (2023)

Article Chemistry, Physical

Mechanistic understanding of the correlation between structure and dynamics of liquid carbonate electrolytes: impact of polarization

Moumita Maiti, Anand Narayanan Krishnamoorthy, Youssef Mabrouk, Nataliia Mozhzhukhina, Aleksandar Matic, Diddo Diddens, Andreas Heuer

Summary: Liquid electrolyte design and modelling is crucial for the development of better lithium ion batteries. Comparing a polarizable force field with a non-polarizable force field, the polarizable force field shows better agreement with experimental results in terms of structural and dynamic properties. It also performs better in terms of transport quantities.

PHYSICAL CHEMISTRY CHEMICAL PHYSICS (2023)

Article Health Care Sciences & Services

Delirium prediction in the ICU: designing a screening tool for preventive interventions

Anirban Bhattacharyya, Seyedmostafa Sheikhalishahi, Heather Torbic, Wesley Yeung, Tiffany Wang, Jennifer Birst, Abhijit Duggal, Leo Anthony Celi, Venet Osmani

Summary: Delirium is a common and resource-intensive issue, and machine learning can be used to develop a delirium prediction model for screening purposes. The research utilized a large amount of clinical data to validate the model's performance and identified techniques that can enhance prediction accuracy.

JAMIA OPEN (2022)

No Data Available