1
|
Vera-Salmerón E, Domínguez-Nogueira C, Sáez JA, Romero-Béjar JL, Mota-Romero E. Differentiating Pressure Ulcer Risk Levels through Interpretable Classification Models Based on Readily Measurable Indicators. Healthcare (Basel) 2024; 12:913. [PMID: 38727470 PMCID: PMC11083727 DOI: 10.3390/healthcare12090913] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2024] [Revised: 04/24/2024] [Accepted: 04/25/2024] [Indexed: 05/13/2024] Open
Abstract
Pressure ulcers carry a significant risk in clinical practice. This paper proposes a practical and interpretable approach to estimate the risk levels of pressure ulcers using decision tree models. In order to address the common problem of imbalanced learning in nursing classification datasets, various oversampling configurations are analyzed to improve the data quality prior to modeling. The decision trees built are based on three easily identifiable and clinically relevant pressure ulcer risk indicators: mobility, activity, and skin moisture. Additionally, this research introduces a novel tabular visualization method to enhance the usability of the decision trees in clinical practice. Thus, the primary aim of this approach is to provide nursing professionals with valuable insights for assessing the potential risk levels of pressure ulcers, which could support their decision-making and allow, for example, the application of suitable preventive measures tailored to each patient's requirements. The interpretability of the models proposed and their performance, evaluated through stratified cross-validation, make them a helpful tool for nursing care in estimating the pressure ulcer risk level.
Collapse
Affiliation(s)
- Eugenio Vera-Salmerón
- Servicio Andaluz de Salud, Distrito Sanitario Granada-Metropolitano, Centro de Salud Dr. Salvador Caballero de Granada, 18012 Granada, Spain; (E.V.-S.); (E.M.-R.)
- Instituto de Investigación Biosanitaria (ibs.GRANADA), 18014 Granada, Spain
| | - Carmen Domínguez-Nogueira
- Inspección Provincial de Servicios Sanitarios, Delegación Territorial de Granada, Consejería de Salud y Familias de la Junta de Andalucía, 41071 Sevilla, Spain;
| | - José A. Sáez
- Department of Statistics and Operations Research, University of Granada, Fuente Nueva s/n, 18071 Granada, Spain;
| | - José L. Romero-Béjar
- Instituto de Investigación Biosanitaria (ibs.GRANADA), 18014 Granada, Spain
- Department of Statistics and Operations Research, University of Granada, Fuente Nueva s/n, 18071 Granada, Spain;
- Institute of Mathematics, University of Granada (IMAG), Ventanilla 11, 18001 Granada, Spain
| | - Emilio Mota-Romero
- Servicio Andaluz de Salud, Distrito Sanitario Granada-Metropolitano, Centro de Salud Dr. Salvador Caballero de Granada, 18012 Granada, Spain; (E.V.-S.); (E.M.-R.)
- Instituto de Investigación Biosanitaria (ibs.GRANADA), 18014 Granada, Spain
- Department of Nursing, University of Granada, Avda. Ilustración 60, 18071 Granada, Spain
| |
Collapse
|
2
|
Kumagai A, Ohno N, Miyati T, Sugama J. Prediction of tissue deformation based on mechanical and physiological factors in the prone position during surgery. J Tissue Viability 2024:S0965-206X(24)00008-1. [PMID: 38378353 DOI: 10.1016/j.jtv.2024.02.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/03/2023] [Revised: 12/16/2023] [Accepted: 02/05/2024] [Indexed: 02/22/2024]
Abstract
AIM This study aimed to predict tissue deformation based on the pressure applied while lying in the prone position and physiological factors. METHODS Healthy volunteers were instructed to lie on mattresses of four different hardness levels (50, 87.5, 175, and 262.5 N). The order in which the mattresses were used was randomized per participant. Pressure at the iliac crests was measured using a pressure mapping sensor sheet. Participants were placed in the prone position for 10 min, with pressure data used from the latter 5 min. For the tissue deformation at the iliac crests, our previous study data were used. Multiple regression analysis was used to identify predictive mechanical and physiological factors. RESULTS The distance between the left and right greater trochanters, maximum interface pressure and age were significant predictors for compression of the skin and soft tissue. Significant predictors of internal soft tissue displacement were the distances between the left and right anterior superior iliac spines and greater trochanters. No factors predicted skin surface displacement. CONCLUSIONS Our study provided predictive factors that may be measured easily in a clinical setting to reduce the risk of pressure ulcers during surgery in the prone position.
Collapse
Affiliation(s)
- Ayumi Kumagai
- Faculty of Nursing and Social Welfare Science, Department of Nursing Science, Fukui Prefectural University, Eiheiji-Town, Fukui, Japan.
| | - Naoki Ohno
- Faculty of Health Sciences, Institute of Medical, Pharmaceutical and Health Sciences, Kanazawa University, Kanazawa, Ishikawa, Japan
| | - Tosiaki Miyati
- Faculty of Health Sciences, Institute of Medical, Pharmaceutical and Health Sciences, Kanazawa University, Kanazawa, Ishikawa, Japan
| | - Junko Sugama
- Department of Gerontological Nursing, Faculty of Nursing, School of Health Sciences, Fujita Health University, Toyoake, Aichi, Japan; Research Center for Implementation Nursing Science Initiative, Innovation Promotion Division, Research Promotion Headquarters, Fujita Health University, Toyoake, Aichi, Japan
| |
Collapse
|
3
|
Han H, Oh YS, Cho S, Park H, Lee SU, Ko K, Park JM, Choi J, Ha JH, Han C, Zhao Z, Liu Z, Xie Z, Lee JS, Min WG, Lee BJ, Koo J, Choi DY, Je M, Sun JY, Park I. Battery-Free, Wireless, Ionic Liquid Sensor Arrays to Monitor Pressure and Temperature of Patients in Bed and Wheelchair. SMALL (WEINHEIM AN DER BERGSTRASSE, GERMANY) 2023; 19:e2205048. [PMID: 36534830 DOI: 10.1002/smll.202205048] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/17/2022] [Revised: 10/20/2022] [Indexed: 06/17/2023]
Abstract
Repositioning is a common guideline for the prevention of pressure injuries of bedridden or wheelchair patients. However, frequent repositioning could deteriorate the quality of patient's life and induce secondary injuries. This paper introduces a method for continuous multi-site monitoring of pressure and temperature distribution from strategically deployed sensor arrays at skin interfaces via battery-free, wireless ionic liquid pressure sensors. The wirelessly delivered power enables stable operation of the ionic liquid pressure sensor, which shows enhanced sensitivity, negligible hysteresis, high linearity and cyclic stability over relevant pressure range. The experimental investigations of the wireless devices, verified by numerical simulation of the key responses, support capabilities for real-time, continuous, long-term monitoring of the pressure and temperature distribution from multiple sensor arrays. Clinical trials on two hemiplegic patients confined on bed or wheelchair integrated with the system demonstrate the feasibility of sensor arrays for a decrease in pressure and temperature distribution under minimal repositioning.
Collapse
Affiliation(s)
- Hyeonseok Han
- Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea
| | - Yong Suk Oh
- Department of Mechanical Engineering, Changwon National University, Changwon, 51140, Republic of Korea
| | - Seokjoo Cho
- Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea
| | - Hyunwoo Park
- School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea
| | - Sung-Uk Lee
- Advanced 3D Printing Technology Development Division, Korea Atomic Energy Research Institute, Daejeon, 34057, Republic of Korea
| | - Kabseok Ko
- Department of Electronics Engineering, Kangwon National University, Chuncheon, 24341, Republic of Korea
| | - Jae-Man Park
- Department of Materials Science & Engineering, Seoul National University, Seoul, 08826, Republic of Korea
| | - Jungrak Choi
- Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea
| | - Ji-Hwan Ha
- Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea
| | - Chankyu Han
- Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea
| | - Zichen Zhao
- State Key Laboratory of Structural Analysis for Industrial Equipment, Dalian University of Technology, Dalian, 116024, P. R. China
| | - Zhuangjian Liu
- Institute of High-Performance Computing, Agency for Science, Technology and Research, Singapore, 138632, Singapore
| | - Zhaoqian Xie
- State Key Laboratory of Structural Analysis for Industrial Equipment, Dalian University of Technology, Dalian, 116024, P. R. China
| | - Je-Sang Lee
- Department of Rehabilitation Medicine, Gimhae Hansol Rehabilitation & Convalescent Hospital, Gimhae, 50924, Republic of Korea
| | - Weon Gi Min
- Department of Planning and Development, Gimhae Hansol Rehabilitation & Convalescent Hospital, Gimhae, 50924, Republic of Korea
| | - Byeong-Ju Lee
- Department of Rehabilitation Medicine, Pusan National University Hospital, Busan, 49241, Republic of Korea
| | - Jahyun Koo
- School of Biomedical Engineering, Korea University, Seoul, 02841, Republic of Korea
- Interdisciplinary Program in Precision Public Health, Korea University, Seoul, 02841, Republic of Korea
| | - Dong Yun Choi
- Biomedical Manufacturing Technology Center, Korea Institute of Industrial Technology (KITECH), Yeongcheon, 38822, Republic of Korea
| | - Minkyu Je
- School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea
| | - Jeong-Yun Sun
- Department of Materials Science & Engineering, Seoul National University, Seoul, 08826, Republic of Korea
- Research Institute of Advanced Materials (RIAM), Seoul National University, Seoul, 08826, Republic of Korea
| | - Inkyu Park
- Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea
| |
Collapse
|
4
|
Mechanical analysis of deep tissue injury during sitting in patients with spinal cord injury via parametric finite element model. Biomech Model Mechanobiol 2022; 21:1573-1584. [PMID: 35931860 DOI: 10.1007/s10237-022-01607-z] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2022] [Accepted: 06/24/2022] [Indexed: 11/02/2022]
Abstract
Spinal cord injury patients are prone to develop deep tissue injury because of long-term mechanical load. However, there is a lack of statistical research on the influence of tissue characteristics on the internal mechanical state of soft tissue. This study aimed to investigate the influence of tissue characteristics on the internal mechanical state of buttock in spinal cord injury patients. A three-dimensional reference buttock model was established and a visualization program was generated to modify the parameter values. Through changing the muscle atrophy, body mass index and the radius of curvature of the ischial tuberosity, 96 different model variants were simulated and validated in this study. With body mass index increasing from 16 to 40, the principal shear stress was 10.4 times principal compressive stress, the maximum shear strain and the max cluster volume increased by 1.2 (P < 0.001) and 8.8 times (P < 0.001), respectively. The interaction between BMI and muscle atrophy was significant when BMI was greater than or equal to 22.5 kg/m2. In all BMI stages, when the radius of curvature of the ischial tuberosity was 19 mm, the internal stress of the tissue always occupies the highest value. The results demonstrate that body mass index is the most important factor affecting the risk of buttock deep tissue injury. This study provides insights into investigation of inter-individual factors influencing the soft tissue response and assessment of deep tissue injury risk during sitting.
Collapse
|
5
|
Subcutaneous Fat Thickness Remarkably Influences Contact Pressure and Load Distribution of Buttock in Seated Posture. JOURNAL OF HEALTHCARE ENGINEERING 2021; 2021:4496416. [PMID: 34900189 PMCID: PMC8654536 DOI: 10.1155/2021/4496416] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/09/2021] [Accepted: 11/18/2021] [Indexed: 11/17/2022]
Abstract
Spinal cord injury patients are prone to develop deep tissue injury (DTI) as they may spend half their time per day in sitting postures, which produce excessive load in their buttocks. However, the impact of fat thickness on the biomechanical response of buttock in sitting posture remained unclear. This study aimed to investigate the influence of subcutaneous fat thickness on the interface pressure and load distribution of buttock of seated humans. To achieve this goal, a 3-dimensional finite element model of male buttock was constructed and the contact pressure on a rigid cushion was evaluated against experimental results. The modified models, which had various fat thicknesses under ischial tuberosity, were built and used to simulate the sitting conditions with different cushion stiffnesses. In the models simulating sitting on the rigid cushion, the peak contact pressure ranges from 0.052 MPa to 0.149 MPa. In the simulation of sitting on the soft cushion, the peak stress of muscle underneath ischial tuberosity in the model with the thickest fat tissue was slightly higher than that of the other models. The results demonstrate that the fat tissue in the buttock could reduce the contact pressure when sitting on the rigid seat. However, contact pressure solely could not be used to estimate the internal tissue stress of seated buttock, especially in subjects with thicker fat tissue.
Collapse
|
6
|
Interpersonal differences in the friction response of skin relate to FTIR measures for skin lipids and hydration. Colloids Surf B Biointerfaces 2020; 189:110883. [PMID: 32105961 DOI: 10.1016/j.colsurfb.2020.110883] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2018] [Revised: 02/16/2020] [Accepted: 02/17/2020] [Indexed: 01/04/2023]
Abstract
Understanding the mechanical response of skin to contact is of importance when developing products that interact with the skin. The shear forces that arise due to friction in the interface are a key aspect of skin interactions, because shear is known to contribute to discomfort and tissue injury. However, the frictional response of skin shows large variations between people. It has been hypothesised that these variations relate to differences between people in the physiological properties of their skin, but the underlying mechanisms are not well understood. In order to gain new insights into these interpersonal differences in friction behaviour, in vivo FTIR measurements and in vivo friction measurements were performed on the same patch of skin. Quantitative analysis of the various peaks in the FTIR spectra provided information on the moisture content of the stratum corneum and the amount and mechanical properties of the lipids on the skin. The lipid viscosity, as characterised by the width of the 2920 cm-1 peak, correlates with the friction, whilst, interestingly, no relationship was found between the quantity of lipids on the skin surface and the coefficient of friction. Additionally, and as expected, a fairly strong correlation was obtained between the moisture content, as characterised by the height of the Amide I peak and the coefficient of friction. The presented results show that spectroscopy techniques can be used in as a non-invasive method to identify people who may show elevated levels of friction and thus are at increased risk of developing shear induced tissue injury.
Collapse
|