1
|
Pirompud P, Sivapirunthep P, Punyapornwithaya V, Chaosap C. Machine learning predictive modeling for condemnation risk assessment in antibiotic-free raised broilers. Poult Sci 2024; 103:104270. [PMID: 39260246 DOI: 10.1016/j.psj.2024.104270] [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: 02/14/2024] [Revised: 08/20/2024] [Accepted: 08/22/2024] [Indexed: 09/13/2024] Open
Abstract
The condemnation of broiler carcasses in the poultry industry is a major challenge and leads to significant financial losses and food waste. This study addresses the critical issue of condemnation risk assessment in the discarding of antibiotic-free raised broilers using machine learning (ML) predictive modeling. In this study, ML approaches, specifically least absolute shrinkage and selection operator (LASSO), classification tree (CT), and random forests (RF), were used to evaluate and compare their effectiveness in predicting high condemnation rates. The dataset of 23,959 truckloads from 2021 to 2022 contained 14 independent variables covering the rearing, catching, transportation, and slaughtering phases. Condemnation rates between 0.26% and 25.99% were used as the dependent variable for the analysis, with the threshold for a high conviction rate set at 3.0%. As high condemnation rates were in the minority (8.05%), sampling methods such as random over sampling (ROS), random under sampling (RUS), both sampling (BOTH), and random over sampling example (ROSE) were used to account for imbalanced datasets. The results showed that RF with RUS performed better than the other models for balanced datasets. In this study, mean body weight, weight per crate, mortality and culling rates, and lairage time were identified as the 4 most important variables for predicting high condemnation rates. This study provides valuable insights into ML applications for predicting condemnation rates in antibiotic-free raised broilers and provides a framework to improve decision-making processes in establishing farm management practices to minimize economic losses in the poultry industry. The proposed methods are adaptable for different broiler producers, which increases their applicability in the industry.
Collapse
Affiliation(s)
- Pranee Pirompud
- Doctoral Program in Innovative Tropical Agriculture, Department of Agricultural Education, Faculty of Industrial Education and Technology, King Mongkut's Institute of Technology Ladkrabang, Bangkok, Thailand 10520
| | - Panneepa Sivapirunthep
- Department of Agricultural Education, Faculty of Industrial Education and Technology, King Mongkut's Institute of Technology Ladkrabang, Bangkok, Thailand 10520
| | - Veerasak Punyapornwithaya
- Department of Veterinary Biosciences and Veterinary Public Health, Faculty of Veterinary Medicine, Chiang Mai University, Chiang Mai 50100, Thailand
| | - Chanporn Chaosap
- Department of Agricultural Education, Faculty of Industrial Education and Technology, King Mongkut's Institute of Technology Ladkrabang, Bangkok, Thailand 10520.
| |
Collapse
|
2
|
Ma Y, He X, Yang T, Yang Y, Yang Z, Gao T, Yan F, Yan B, Wang J, Han L. Evaluation of the risk prediction model of pressure injuries in hospitalized patient: A systematic review and meta-analysis. J Clin Nurs 2024. [PMID: 39073235 DOI: 10.1111/jocn.17367] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2023] [Revised: 04/13/2024] [Accepted: 07/04/2024] [Indexed: 07/30/2024]
Abstract
AIMS AND OBJECTIVES The main aim of this study is to synthesize the prevalent predictive models for pressure injuries in hospitalized patients, with the goal of identifying common predictive factors linked to pressure injuries in hospitalized patients. This endeavour holds the potential to provide clinical nurses with a valuable reference for providing targeted care to high-risk patients. BACKGROUND Pressure injuries (PIs) are a frequently occurring health problem throughout the world. There are mounting studies about risk prediction model of PIs reported and published. However, the prediction performance of the models is still unclear. DESIGN Systematic review and meta-analysis: The Cochrane Library, PubMed, Embase, CINAHL, Web of Science and Chinese databases including CNKI (China National Knowledge Infrastructure), Wanfang Database, Weipu Database and CBM (China Biology Medicine). METHODS This systematic review was conducted following PRISMA recommendations. The databases of Cochrane Library, PubMed, Embase, CINAHL, Web of Science, and CNKI, Weipu Database, Wanfang Database and CBM were searched for all studies published before September 2023. We included studies with cohort, case-control designs, reporting the development of risk model and have been validated externally and internally among the hospitalized patients. Two researchers selected the retrieved studies according to the inclusion and exclusion criteria, and critically evaluated the quality of studies based on the CHARMS checklist. The PRISMA guideline was used to report the systematic review and meta-analysis. RESULTS Sixty-two studies were included, which contained 99 pressure injuries risk prediction models. The AUC (area under ROC curve) of modelling in 32 prediction models were reported ranged from .70 to .99, while the AUC of verification in 38 models were reported ranged from .70 to .98. Gender (OR = 1.41, CI: .99 ~ 1.31), age (WMD = 8.81, CI: 8.11 ~ 9.57), diabetes mellitus (OR = 1.64, CI: 1.36 ~ 1.99), mechanical ventilation (OR = 2.71, CI: 2.05 ~ 3.57), length of hospital stay (WMD = 7.65, CI: 7.24 ~ 8.05) were the most common predictors of pressure injuries. CONCLUSION Studies of PIs risk prediction model in hospitalized patients had high research quality, and the risk prediction models also had good predictive performance. However, some of the included studies lacked of internal or external validation in modelling, which affected the stability and extendibility. The aged, male patient in ICU, albumin, haematocrit, low haemoglobin level, diabetes, mechanical ventilation and length of stay in hospital were high-risk factors for pressure injuries in hospitalized patients. In the future, it is recommended that clinical nurses, in practice, select predictive models with better performance to identify high-risk patients based on the actual situation and provide care targeting the high-risk factors to prevent the occurrence of diseases. RELEVANCE TO CLINICAL PRACTICE The risk prediction model is an effective tool for identifying patients at the risk of developing PIs. With the help of risk prediction tool, nurses can identify the high-risk patients and common predictive factors, predict the probability of developing PIs, then provide specific preventive measures to improve the outcomes of these patients. REGISTRATION NUMBER (PROSPERO) CRD42023445258.
Collapse
Affiliation(s)
- Yuxia Ma
- Evidence-Based Nursing Center, School of Nursing, Lanzhou University, Lanzhou, China
| | - Xiang He
- Evidence-Based Nursing Center, School of Nursing, Lanzhou University, Lanzhou, China
| | - Tingting Yang
- Evidence-Based Nursing Center, School of Nursing, Lanzhou University, Lanzhou, China
| | - Yifang Yang
- Evidence-Based Nursing Center, School of Nursing, Lanzhou University, Lanzhou, China
| | - Ziyan Yang
- Evidence-Based Nursing Center, School of Nursing, Lanzhou University, Lanzhou, China
| | - Tian Gao
- Evidence-Based Nursing Center, School of Nursing, Lanzhou University, Lanzhou, China
| | - Fanghong Yan
- Evidence-Based Nursing Center, School of Nursing, Lanzhou University, Lanzhou, China
| | - Boling Yan
- The First Hospital of Lanzhou University, Lanzhou, China
| | - Juan Wang
- Department of Nursing, Second Hospital of Lanzhou University, Lanzhou, China
| | - Lin Han
- Evidence-Based Nursing Center, School of Nursing, Lanzhou University, Lanzhou, China
- The First Hospital of Lanzhou University, Lanzhou, China
- Department of Nursing, Gansu Provincial Hospital, Lanzhou, China
| |
Collapse
|
3
|
Sun S, Zhang H, Ye L, Huang L, Du J, Liang X, Zhang X, Chen J, Jiang Y, Chen L. Combined analysis of the microbiome and metabolome to reveal the characteristics of saliva from different diets: a comparison among vegans, seafood-based omnivores, and red meat (beef and lamb) omnivores. Front Microbiol 2024; 15:1419686. [PMID: 39077734 PMCID: PMC11284149 DOI: 10.3389/fmicb.2024.1419686] [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: 04/18/2024] [Accepted: 07/01/2024] [Indexed: 07/31/2024] Open
Abstract
Introduction Revealing individual characteristics is supportive for identifying individuals in forensic crime. As saliva is one of the most common biological samples used in crime scenes, it is important to make full use of the rich individual information contained in saliva. The aim of this study was to explore the application of the microbiome in forensic science by analysing differences in the salivary microbiome and metabolome of healthy individuals with different dietary habits. Methods We performed 16S rDNA sequencing analysis based on oral saliva samples collected from 12 vegetarians, 12 seafood omnivores and 12 beef and lamb omnivores. Non-targeted metabolomics analyses were also performed based on saliva samples from healthy individuals. Results The results showed that the dominant flora of vegetarians was dominated by Neisseria (belonging to the phylum Proteobacteria), while seafood omnivores and beef and lamb omnivores were dominated by Streptococcus (belonging to the phylum Firmicutes). NDMS-based and cluster analyses showed that vegetarian dieters were significantly differentiated from meat dieters (seafood omnivores and beef and lamb omnivores), which may be related to the fact that high-fiber diets can create a different salivary flora structure. Variants were also detected in salivary metabolic pathways, including positive correlations with Lipid metabolism, Amino acid metabolism, Carbohydrate metabolism, and Nucleotide metabolism in vegetarians, and correlations in seafood omnivores. In order to select salivary microorganisms and metabolic markers that can distinguish different dietary profiles, a random forest classifier model was constructed in this study, and the results showed that individuals with different dietary profiles could be successfully distinguished based on the core genera and metabolites such as Streptococcus, Histidinyl-Valine. Conclusion Our study provides a supportive basis for the application of salivary polyomics in order to reveal the dietary characteristics of individuals for forensic investigation and crime solving.
Collapse
Affiliation(s)
- Shiyu Sun
- Guangdong Second Provincial General Hospital, Guangzhou, Guangdong, China
| | - Huiqiong Zhang
- Department of Pediatrics, Guangdong Provincial People’s Hospital, Guangzhou, China
| | - Linying Ye
- School of Forensic Medicine, Southern Medical University, Guangzhou, Guangdong Province, China
| | - Litao Huang
- School of Forensic Medicine, Southern Medical University, Guangzhou, Guangdong Province, China
| | - Jieyu Du
- School of Forensic Medicine, Southern Medical University, Guangzhou, Guangdong Province, China
| | - Xiaomin Liang
- School of Forensic Medicine, Southern Medical University, Guangzhou, Guangdong Province, China
| | - Xiaofeng Zhang
- School of Forensic Medicine, Southern Medical University, Guangzhou, Guangdong Province, China
| | - Jiaxing Chen
- School of Forensic Medicine, Southern Medical University, Guangzhou, Guangdong Province, China
| | - Yingping Jiang
- Guangdong Second Provincial General Hospital, Guangzhou, Guangdong, China
| | - Ling Chen
- School of Forensic Medicine, Southern Medical University, Guangzhou, Guangdong Province, China
| |
Collapse
|
4
|
Wu H, Chen Z, Gu J, Jiang Y, Gao S, Chen W, Miao C. Predicting Chronic Pain and Treatment Outcomes Using Machine Learning Models Based on High-dimensional Clinical Data From a Large Retrospective Cohort. Clin Ther 2024; 46:490-498. [PMID: 38824080 DOI: 10.1016/j.clinthera.2024.04.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2023] [Revised: 04/13/2024] [Accepted: 04/27/2024] [Indexed: 06/03/2024]
Abstract
PURPOSE To identify factors and indicators that affect chronic pain and pain relief, and to develop predictive models using machine learning. METHODS We analyzed the data of 67,028 outpatient cases and 11,310 valid samples with pain from a large retrospective cohort. We used decision tree, random forest, AdaBoost, neural network, and logistic regression to discover significant indicators and to predict pain and treatment relief. FINDINGS The random forest model had the highest accuracy, F1 value, precision, and recall rates for predicting pain relief. The main factors affecting pain and treatment relief included body mass index, blood pressure, age, body temperature, heart rate, pulse, and neutrophil/lymphocyte × platelet ratio. The logistic regression model had high sensitivity and specificity for predicting pain occurrence. IMPLICATIONS Machine learning models can be used to analyze the risk factors and predictors of chronic pain and pain relief, and to provide personalized and evidence-based pain management.
Collapse
Affiliation(s)
- Han Wu
- Department of Anesthesiology, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Key laboratory of Perioperative Stress and Protection, Shanghai, China
| | - Zhaoyuan Chen
- Department of Anesthesiology, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Key laboratory of Perioperative Stress and Protection, Shanghai, China
| | - Jiahui Gu
- Department of Anesthesiology, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Key laboratory of Perioperative Stress and Protection, Shanghai, China
| | - Yi Jiang
- Department of Anesthesiology, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Key laboratory of Perioperative Stress and Protection, Shanghai, China
| | - Shenjia Gao
- Department of Anesthesiology, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Key laboratory of Perioperative Stress and Protection, Shanghai, China
| | - Wankun Chen
- Department of Anesthesiology, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Key laboratory of Perioperative Stress and Protection, Shanghai, China.
| | - Changhong Miao
- Department of Anesthesiology, Zhongshan Hospital, Fudan University, Shanghai, China; Shanghai Key laboratory of Perioperative Stress and Protection, Shanghai, China.
| |
Collapse
|
5
|
Charon C, Wuillemin PH, Havreng-Théry C, Belmin J. One Month Prediction of Pressure Ulcers in Nursing Home Residents with Bayesian Networks. J Am Med Dir Assoc 2024; 25:104945. [PMID: 38431264 DOI: 10.1016/j.jamda.2024.01.014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2023] [Revised: 01/12/2024] [Accepted: 01/17/2024] [Indexed: 03/05/2024]
Abstract
OBJECTIVES Pressure ulcers (PUs) are a common and avoidable condition among residents of nursing homes, and their consequences are severe. Reliable and simple identification of high-risk residents is a major challenge for prevention. Available tools like the Braden and Norton scale have imperfect predictive performance. The objective is to predict the occurrence of PUs in nursing home residents from electronic health record (EHR) data. DESIGN Longitudinal retrospective nested case-control study. SETTING AND PARTICIPANTS EHR database of French nursing homes from 2013 to 2022. METHODS Residents who suffered from PUs were cases and those who did not were controls. For cases, we analyzed the data available in their EHR 1 month before the occurrence of the first PU. For controls, we used available data 1 month before an index date adjusted on the delays of PU onset. We conducted a Bayesian network (BN) analysis, an explainable machine learning method, using 136 input variables of potential medical interest determined with experts. To validate the model, we used scores, features selection, and explainability tools such as Shapley values. RESULTS Among 58,368 residents analyzed, 29% suffered from PUs during their stay. The obtained BN model predicts the occurrence of a PU at a 1-month horizon with a sensitivity of 0.94 (±0.01), a precision of 0.32 (±0.01) and an area under the curve of 0.69 (±0.02). It selects 3 variables: length of stay, delay since last hospitalization, and dependence for transfer. This BN model is suitable and simpler than models provided by other machine learning methods. CONCLUSIONS AND IMPLICATIONS One-month prediction for incident PU is possible in nursing home residents from their EHR data. The study paves the way for the development of a predictive tool fueled by routinely collected data that do not require additional work from health care professionals, thereby opening a new preventive strategy for PUs.
Collapse
Affiliation(s)
- Clara Charon
- LIP6 (UMR 7606), Sorbonne Université, Paris, France; Teranga Software, Paris, France
| | | | | | - Joël Belmin
- LIMICS (UMR 1142), Sorbonne Université, Paris, France; AP-HP, Hôpital Charles-Foix, Ivry-sur-Seine, France.
| |
Collapse
|
6
|
Kushwaha NL, Kudnar NS, Vishwakarma DK, Subeesh A, Jatav MS, Gaddikeri V, Ahmed AA, Abdelaty I. Stacked hybridization to enhance the performance of artificial neural networks (ANN) for prediction of water quality index in the Bagh river basin, India. Heliyon 2024; 10:e31085. [PMID: 38784559 PMCID: PMC11112320 DOI: 10.1016/j.heliyon.2024.e31085] [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: 02/07/2024] [Revised: 05/03/2024] [Accepted: 05/09/2024] [Indexed: 05/25/2024] Open
Abstract
Water quality assessment is paramount for environmental monitoring and resource management, particularly in regions experiencing rapid urbanization and industrialization. This study introduces Artificial Neural Networks (ANN) and its hybrid machine learning models, namely ANN-RF (Random Forest), ANN-SVM (Support Vector Machine), ANN-RSS (Random Subspace), ANN-M5P (M5 Pruned), and ANN-AR (Additive Regression) for water quality assessment in the rapidly urbanizing and industrializing Bagh River Basin, India. The Relief algorithm was employed to select the most influential water quality input parameters, including Nitrate (NO3-), Magnesium (Mg2+), Sulphate (SO42-), Calcium (Ca2+), and Potassium (K+). The comparative analysis of developed ANN and its hybrid models was carried out using statistical indicators (i.e., Nash-Sutcliffe Efficiency (NSE), Pearson Correlation Coefficient (PCC), Coefficient of Determination (R2), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Relative Root Square Error (RRSE), Relative Absolute Error (RAE), and Mean Bias Error (MBE)) and graphical representations (i.e., Taylor diagram). Results indicate that the integration of support vector machine (SVM) with ANN significantly improves performance, yielding impressive statistical indicators: NSE (0.879), R2 (0.904), MAE (22.349), and MBE (12.548). The methodology outlined in this study can serve as a template for enhancing the predictive capabilities of ANN models in various other environmental and ecological applications, contributing to sustainable development and safeguarding natural resources.
Collapse
Affiliation(s)
- Nand Lal Kushwaha
- Department of Soil and Water Engineering, Punjab Agricultural University Ludhiana, Punjab, 141004, India
- Division of Agricultural Engineering, ICAR-Indian Agricultural Research Institute, New Delhi, 110012, India
| | - Nanabhau S. Kudnar
- Department of Geography, C. J. Patel College Tirora, Gondia, Maharashtra, 441911, India
| | - Dinesh Kumar Vishwakarma
- Department of Irrigation and Drainage Engineering, G.B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, 263145, India
| | - A. Subeesh
- ICAR- Central Institute of Agricultural Engineering, Bhopal, Madhya Pradesh, 462038, India
| | - Malkhan Singh Jatav
- National Institute of Hydrology, North Western Regional Centre, Jodhpur, Rajasthan, 342003, India
| | - Venkatesh Gaddikeri
- Division of Agricultural Engineering, ICAR-Indian Agricultural Research Institute, New Delhi, 110012, India
| | - Ashraf A. Ahmed
- Department of Civil and Environmental Engineering, Brunel University London, Kingston Lane, Uxbridge UB38PH, UK
| | - Ismail Abdelaty
- Water and Water Structures Engineering Department, Faculty of Engineering, Zagazig University, Zagazig, 44519, Egypt
| |
Collapse
|
7
|
Reese TJ, Domenico HJ, Hernandez A, Byrne DW, Moore RP, Williams JB, Douthit BJ, Russo E, McCoy AB, Ivory CH, Steitz BD, Wright A. Implementable Prediction of Pressure Injuries in Hospitalized Adults: Model Development and Validation. JMIR Med Inform 2024; 12:e51842. [PMID: 38722209 PMCID: PMC11094428 DOI: 10.2196/51842] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2023] [Revised: 03/08/2024] [Accepted: 03/10/2024] [Indexed: 05/18/2024] Open
Abstract
Background Numerous pressure injury prediction models have been developed using electronic health record data, yet hospital-acquired pressure injuries (HAPIs) are increasing, which demonstrates the critical challenge of implementing these models in routine care. Objective To help bridge the gap between development and implementation, we sought to create a model that was feasible, broadly applicable, dynamic, actionable, and rigorously validated and then compare its performance to usual care (ie, the Braden scale). Methods We extracted electronic health record data from 197,991 adult hospital admissions with 51 candidate features. For risk prediction and feature selection, we used logistic regression with a least absolute shrinkage and selection operator (LASSO) approach. To compare the model with usual care, we used the area under the receiver operating curve (AUC), Brier score, slope, intercept, and integrated calibration index. The model was validated using a temporally staggered cohort. Results A total of 5458 HAPIs were identified between January 2018 and July 2022. We determined 22 features were necessary to achieve a parsimonious and highly accurate model. The top 5 features included tracheostomy, edema, central line, first albumin measure, and age. Our model achieved higher discrimination than the Braden scale (AUC 0.897, 95% CI 0.893-0.901 vs AUC 0.798, 95% CI 0.791-0.803). Conclusions We developed and validated an accurate prediction model for HAPIs that surpassed the standard-of-care risk assessment and fulfilled necessary elements for implementation. Future work includes a pragmatic randomized trial to assess whether our model improves patient outcomes.
Collapse
Affiliation(s)
- Thomas J Reese
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Henry J Domenico
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Antonio Hernandez
- Department of Anesthesiology, Division of Critical Care Medicine, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Daniel W Byrne
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, United States
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Ryan P Moore
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Jessica B Williams
- Department of Nursing, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Brian J Douthit
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Elise Russo
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Allison B McCoy
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Catherine H Ivory
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Bryan D Steitz
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, United States
| | - Adam Wright
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, United States
| |
Collapse
|
8
|
Shafiabady N, Hadjinicolaou N, Hettikankanamage N, MohammadiSavadkoohi E, Wu RMX, Vakilian J. eXplainable Artificial Intelligence (XAI) for improving organisational regility. PLoS One 2024; 19:e0301429. [PMID: 38656983 PMCID: PMC11042710 DOI: 10.1371/journal.pone.0301429] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2023] [Accepted: 03/15/2024] [Indexed: 04/26/2024] Open
Abstract
Since the pandemic started, organisations have been actively seeking ways to improve their organisational agility and resilience (regility) and turn to Artificial Intelligence (AI) to gain a deeper understanding and further enhance their agility and regility. Organisations are turning to AI as a critical enabler to achieve these goals. AI empowers organisations by analysing large data sets quickly and accurately, enabling faster decision-making and building agility and resilience. This strategic use of AI gives businesses a competitive advantage and allows them to adapt to rapidly changing environments. Failure to prioritise agility and responsiveness can result in increased costs, missed opportunities, competition and reputational damage, and ultimately, loss of customers, revenue, profitability, and market share. Prioritising can be achieved by utilising eXplainable Artificial Intelligence (XAI) techniques, illuminating how AI models make decisions and making them transparent, interpretable, and understandable. Based on previous research on using AI to predict organisational agility, this study focuses on integrating XAI techniques, such as Shapley Additive Explanations (SHAP), in organisational agility and resilience. By identifying the importance of different features that affect organisational agility prediction, this study aims to demystify the decision-making processes of the prediction model using XAI. This is essential for the ethical deployment of AI, fostering trust and transparency in these systems. Recognising key features in organisational agility prediction can guide companies in determining which areas to concentrate on in order to improve their agility and resilience.
Collapse
Affiliation(s)
- Niusha Shafiabady
- Faculty of Science and Technology, Charles Darwin University, Haymarket, New South Wales, Australia
| | - Nick Hadjinicolaou
- Adelaide Institute of Higher Education, Adelaide, South Australia, Australia
| | | | | | - Robert M. X. Wu
- Faculty of Engineering and Information Technology, University of Technology Sydney, Broadway, New South Wales, Australia
| | - James Vakilian
- Faculty of Science and Technology, Charles Darwin University, Haymarket, New South Wales, Australia
| |
Collapse
|
9
|
Rippon MG, Fleming L, Chen T, Rogers AA, Ousey K. Artificial intelligence in wound care: diagnosis, assessment and treatment of hard-to-heal wounds: a narrative review. J Wound Care 2024; 33:229-242. [PMID: 38573907 DOI: 10.12968/jowc.2024.33.4.229] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/06/2024]
Abstract
OBJECTIVE The effective assessment of wounds, both acute and hard-to-heal, is an important component in the delivery by wound care practitioners of efficacious wound care for patients. Improved wound diagnosis, optimising wound treatment regimens, and enhanced prevention of wounds aid in providing patients with a better quality of life (QoL). There is significant potential for the use of artificial intelligence (AI) in health-related areas such as wound care. However, AI-based systems remain to be developed to a point where they can be used clinically to deliver high-quality wound care. We have carried out a narrative review of the development and use of AI in the diagnosis, assessment and treatment of hard-to-heal wounds. We retrieved 145 articles from several online databases and other online resources, and 81 of them were included in this narrative review. Our review shows that AI application in wound care offers benefits in the assessment/diagnosis, monitoring and treatment of acute and hard-to-heal wounds. As well as offering patients the potential of improved QoL, AI may also enable better use of healthcare resources.
Collapse
Affiliation(s)
- Mark G Rippon
- University of Huddersfield, Huddersfield, UK
- Daneriver Consultancy Ltd, Holmes Chapel, UK
| | - Leigh Fleming
- School of Computing and Engineering, University of Huddersfield, Huddersfield, UK
| | - Tianhua Chen
- School of Computing and Engineering, University of Huddersfield, Huddersfield, UK
| | | | - Karen Ousey
- University of Huddersfield Department of Nursing and Midwifery, Huddersfield, UK
- Adjunct Professor, School of Nursing, Faculty of Health at the Queensland University of Technology, Australia
- Visiting Professor, Royal College of Surgeons in Ireland, Dublin, Ireland
- Chair, International Wound Infection Institute
- President Elect, International Skin Tear Advisory Panel
| |
Collapse
|
10
|
Wang S, Song F, Song M, Wei X, Zhou Y, Jiang L, Wang Z, Sun C, Yao H, Liang W, Luo H. Explore variation of salivary bacteria across time and geolocations. Int J Legal Med 2024; 138:547-554. [PMID: 37353677 DOI: 10.1007/s00414-023-03045-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Accepted: 06/13/2023] [Indexed: 06/25/2023]
Abstract
Saliva is an informative body fluid that can be found at various crime scenes, and the salivary bacterial community has been revealed it is a potential auxiliary target for forensic identification. However, the variation of salivary bacterial community composition across time and geolocation needs to be explored. The study was designed to be carried out during the winter vacation that was across about 50 days and eight geographic locations. The high throughput sequencing was performed with the V3-V4 region of the16S rRNA gene to explore salivary bacterial community composition. An overall slight fluctuation of the salivary bacteria was observed, which primarily occurred in the relative abundance of the salivary bacterial taxa. The results of principal coordinate analysis and hierarchical clustering showed samples were clustered by the individuals. All individuals could be correctly identified with the random forest model. In summation, although the relative abundance of salivary bacteria varied across the changes of time and geolocation, the individualized characteristic of salivary bacteria remained steady, which is beneficial for the salivary bacterial application in personal identification.
Collapse
Affiliation(s)
- Shuangshuang Wang
- Department of Forensic Genetics, West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, China
| | - Feng Song
- Department of Forensic Genetics, West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, China
| | - Mengyuan Song
- Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, Sichuan, China
| | - Xiaowen Wei
- Department of Forensic Genetics, West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, China
| | - Yuxiang Zhou
- Department of Forensic Genetics, West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, China
| | - Lanrui Jiang
- Department of Forensic Genetics, West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, China
| | - Zefei Wang
- Department of Forensic Genetics, West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, China
| | - Chaoran Sun
- Department of Forensic Genetics, West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, China
| | - Hewen Yao
- Department of Forensic Genetics, West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, China
| | - Weibo Liang
- Department of Forensic Genetics, West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, China.
| | - Haibo Luo
- Department of Forensic Genetics, West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, China.
| |
Collapse
|
11
|
Lee YC, Ng CJ, Hsu CC, Cheng CW, Chen SY. Machine learning models for predicting unscheduled return visits to an emergency department: a scoping review. BMC Emerg Med 2024; 24:20. [PMID: 38287243 PMCID: PMC10826225 DOI: 10.1186/s12873-024-00939-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/17/2023] [Accepted: 01/22/2024] [Indexed: 01/31/2024] Open
Abstract
BACKGROUND Unscheduled return visits (URVs) to emergency departments (EDs) are used to assess the quality of care in EDs. Machine learning (ML) models can incorporate a wide range of complex predictors to identify high-risk patients and reduce errors to save time and cost. However, the accuracy and practicality of such models are questionable. This review compares the predictive power of multiple ML models and examines the effects of multiple research factors on these models' performance in predicting URVs to EDs. METHODS We conducted the present scoping review by searching eight databases for data from 2010 to 2023. The criteria focused on eligible articles that used ML to predict ED return visits. The primary outcome was the predictive performances of the ML models, and results were analyzed on the basis of intervals of return visits, patient population, and research scale. RESULTS A total of 582 articles were identified through the database search, with 14 articles selected for detailed analysis. Logistic regression was the most widely used method; however, eXtreme Gradient Boosting generally exhibited superior performance. Variations in visit interval, target group, and research scale did not significantly affect the predictive power of the models. CONCLUSION This is the first study to summarize the use of ML for predicting URVs in ED patients. The development of practical ML prediction models for ED URVs is feasible, but improving the accuracy of predicting ED URVs to beyond 0.75 remains a challenge. Including multiple data sources and dimensions is key for enabling ML models to achieve high accuracy; however, such inclusion could be challenging within a limited timeframe. The application of ML models for predicting ED URVs may improve patient safety and reduce medical costs by decreasing the frequency of URVs. Further research is necessary to explore the real-world efficacy of ML models.
Collapse
Affiliation(s)
- Yi-Chih Lee
- Department of Emergency Medicine, Chang Gung Memorial Hospital and Chang Gung University, College of Medicine, Taoyuan City, 333, Taiwan
| | - Chip-Jin Ng
- Department of Emergency Medicine, Chang Gung Memorial Hospital and Chang Gung University, College of Medicine, Taoyuan City, 333, Taiwan
| | - Chun-Chuan Hsu
- Department of Emergency Medicine, Chang Gung Memorial Hospital and Chang Gung University, College of Medicine, Taoyuan City, 333, Taiwan
| | - Chien-Wei Cheng
- Department of Emergency Medicine, Chang Gung Memorial Hospital, Keelung and Chang Gung University, College of Medicine, No. 5 Fushing St., Gueishan Shiang, Taoyuan City, 333, Taiwan
| | - Shou-Yen Chen
- Department of Emergency Medicine, Chang Gung Memorial Hospital and Chang Gung University, College of Medicine, Taoyuan City, 333, Taiwan.
- Department of Emergency Medicine, Chang Gung Memorial Hospital, Keelung and Chang Gung University, College of Medicine, No. 5 Fushing St., Gueishan Shiang, Taoyuan City, 333, Taiwan.
| |
Collapse
|
12
|
Hong QQ, Yan S, Zhao YL, Fan L, Yang L, Zhang WB, Liu H, Lin HX, Zhang J, Ye ZJ, Shen X, Cai LS, Zhang GW, Zhu JM, Ji G, Chen JP, Wang W, Li ZR, Zhu JT, Li GX, You J. Machine learning identifies the risk of complications after laparoscopic radical gastrectomy for gastric cancer. World J Gastroenterol 2024; 30:79-90. [PMID: 38293327 PMCID: PMC10823896 DOI: 10.3748/wjg.v30.i1.79] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/30/2023] [Revised: 10/30/2023] [Accepted: 12/19/2023] [Indexed: 01/06/2024] Open
Abstract
BACKGROUND Laparoscopic radical gastrectomy is widely used, and perioperative complications have become a highly concerned issue. AIM To develop a predictive model for complications in laparoscopic radical gastrectomy for gastric cancer to better predict the likelihood of complications in gastric cancer patients within 30 days after surgery, guide perioperative treatment strategies for gastric cancer patients, and prevent serious complications. METHODS In total, 998 patients who underwent laparoscopic radical gastrectomy for gastric cancer at 16 Chinese medical centers were included in the training group for the complication model, and 398 patients were included in the validation group. The clinicopathological data and 30-d postoperative complications of gastric cancer patients were collected. Three machine learning methods, lasso regression, random forest, and artificial neural networks, were used to construct postoperative complication prediction models for laparoscopic distal gastrectomy and laparoscopic total gastrectomy, and their prediction efficacy and accuracy were evaluated. RESULTS The constructed complication model, particularly the random forest model, could better predict serious complications in gastric cancer patients undergoing laparoscopic radical gastrectomy. It exhibited stable performance in external validation and is worthy of further promotion in more centers. CONCLUSION Using the risk factors identified in multicenter datasets, highly sensitive risk prediction models for complications following laparoscopic radical gastrectomy were established. We hope to facilitate the diagnosis and treatment of preoperative and postoperative decision-making by using these models.
Collapse
Affiliation(s)
- Qing-Qi Hong
- Department of Gastrointestinal Oncology Surgery, The First Affiliated Hospital of Xiamen University, School of Medicine, Xiamen 361001, Fujian Province, China
| | - Su Yan
- Department of Gastrointestinal Surgery, Qinghai University Affiliated Hospital, Xining 810000, Qinghai Province, China
| | - Yong-Liang Zhao
- Department of General Surgery and Center of Minimal Invasive Gastrointestinal Surgery, The First Hospital Affiliated to Army Medical University, Chongqing 400038, China
| | - Lin Fan
- Department of General Surgery, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an 710061, Shaanxi Province, China
| | - Li Yang
- Department of General Surgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, Jiangsu Province, China
| | - Wen-Bin Zhang
- Department of Gastrointestinal Surgery, The First Affiliated Hospital of Xinjiang Medical University, Urmuqi 830054, Xinjiang Uygur Autonomous Region, China
| | - Hao Liu
- Department of General Surgery, Nanfang Hospital, Southern Medical University, Guangzhou 510515, Guangdong Province, China
| | - He-Xin Lin
- Department of Gastrointestinal Oncology Surgery, The First Affiliated Hospital of Xiamen University, School of Medicine, Xiamen 361001, Fujian Province, China
| | - Jian Zhang
- Department of Gastrointestinal Surgery, Affiliated Hangzhou First People's Hospital, Zhejiang University School of Medicine, Hangzhou 310006, Zhejiang Province, China
| | - Zhi-Jian Ye
- Department of Gastrointestinal Surgery, Zhongshan Hospital of Xiamen University, Xiamen 361004, Fujian Province, China
| | - Xian Shen
- Department of Surgery, The Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou 325027, Zhejiang Province, China
| | - Li-Sheng Cai
- Department of General Surgery Unit 4, Zhangzhou Affiliated Hospital of Fujian Medical University, Zhangzhou 363000, Fujian Province, China
| | - Guo-Wei Zhang
- Department of Gastrointestinal Surgery, The Second Affiliated Hospital of Xiamen Medical College, Xiamen 361021, Fujian Province, China
| | - Jia-Ming Zhu
- Department of Gastrointestinal Nutrition and Hernia Surgery, The Second Hospital of Jilin University, Changchun 130041, Jilin Province, China
| | - Gang Ji
- Department of Digestive Diseases, Xijing Hospital, Air Force Military Medical University, Xi'an 710032, Shaanxi Province, China
| | - Jin-Ping Chen
- Department of Gastrointestinal Surgery, Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou 362002, Fujian Province, China
| | - Wei Wang
- Department of Gastrointestinal Surgery, Guangdong Provincial Hospital of Chinese Medicine, Guangzhou 510120, Guangdong Province, China
| | - Zheng-Rong Li
- Department of Gastrointestinal Surgery, The First Affiliated Hospital of Nanchang University, Nanchang 330006, Jiangxi Province, China
| | - Jing-Tao Zhu
- The Third Clinical Medical College, Fujian Medical University, Fuzhou 35000, Fujian Province, China
| | - Guo-Xin Li
- Department of General Surgery, Nanfang Hospital, Southern Medical University, Guangzhou 510515, Guangdong Province, China
| | - Jun You
- Department of Gastrointestinal Oncology Surgery, The First Affiliated Hospital of Xiamen University, School of Medicine, Xiamen 361001, Fujian Province, China
| |
Collapse
|
13
|
Hu H, Ke X, Zheng F, You M, Zhou T, Xu Y, Wu J, Tong S, Hu L. Diagnostic and prognostic value of diquat plasma concentration and complete blood count in patients with acute diquat poisoning based on random forest algorithms. Hum Exp Toxicol 2024; 43:9603271241276981. [PMID: 39226487 DOI: 10.1177/09603271241276981] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/05/2024]
Abstract
Currently, the incidence of diquat (DQ) poisoning is increasing, and quickly predicting the prognosis of poisoned patients is crucial for clinical treatment. In this study, a total of 84 DQ poisoning patients were included, with 38 surviving and 46 deceased. The plasma DQ concentration of DQ poisoned patients, determined by liquid chromatography-mass spectrometry (LC-MS) were collected and analyzed with their complete blood count (CBC) indicators. Based on DQ concentration and CBC dataset, the random forest of diagnostic and prognostic models were established. The results showed that the initial DQ plasma concentration was highly correlated with patient prognosis. There was data redundancy in the CBC dataset, continuous measurement of CBC tests could improve the model's predictive accuracy. After feature selection, the predictive accuracy of the CBC dataset significantly increased to 0.81 ± 0.17, with the most important features being white blood cells and neutrophils. The constructed CBC random forest prediction model achieved a high predictive accuracy of 0.95 ± 0.06 when diagnosing DQ poisoning. In conclusion, both DQ concentration and CBC dataset can be used to predict the prognosis of DQ treatment. In the absence of DQ concentration, the random forest model using CBC data can effectively diagnose DQ poisoning and patient's prognosis.
Collapse
Affiliation(s)
- Hui Hu
- Department of Pharmacy, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Xiaofang Ke
- Department of Pharmacy, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Fangfang Zheng
- The First Clinical Medical College, Wenzhou Medical University, Wenzhou, China
| | - Minjie You
- The First Clinical Medical College, Wenzhou Medical University, Wenzhou, China
| | - Tao Zhou
- The First Clinical Medical College, Wenzhou Medical University, Wenzhou, China
| | - Yanwen Xu
- The First Clinical Medical College, Wenzhou Medical University, Wenzhou, China
| | - Jiaiying Wu
- The First Clinical Medical College, Wenzhou Medical University, Wenzhou, China
| | - Shuhua Tong
- Department of Pharmacy, Maternal and Child Health Hospital of Hubei Province, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Lufeng Hu
- Department of Pharmacy, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| |
Collapse
|
14
|
Liu Z, Liu J, Geng J, Wu E, Zhu J, Cong B, Wu R, Sun H. Metatranscriptomic characterization of six types of forensic samples and its potential application to body fluid/tissue identification: A pilot study. Forensic Sci Int Genet 2024; 68:102978. [PMID: 37995518 DOI: 10.1016/j.fsigen.2023.102978] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2023] [Revised: 10/21/2023] [Accepted: 11/13/2023] [Indexed: 11/25/2023]
Abstract
Microorganisms are potential markers for identifying body fluids (venous and menstrual blood, semen, saliva, and vaginal secretion) and skin tissue in forensic genetics. Existing published studies have mainly focused on investigating microbial DNA by 16 S rRNA gene sequencing or metagenome shotgun sequencing. We rarely find microbial RNA level investigations on common forensic body fluid/tissue. Therefore, the use of metatranscriptomics to characterize common forensic body fluids/tissue has not been explored in detail, and the potential application of metatranscriptomics in forensic science remains unknown. Here, we performed 30 metatranscriptome analyses on six types of common forensic sample from healthy volunteers by massively parallel sequencing. After quality control and host RNA filtering, a total of 345,300 unigenes were assembled from clean reads. Four kingdoms, 137 phyla, 267 classes, 488 orders, 985 families, 2052 genera, and 4690 species were annotated across all samples. Alpha- and beta-diversity and differential analysis were also performed. As a result, the saliva and skin groups demonstrated high alpha diversity (Simpson index), while the venous blood group exhibited the lowest diversity despite a high Chao1 index. Specifically, we discussed potential microorganism contamination and the "core microbiome," which may be of special interest to forensic researchers. In addition, we implemented and evaluated artificial neural network (ANN), random forest (RF), and support vector machine (SVM) models for forensic body fluid/tissue identification (BFID) using genus- and species-level metatranscriptome profiles. The ANN and RF prediction models discriminated six forensic body fluids/tissue, demonstrating that the microbial RNA-based method could be applied to BFID. Unlike metagenomic research, metatranscriptomic analysis can provide information about active microbial communities; thus, it may have greater potential to become a powerful tool in forensic science for microbial-based individual identification. This study represents the first attempt to explore the application potential of metatranscriptome profiles in forensic science. Our findings help deepen our understanding of the microorganism community structure at the RNA level and are beneficial for other forensic applications of metatranscriptomics.
Collapse
Affiliation(s)
- Zhiyong Liu
- Faculty of Forensic Medicine, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou 510080, China; Guangdong Province Translational Forensic Medicine Engineering Technology Research Center, Sun Yat-sen University, Guangzhou 510080, China
| | - Jiajun Liu
- Faculty of Forensic Medicine, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou 510080, China; Guangdong Province Translational Forensic Medicine Engineering Technology Research Center, Sun Yat-sen University, Guangzhou 510080, China
| | - Jiaojiao Geng
- Faculty of Forensic Medicine, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou 510080, China; Guangdong Province Translational Forensic Medicine Engineering Technology Research Center, Sun Yat-sen University, Guangzhou 510080, China
| | - Enlin Wu
- Faculty of Forensic Medicine, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou 510080, China; Guangdong Province Translational Forensic Medicine Engineering Technology Research Center, Sun Yat-sen University, Guangzhou 510080, China
| | - Jianzhang Zhu
- Guangzhou Eighth People's Hospital, Guangzhou Medical University, Guangzhou 510080, China
| | - Bin Cong
- College of Forensic Medicine, Hebei Medical University, Hebei Key Laboratory of Forensic Medicine, Shijiazhuang 050017, China.
| | - Riga Wu
- Faculty of Forensic Medicine, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou 510080, China; Guangdong Province Translational Forensic Medicine Engineering Technology Research Center, Sun Yat-sen University, Guangzhou 510080, China.
| | - Hongyu Sun
- Faculty of Forensic Medicine, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou 510080, China; Guangdong Province Translational Forensic Medicine Engineering Technology Research Center, Sun Yat-sen University, Guangzhou 510080, China.
| |
Collapse
|
15
|
Kim M, Kim TH, Kim D, Lee D, Kim D, Heo J, Kang S, Ha T, Kim J, Moon DH, Heo Y, Kim WJ, Lee SJ, Kim Y, Park SW, Han SS, Choi HS. In-Advance Prediction of Pressure Ulcers via Deep-Learning-Based Robust Missing Value Imputation on Real-Time Intensive Care Variables. J Clin Med 2023; 13:36. [PMID: 38202043 PMCID: PMC10780209 DOI: 10.3390/jcm13010036] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2023] [Revised: 12/06/2023] [Accepted: 12/15/2023] [Indexed: 01/12/2024] Open
Abstract
Pressure ulcers (PUs) are a prevalent skin disease affecting patients with impaired mobility and in high-risk groups. These ulcers increase patients' suffering, medical expenses, and burden on medical staff. This study introduces a clinical decision support system and verifies it for predicting real-time PU occurrences within the intensive care unit (ICU) by using MIMIC-IV and in-house ICU data. We develop various machine learning (ML) and deep learning (DL) models for predicting PU occurrences in real time using the MIMIC-IV and validate using the MIMIC-IV and Kangwon National University Hospital (KNUH) dataset. To address the challenge of missing values in time series, we propose a novel recurrent neural network model, GRU-D++. This model outperformed other experimental models by achieving the area under the receiver operating characteristic curve (AUROC) of 0.945 for the on-time prediction and AUROC of 0.912 for 48h in-advance prediction. Furthermore, in the external validation with the KNUH dataset, the fine-tuned GRU-D++ model demonstrated superior performances, achieving an AUROC of 0.898 for on-time prediction and an AUROC of 0.897 for 48h in-advance prediction. The proposed GRU-D++, designed to consider temporal information and missing values, stands out for its predictive accuracy. Our findings suggest that this model can significantly alleviate the workload of medical staff and prevent the worsening of patient conditions by enabling timely interventions for PUs in the ICU.
Collapse
Affiliation(s)
- Minkyu Kim
- Department of Research & Development, Ziovision Co., Ltd., Chuncheon 24341, Republic of Korea; (M.K.); (D.K.); (D.L.); (D.K.)
| | - Tae-Hoon Kim
- Department of Internal Medicine, Kangwon National University, Chuncheon 24341, Republic of Korea; (T.-H.K.); (J.H.); (J.K.); (D.H.M.); (Y.H.); (W.J.K.); (S.-J.L.)
| | - Dowon Kim
- Department of Research & Development, Ziovision Co., Ltd., Chuncheon 24341, Republic of Korea; (M.K.); (D.K.); (D.L.); (D.K.)
| | - Donghoon Lee
- Department of Research & Development, Ziovision Co., Ltd., Chuncheon 24341, Republic of Korea; (M.K.); (D.K.); (D.L.); (D.K.)
| | - Dohyun Kim
- Department of Research & Development, Ziovision Co., Ltd., Chuncheon 24341, Republic of Korea; (M.K.); (D.K.); (D.L.); (D.K.)
| | - Jeongwon Heo
- Department of Internal Medicine, Kangwon National University, Chuncheon 24341, Republic of Korea; (T.-H.K.); (J.H.); (J.K.); (D.H.M.); (Y.H.); (W.J.K.); (S.-J.L.)
| | - Seonguk Kang
- Department of Convergence Security, Kangwon National University, Chuncheon 24341, Republic of Korea;
| | - Taejun Ha
- Biomedical Research Institute, Kangwon National University Hospital, Chuncheon 24289, Republic of Korea;
| | - Jinju Kim
- Department of Internal Medicine, Kangwon National University, Chuncheon 24341, Republic of Korea; (T.-H.K.); (J.H.); (J.K.); (D.H.M.); (Y.H.); (W.J.K.); (S.-J.L.)
| | - Da Hye Moon
- Department of Internal Medicine, Kangwon National University, Chuncheon 24341, Republic of Korea; (T.-H.K.); (J.H.); (J.K.); (D.H.M.); (Y.H.); (W.J.K.); (S.-J.L.)
- Department of Pulmonology, Kangwon National University Hospital, Chuncheon 24289, Republic of Korea
| | - Yeonjeong Heo
- Department of Internal Medicine, Kangwon National University, Chuncheon 24341, Republic of Korea; (T.-H.K.); (J.H.); (J.K.); (D.H.M.); (Y.H.); (W.J.K.); (S.-J.L.)
- Department of Pulmonology, Kangwon National University Hospital, Chuncheon 24289, Republic of Korea
| | - Woo Jin Kim
- Department of Internal Medicine, Kangwon National University, Chuncheon 24341, Republic of Korea; (T.-H.K.); (J.H.); (J.K.); (D.H.M.); (Y.H.); (W.J.K.); (S.-J.L.)
| | - Seung-Joon Lee
- Department of Internal Medicine, Kangwon National University, Chuncheon 24341, Republic of Korea; (T.-H.K.); (J.H.); (J.K.); (D.H.M.); (Y.H.); (W.J.K.); (S.-J.L.)
| | - Yoon Kim
- Department of Computer Science and Engineering, Kangwon National University, Chuncheon 24341, Republic of Korea;
| | - Sang Won Park
- Department of Medical Informatics, School of Medicine, Kangwon National University, Chuncheon 24341, Republic of Korea;
- Institute of Medical Science, School of Medicine, Kangwon National University, Chuncheon 24341, Republic of Korea
| | - Seon-Sook Han
- Department of Internal Medicine, Kangwon National University, Chuncheon 24341, Republic of Korea; (T.-H.K.); (J.H.); (J.K.); (D.H.M.); (Y.H.); (W.J.K.); (S.-J.L.)
| | - Hyun-Soo Choi
- Department of Computer Science and Engineering, Seoul National University of Science and Technology, Seoul 01811, Republic of Korea
| |
Collapse
|
16
|
Pei J, Guo X, Tao H, Wei Y, Zhang H, Ma Y, Han L. Machine learning-based prediction models for pressure injury: A systematic review and meta-analysis. Int Wound J 2023; 20:4328-4339. [PMID: 37340520 PMCID: PMC10681397 DOI: 10.1111/iwj.14280] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2023] [Accepted: 06/01/2023] [Indexed: 06/22/2023] Open
Abstract
Despite the fact that machine learning (ML) algorithms to construct predictive models for pressure injury development are widely reported, the performance of the model remains unknown. The goal of the review was to systematically appraise the performance of ML models in predicting pressure injury. PubMed, Embase, Cochrane Library, Web of Science, CINAHL, Grey literature and other databases were systematically searched. Original journal papers were included which met the inclusion criteria. The methodological quality was assessed independently by two reviewers using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Meta-analysis was performed with Metadisc software, with the area under the receiver operating characteristic curve, sensitivity and specificity as effect measures. Chi-squared and I2 tests were used to assess the heterogeneity. A total of 18 studies were included for the narrative review, and 14 of them were eligible for meta-analysis. The models achieved excellent pooled AUC of 0.94, sensitivity of 0.79 (95% CI [0.78-0.80]) and specificity of 0.87 (95% CI [0.88-0.87]). Meta-regressions did not provide evidence that model performance varied by data or model types. The present findings indicate that ML models show an outstanding performance in predicting pressure injury. However, good-quality studies should be conducted to verify our results and confirm the clinical value of ML in pressure injury development.
Collapse
Affiliation(s)
- Juhong Pei
- The First Clinical Medical College, School of NursingLanzhou UniversityLanzhouChina
| | | | - Hongxia Tao
- The First Clinical Medical College, School of NursingLanzhou UniversityLanzhouChina
| | - Yuting Wei
- School of NursingLanzhou UniversityLanzhouChina
| | - Hongyan Zhang
- Department of NursingGansu Provincial HospitalLanzhouChina
| | - Yuxia Ma
- School of NursingLanzhou UniversityLanzhouChina
| | - Lin Han
- The First Clinical Medical College, School of NursingLanzhou UniversityLanzhouChina
- Department of NursingGansu Provincial HospitalLanzhouChina
| |
Collapse
|
17
|
Owusu-Adjei M, Ben Hayfron-Acquah J, Frimpong T, Abdul-Salaam G. Imbalanced class distribution and performance evaluation metrics: A systematic review of prediction accuracy for determining model performance in healthcare systems. PLOS DIGITAL HEALTH 2023; 2:e0000290. [PMID: 38032863 PMCID: PMC10688675 DOI: 10.1371/journal.pdig.0000290] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/31/2023] [Accepted: 10/29/2023] [Indexed: 12/02/2023]
Abstract
Focus on predictive algorithm and its performance evaluation is extensively covered in most research studies to determine best or appropriate predictive model with Optimum prediction solution indicated by prediction accuracy score, precision, recall, f1score etc. Prediction accuracy score from performance evaluation has been used extensively as the main determining metric for performance recommendation. It is one of the most widely used metric for identifying optimal prediction solution irrespective of dataset class distribution context or nature of dataset and output class distribution between the minority and majority variables. The key research question however is the impact of class inequality on prediction accuracy score in such datasets with output class distribution imbalance as compared to balanced accuracy score in the determination of model performance in healthcare and other real-world application systems. Answering this question requires an appraisal of current state of knowledge in both prediction accuracy score and balanced accuracy score use in real-world applications where there is unequal class distribution. Review of related works that highlight the use of imbalanced class distribution datasets with evaluation metrics will assist in contextualizing this systematic review.
Collapse
Affiliation(s)
- Michael Owusu-Adjei
- Department of Computer Science, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana
| | - James Ben Hayfron-Acquah
- Department of Computer Science, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana
| | - Twum Frimpong
- Department of Computer Science, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana
| | - Gaddafi Abdul-Salaam
- Department of Computer Science, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana
| |
Collapse
|
18
|
Toffaha KM, Simsekler MCE, Omar MA. Leveraging artificial intelligence and decision support systems in hospital-acquired pressure injuries prediction: A comprehensive review. Artif Intell Med 2023; 141:102560. [PMID: 37295900 DOI: 10.1016/j.artmed.2023.102560] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2022] [Revised: 04/19/2023] [Accepted: 04/20/2023] [Indexed: 06/12/2023]
Abstract
BACKGROUND Hospital-acquired pressure injuries (HAPIs) constitute a significant challenge harming thousands of people worldwide yearly. While various tools and methods are used to identify pressure injuries, artificial intelligence (AI) and decision support systems (DSS) can help to reduce HAPIs risks by proactively identifying patients at risk and preventing them before harming patients. OBJECTIVE This paper comprehensively reviews AI and DSS applications for HAPIs prediction using Electronic Health Records (EHR), including a systematic literature review and bibliometric analysis. METHODS A systematic literature review was conducted through PRISMA and bibliometric analysis. In February 2023, the search was performed using four electronic databases: SCOPIS, PubMed, EBSCO, and PMCID. Articles on using AI and DSS in the management of PIs were included. RESULTS The search approach yielded 319 articles, 39 of which have been included and classified into 27 AI-related and 12 DSS-related categories. The years of publication varied from 2006 to 2023, with 40% of the studies taking place in the US. Most studies focused on using AI algorithms or DSS for HAPIs prediction in inpatient units using various types of data such as electronic health records, PI assessment scales, and expert knowledge-based and environmental data to identify the risk factors associated with HAPIs development. CONCLUSIONS There is insufficient evidence in the existing literature concerning the real impact of AI or DSS on making decisions for HAPIs treatment or prevention. Most studies reviewed are solely hypothetical and retrospective prediction models, with no actual application in healthcare settings. The accuracy rates, prediction results, and intervention procedures suggested based on the prediction, on the other hand, should inspire researchers to combine both approaches with larger-scale data to bring a new venue for HAPIs prevention and to investigate and adopt the suggested solutions to the existing gaps in AI and DSS prediction methods.
Collapse
Affiliation(s)
- Khaled M Toffaha
- Department of Industrial and Systems Engineering, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates
| | - Mecit Can Emre Simsekler
- Department of Industrial and Systems Engineering, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates.
| | - Mohammed Atif Omar
- Department of Industrial and Systems Engineering, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates
| |
Collapse
|
19
|
Dweekat OY, Lam SS, McGrath L. An Integrated System of Braden Scale and Random Forest Using Real-Time Diagnoses to Predict When Hospital-Acquired Pressure Injuries (Bedsores) Occur. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2023; 20:4911. [PMID: 36981818 PMCID: PMC10049700 DOI: 10.3390/ijerph20064911] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/12/2022] [Revised: 02/24/2023] [Accepted: 03/06/2023] [Indexed: 06/18/2023]
Abstract
BACKGROUND AND OBJECTIVES Bedsores/Pressure Injuries (PIs) are the second most common diagnosis in healthcare system billing records in the United States and account for 60,000 deaths annually. Hospital-Acquired Pressure Injuries (HAPIs) are one classification of PIs and indicate injuries that occurred while the patient was cared for within the hospital. Until now, all studies have predicted who will develop HAPI using classic machine algorithms, which provides incomplete information for the clinical team. Knowing who will develop HAPI does not help differentiate at which point those predicted patients will develop HAPIs; no studies have investigated when HAPI develops for predicted at-risk patients. This research aims to develop a hybrid system of Random Forest (RF) and Braden Scale to predict HAPI time by considering the changes in patients' diagnoses from admission until HAPI occurrence. METHODS Real-time diagnoses and risk factors were collected daily for 485 patients from admission until HAPI occurrence, which resulted in 4619 records. Then for each record, HAPI time was calculated from the day of diagnosis until HAPI occurrence. Recursive Feature Elimination (RFE) selected the best factors among the 60 factors. The dataset was separated into 80% training (10-fold cross-validation) and 20% testing. Grid Search (GS) with RF (GS-RF) was adopted to predict HAPI time using collected risk factors, including Braden Scale. Then, the proposed model was compared with the seven most common algorithms used to predict HAPI; each was replicated for 50 different experiments. RESULTS GS-RF achieved the best Area Under the Curve (AUC) (91.20 ± 0.26) and Geometric Mean (G-mean) (91.17 ± 0.26) compared to the seven algorithms. RFE selected 43 factors. The most dominant interactable risk factors in predicting HAPI time were visiting ICU during hospitalization, Braden subscales, BMI, Stimuli Anesthesia, patient refusal to change position, and another lab diagnosis. CONCLUSION Identifying when the patient is likely to develop HAPI can target early intervention when it is needed most and reduces unnecessary burden on patients and care teams when patients are at lower risk, which further individualizes the plan of care.
Collapse
Affiliation(s)
- Odai Y. Dweekat
- Department of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA
| | - Sarah S. Lam
- Department of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA
| | - Lindsay McGrath
- Wound Ostomy Continence Nursing, ChristianaCare Health System, Newark, DE 19718, USA
| |
Collapse
|
20
|
Dweekat OY, Lam SS, McGrath L. An Integrated System of Multifaceted Machine Learning Models to Predict If and When Hospital-Acquired Pressure Injuries (Bedsores) Occur. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2023; 20:ijerph20010828. [PMID: 36613150 PMCID: PMC9820011 DOI: 10.3390/ijerph20010828] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/13/2022] [Revised: 12/21/2022] [Accepted: 12/27/2022] [Indexed: 06/12/2023]
Abstract
Hospital-Acquired Pressure Injury (HAPI), known as bedsore or decubitus ulcer, is one of the most common health conditions in the United States. Machine learning has been used to predict HAPI. This is insufficient information for the clinical team because knowing who would develop HAPI in the future does not help differentiate the severity of those predicted cases. This research develops an integrated system of multifaceted machine learning models to predict if and when HAPI occurs. Phase 1 integrates Genetic Algorithm with Cost-Sensitive Support Vector Machine (GA-CS-SVM) to handle the high imbalance HAPI dataset to predict if patients will develop HAPI. Phase 2 adopts Grid Search with SVM (GS-SVM) to predict when HAPI will occur for at-risk patients. This helps to prioritize who is at the highest risk and when that risk will be highest. The performance of the developed models is compared with state-of-the-art models in the literature. GA-CS-SVM achieved the best Area Under the Curve (AUC) (75.79 ± 0.58) and G-mean (75.73 ± 0.59), while GS-SVM achieved the best AUC (75.06) and G-mean (75.06). The research outcomes will help prioritize at-risk patients, allocate targeted resources and aid with better medical staff planning to provide intervention to those patients.
Collapse
Affiliation(s)
- Odai Y. Dweekat
- Department of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA
| | - Sarah S. Lam
- Department of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA
| | - Lindsay McGrath
- Wound Ostomy Continence Nursing, ChristianaCare Health System, Newark, DE 19718, USA
| |
Collapse
|
21
|
Dweekat OY, Lam SS, McGrath L. Machine Learning Techniques, Applications, and Potential Future Opportunities in Pressure Injuries (Bedsores) Management: A Systematic Review. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2023; 20:796. [PMID: 36613118 PMCID: PMC9819814 DOI: 10.3390/ijerph20010796] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/18/2022] [Revised: 12/21/2022] [Accepted: 12/27/2022] [Indexed: 06/17/2023]
Abstract
Pressure Injuries (PI) are one of the most common health conditions in the United States. Most acute or long-term care patients are at risk of developing PI. Machine Learning (ML) has been utilized to manage patients with PI, in which one systematic review describes how ML is used in PI management in 32 studies. This research, different from the previous systematic review, summarizes the previous contributions of ML in PI from January 2007 to July 2022, categorizes the studies according to medical specialties, analyzes gaps, and identifies opportunities for future research directions. PRISMA guidelines were adopted using the four most common databases (PubMed, Web of Science, Scopus, and Science Direct) and other resources, which result in 90 eligible studies. The reviewed articles are divided into three categories based on PI time of occurrence: before occurrence (48%); at time of occurrence (16%); and after occurrence (36%). Each category is further broken down into sub-fields based on medical specialties, which result in sixteen specialties. Each specialty is analyzed in terms of methods, inputs, and outputs. The most relevant and potentially useful applications and methods in PI management are outlined and discussed. This includes deep learning techniques and hybrid models, integration of existing risk assessment tools with ML that leads to a partnership between provider assessment and patients' Electronic Health Records (EHR).
Collapse
Affiliation(s)
- Odai Y. Dweekat
- Department of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA
| | - Sarah S. Lam
- Department of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA
| | - Lindsay McGrath
- Wound Ostomy Continence Nursing, ChristianaCare Health System, Newark, DE 19718, USA
| |
Collapse
|
22
|
Dweekat OY, Lam SS, McGrath L. A Hybrid System of Braden Scale and Machine Learning to Predict Hospital-Acquired Pressure Injuries (Bedsores): A Retrospective Observational Cohort Study. Diagnostics (Basel) 2022; 13:diagnostics13010031. [PMID: 36611323 PMCID: PMC9818183 DOI: 10.3390/diagnostics13010031] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2022] [Revised: 12/16/2022] [Accepted: 12/19/2022] [Indexed: 12/25/2022] Open
Abstract
Background: The Braden Scale is commonly used to determine Hospital-Acquired Pressure Injuries (HAPI). However, the volume of patients who are identified as being at risk stretches already limited resources, and caregivers are limited by the number of factors that can reasonably assess during patient care. In the last decade, machine learning techniques have been used to predict HAPI by utilizing related risk factors. Nevertheless, none of these studies consider the change in patient status from admission until discharge. Objectives: To develop an integrated system of Braden and machine learning to predict HAPI and assist with resource allocation for early interventions. The proposed approach captures the change in patients' risk by assessing factors three times across hospitalization. Design: Retrospective observational cohort study. Setting(s): This research was conducted at ChristianaCare hospital in Delaware, United States. Participants: Patients discharged between May 2020 and February 2022. Patients with HAPI were identified from Nursing documents (N = 15,889). Methods: Support Vector Machine (SVM) was adopted to predict patients' risk for developing HAPI using multiple risk factors in addition to Braden. Multiple performance metrics were used to compare the results of the integrated system versus Braden alone. Results: The HAPI rate is 3%. The integrated system achieved better sensitivity (74.29 ± 1.23) and detection prevalence (24.27 ± 0.16) than the Braden scale alone (sensitivity (66.90 ± 4.66) and detection prevalence (41.96 ± 1.35)). The most important risk factors to predict HAPI were Braden sub-factors, overall Braden, visiting ICU during hospitalization, and Glasgow coma score. Conclusions: The integrated system which combines SVM with Braden offers better performance than Braden and reduces the number of patients identified as at-risk. Furthermore, it allows for better allocation of resources to high-risk patients. It will result in cost savings and better utilization of resources. Relevance to clinical practice: The developed model provides an automated system to predict HAPI patients in real time and allows for ongoing intervention for patients identified as at-risk. Moreover, the integrated system is used to determine the number of nurses needed for early interventions. Reporting Method: EQUATOR guidelines (TRIPOD) were adopted in this research to develop the prediction model. Patient or Public Contribution: This research was based on a secondary analysis of patients' Electronic Health Records. The dataset was de-identified and patient identifiers were removed before processing and modeling.
Collapse
Affiliation(s)
- Odai Y. Dweekat
- Department of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA
- Correspondence:
| | - Sarah S. Lam
- Department of Systems Science and Industrial Engineering, Binghamton University, Binghamton, NY 13902, USA
| | - Lindsay McGrath
- Wound Ostomy Continence Nursing, ChristianaCare Health System, Newark, DE 19718, USA
| |
Collapse
|
23
|
Qu C, Luo W, Zeng Z, Lin X, Gong X, Wang X, Zhang Y, Li Y. The predictive effect of different machine learning algorithms for pressure injuries in hospitalized patients: A network meta-analyses. Heliyon 2022; 8:e11361. [DOI: 10.1016/j.heliyon.2022.e11361] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2022] [Revised: 09/21/2022] [Accepted: 10/27/2022] [Indexed: 11/09/2022] Open
|
24
|
Zhou Y, Yang X, Ma S, Yuan Y, Yan M. A systematic review of predictive models for hospital-acquired pressure injury using machine learning. Nurs Open 2022; 10:1234-1246. [PMID: 36310417 PMCID: PMC9912391 DOI: 10.1002/nop2.1429] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2021] [Revised: 02/28/2022] [Accepted: 10/11/2022] [Indexed: 02/11/2023] Open
Abstract
AIMS AND OBJECTIVES To summarize the use of machine learning (ML) for hospital-acquired pressure injury (HAPI) prediction and to systematically assess the performance and construction process of ML models to provide references for establishing high-quality ML predictive models. BACKGROUND As an adverse event, HAPI seriously affects patient prognosis and quality of life, and causes unnecessary medical investment. At present, the performance of various scales used to predict HAPIs is still unsatisfactory. As a new statistical tool, ML has been applied to predict HAPIs. However, its performance has varied in different studies; moreover, some deficiencies in the model construction process were observed in each study. DESIGN Systematic review. METHODS Relevant articles published between 2010-2021 were identified in the PubMed, Web of Science, Scopus, Embase and CINHAL databases. Study selection was performed in accordance with the preferred reporting items for systematic reviews and meta-analysis guidelines. The quality of the included articles was assessed using the prediction model risk of bias assessment tool. RESULTS Twenty-three studies out of 1793 articles were considered in this systematic review. The sample size of each study ranged from 149-75353; the prevalence of pressure injuries ranged from 0.5%-49.8%. ML showed good performance for HAPI prediction. However, some deficiencies were observed in terms of data management, data pre-processing and model validation. CONCLUSIONS ML, as a powerful decision-making assistance tool, is helpful for the prediction of HAPIs. However, existing studies have been insufficient in terms of data management, data pre-processing and model validation. Future studies should address these issues to establish ML models for HAPI prediction that can be widely used in clinical practice. RELEVANCE TO CLINICAL PRACTICE This review highlights that ML is helpful in predicting HAPI; however, in the process of data management, data pre-processing and model validation, some deficiencies still need to be addressed. The ultimate goal of integrating ML into HAPI prediction is to develop a practical clinical decision-making tool. A complete and rigorous model construction process should be followed in future studies to develop high-quality ML models that can be applied in clinical practice.
Collapse
Affiliation(s)
- You Zhou
- Department of Gastroenterology, Affiliated Hospital of Yangzhou UniversityYangzhou UniversityYangzhouChina,School of Nursing, School of Public HealthYangzhou UniversityYangzhouChina
| | - Xiaoxi Yang
- Department of Gastroenterology, Affiliated Hospital of Yangzhou UniversityYangzhou UniversityYangzhouChina,School of Nursing, School of Public HealthYangzhou UniversityYangzhouChina
| | - Shuli Ma
- Department of Gastroenterology, Affiliated Hospital of Yangzhou UniversityYangzhou UniversityYangzhouChina,School of Nursing, School of Public HealthYangzhou UniversityYangzhouChina
| | - Yuan Yuan
- Department of Nursing, Affiliated Hospital of Yangzhou UniversityYangzhou UniversityYangzhouChina
| | - Mingquan Yan
- Department of Gastroenterology, Affiliated Hospital of Yangzhou UniversityYangzhou UniversityYangzhouChina
| |
Collapse
|
25
|
Jiang X, Wang Y, Wang Y, Zhou M, Huang P, Yang Y, Peng F, Wang H, Li X, Zhang L, Cai F. Application of an infrared thermography-based model to detect pressure injuries: a prospective cohort study. Br J Dermatol 2022; 187:571-579. [PMID: 35560229 DOI: 10.1111/bjd.21665] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2021] [Revised: 05/09/2022] [Accepted: 05/10/2022] [Indexed: 02/02/2023]
Abstract
BACKGROUND It is challenging to detect pressure injuries at an early stage of their development. OBJECTIVES To assess the ability of an infrared thermography (IRT)-based model, constructed using a convolution neural network, to reliably detect pressure injuries. METHODS A prospective cohort study compared validity in patients with pressure injury (n = 58) and without pressure injury (n = 205) using different methods. Each patient was followed up for 10 days. RESULTS The optimal cut-off values of the IRT-based model were 0·53 for identifying tissue damage 1 day before visual detection of pressure injury and 0·88 for pressure injury detection on the day visual detection is possible. Kaplan-Meier curves and Cox proportional hazard regression model analysis showed that the risk of pressure injury increased 13-fold 1 day before visual detection with a cut-off value higher than 0·53 [hazard ratio (HR) 13·04, 95% confidence interval (CI) 6·32-26·91; P < 0·001]. The ability of the IRT-based model to detect pressure injuries [area under the receiver operating characteristic curve (AUC)lag 0 days , 0·98, 95% CI 0·95-1·00] was better than that of other methods. CONCLUSIONS The IRT-based model is a useful and reliable method for clinical dermatologists and nurses to detect pressure injuries. It can objectively and accurately detect pressure injuries 1 day before visual detection and is therefore able to guide prevention earlier than would otherwise be possible. What is already known about this topic? Detection of pressure injuries at an early stage is challenging. Infrared thermography can be used for the physiological and anatomical evaluation of subcutaneous tissue abnormalities. A convolutional neural network is increasingly used in medical imaging analysis. What does this study add? The optimal cut-off values of the IRT-based model were 0·53 for identifying tissue damage 1 day before visual detection of pressure injury and 0·88 for pressure injury detection on the day visual detection is possible. Infrared thermography-based models can be used by clinical dermatologists and nurses to detect pressure injuries at an early stage objectively and accurately.
Collapse
Affiliation(s)
- Xiaoqiong Jiang
- College of Nursing, Wenzhou Medical University, Wenzhou, China
| | - Yu Wang
- Medical Engineering Office, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Yuxin Wang
- College of Nursing, Wenzhou Medical University, Wenzhou, China
| | - Min Zhou
- College of Nursing, Wenzhou Medical University, Wenzhou, China
| | - Pan Huang
- College of Nursing, Wenzhou Medical University, Wenzhou, China
| | - Yufan Yang
- The Second Clinical College, Wenzhou Medical University, Wenzhou, China
| | - Fang Peng
- School of Public Health and Management, Wenzhou Medical University, Wenzhou, China
| | - Haishuang Wang
- Cardiovascular Medicine Deparment, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Xiaomei Li
- School of Nursing, Xi'an Jiaotong University Health Science Centre, Xi'an, China
| | - Liping Zhang
- The Second Affiliated Hospital of Wenzhou Medical University, Wenzhou, China
| | - Fuman Cai
- College of Nursing, Wenzhou Medical University, Wenzhou, China
| |
Collapse
|
26
|
Exploring the predictive capability of machine learning models in identifying foot and mouth disease outbreak occurrences in cattle farms in an endemic setting of Thailand. Prev Vet Med 2022; 207:105706. [DOI: 10.1016/j.prevetmed.2022.105706] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/10/2022] [Revised: 06/09/2022] [Accepted: 07/01/2022] [Indexed: 11/20/2022]
|
27
|
Liang X, Han X, Liu C, Du W, Zhong P, Huang L, Huang M, Fu L, Liu C, Chen L. Integrating the salivary microbiome in the forensic toolkit by 16S rRNA gene: potential application in body fluid identification and biogeographic inference. Int J Legal Med 2022; 136:975-985. [PMID: 35536322 DOI: 10.1007/s00414-022-02831-z] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2022] [Accepted: 04/21/2022] [Indexed: 11/30/2022]
Abstract
Saliva is a common body fluid with significant forensic value used to investigate criminal cases such as murder and assault. In the past, saliva identification often relied on the α-amylase test; however, this method has low specificity and is prone to false positives. Accordingly, forensic researchers have been working to find new specific molecular markers to refine the current saliva identification approach. At present, research on immunological methods, mRNA, microRNA, circRNA, and DNA methylation is still in the exploratory stage, and the application of these markers still has various limitations. It has been established that salivary microorganisms exhibit good specificity and stability. In this study, 16S rDNA sequencing technology was used to sequence the V3-V4 hypervariable regions in saliva samples from five regions to reveal the role of regional location on the heterogeneity in microbial profile information in saliva. Although the relative abundance of salivary flora was affected to a certain extent by geographical factors, the salivary flora of each sample was still dominated by Streptococcus, Neisseria, and Rothia. In addition, the microbial community in the saliva samples in this study was significantly different from that in the vaginal secretions, semen, and skin samples reported in our previous studies. Accordingly, saliva can be distinguished from the other three body fluids and tissues. Moreover, we established a prediction model based on the random forest algorithm that could distinguish saliva between different regions at the genus level even though the model has a certain probability of misjudgment which needs more in-depth research. Overall, the microbial community information in saliva stains might have prospects for potential application in body fluid identification and biogeographic inference.
Collapse
Affiliation(s)
- Xiaomin Liang
- Multi-Omics Innovative Research Center of Forensic Identification, Department of Forensic Genetics, School of Forensic Medicine, Southern Medical University, Guangzhou, 510515, People's Republic of China
| | - Xiaolong Han
- Guangzhou Forensic Science Institute, Guangzhou, 510030, People's Republic of China
| | - Changhui Liu
- Guangzhou Forensic Science Institute, Guangzhou, 510030, People's Republic of China
| | - Weian Du
- Multi-Omics Innovative Research Center of Forensic Identification, Department of Forensic Genetics, School of Forensic Medicine, Southern Medical University, Guangzhou, 510515, People's Republic of China
| | - Peiwen Zhong
- Multi-Omics Innovative Research Center of Forensic Identification, Department of Forensic Genetics, School of Forensic Medicine, Southern Medical University, Guangzhou, 510515, People's Republic of China
| | - Litao Huang
- Multi-Omics Innovative Research Center of Forensic Identification, Department of Forensic Genetics, School of Forensic Medicine, Southern Medical University, Guangzhou, 510515, People's Republic of China
| | - Manling Huang
- Multi-Omics Innovative Research Center of Forensic Identification, Department of Forensic Genetics, School of Forensic Medicine, Southern Medical University, Guangzhou, 510515, People's Republic of China
| | - Linhe Fu
- Multi-Omics Innovative Research Center of Forensic Identification, Department of Forensic Genetics, School of Forensic Medicine, Southern Medical University, Guangzhou, 510515, People's Republic of China
| | - Chao Liu
- Multi-Omics Innovative Research Center of Forensic Identification, Department of Forensic Genetics, School of Forensic Medicine, Southern Medical University, Guangzhou, 510515, People's Republic of China.
- Guangzhou Forensic Science Institute, Guangzhou, 510030, People's Republic of China.
| | - Ling Chen
- Multi-Omics Innovative Research Center of Forensic Identification, Department of Forensic Genetics, School of Forensic Medicine, Southern Medical University, Guangzhou, 510515, People's Republic of China.
| |
Collapse
|
28
|
Barbosa-Silva A, Magalhães M, Da Silva GF, Da Silva FAB, Carneiro FRG, Carels N. A Data Science Approach for the Identification of Molecular Signatures of Aggressive Cancers. Cancers (Basel) 2022; 14:2325. [PMID: 35565454 PMCID: PMC9103663 DOI: 10.3390/cancers14092325] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2022] [Revised: 03/04/2022] [Accepted: 03/12/2022] [Indexed: 02/05/2023] Open
Abstract
The main hallmarks of cancer include sustaining proliferative signaling and resisting cell death. We analyzed the genes of the WNT pathway and seven cross-linked pathways that may explain the differences in aggressiveness among cancer types. We divided six cancer types (liver, lung, stomach, kidney, prostate, and thyroid) into classes of high (H) and low (L) aggressiveness considering the TCGA data, and their correlations between Shannon entropy and 5-year overall survival (OS). Then, we used principal component analysis (PCA), a random forest classifier (RFC), and protein-protein interactions (PPI) to find the genes that correlated with aggressiveness. Using PCA, we found GRB2, CTNNB1, SKP1, CSNK2A1, PRKDC, HDAC1, YWHAZ, YWHAB, and PSMD2. Except for PSMD2, the RFC analysis showed a different list, which was CAD, PSMD14, APH1A, PSMD2, SHC1, TMEFF2, PSMD11, H2AFZ, PSMB5, and NOTCH1. Both methods use different algorithmic approaches and have different purposes, which explains the discrepancy between the two gene lists. The key genes of aggressiveness found by PCA were those that maximized the separation of H and L classes according to its third component, which represented 19% of the total variance. By contrast, RFC classified whether the RNA-seq of a tumor sample was of the H or L type. Interestingly, PPIs showed that the genes of PCA and RFC lists were connected neighbors in the PPI signaling network of WNT and cross-linked pathways.
Collapse
Affiliation(s)
- Adriano Barbosa-Silva
- Center for Medical Statistics, Informatics and Intelligent Systems, Institute for Artificial Intelligence, Medical University of Vienna, 1090 Vienna, Austria
- Centre for Translational Bioinformatics, William Harvey Research Institute, Queen Mary University of London, London E14NS, UK
- ITTM S.A.-Information Technology for Translational Medicine, Esch-sur-Alzette, 4354 Luxembourg, Luxembourg
| | - Milena Magalhães
- Plataforma de Modelagem de Sistemas Biológicos, Center for Technology Development in Health (CDTS), Oswaldo Cruz Foundation (FIOCRUZ), Rio de Janeiro 21040900, Brazil
| | - Gilberto Ferreira Da Silva
- Plataforma de Modelagem de Sistemas Biológicos, Center for Technology Development in Health (CDTS), Oswaldo Cruz Foundation (FIOCRUZ), Rio de Janeiro 21040900, Brazil
| | - Fabricio Alves Barbosa Da Silva
- Laboratório de Modelagem Computacional de Sistemas Biológicos, Scientific Computing Program, Oswaldo Cruz Foundation (FIOCRUZ), Rio de Janeiro 21040900, Brazil
| | - Flávia Raquel Gonçalves Carneiro
- Center for Technology Development in Health (CDTS), Oswaldo Cruz Foundation (FIOCRUZ), Rio de Janeiro 21040900, Brazil
- Laboratório Interdisciplinar de Pesquisas Médicas, Instituto Oswaldo Cruz, Oswaldo Cruz Foundation (FIOCRUZ), Rio de Janeiro 21040900, Brazil
- Program of Immunology and Tumor Biology, Brazilian National Cancer Institute (INCA), Rio de Janeiro 20231050, Brazil
| | - Nicolas Carels
- Plataforma de Modelagem de Sistemas Biológicos, Center for Technology Development in Health (CDTS), Oswaldo Cruz Foundation (FIOCRUZ), Rio de Janeiro 21040900, Brazil
| |
Collapse
|
29
|
Machine Learning-Based Pressure Ulcer Prediction in Modular Critical Care Data. Diagnostics (Basel) 2022; 12:diagnostics12040850. [PMID: 35453898 PMCID: PMC9030498 DOI: 10.3390/diagnostics12040850] [Citation(s) in RCA: 17] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2022] [Revised: 03/25/2022] [Accepted: 03/28/2022] [Indexed: 02/07/2023] Open
Abstract
Increasingly available open medical and health datasets encourage data-driven research with a promise of improving patient care through knowledge discovery and algorithm development. Among efficient approaches to such high-dimensional problems are a number of machine learning methods, which are applied in this paper to pressure ulcer prediction in modular critical care data. An inherent property of many health-related datasets is a high number of irregularly sampled time-variant and scarcely populated features, often exceeding the number of observations. Although machine learning methods are known to work well under such circumstances, many choices regarding model and data processing exist. In particular, this paper address both theoretical and practical aspects related to the application of six classification models to pressure ulcers, while utilizing one of the largest available Medical Information Mart for Intensive Care (MIMIC-IV) databases. Random forest, with an accuracy of 96%, is the best-performing approach among the considered machine learning algorithms.
Collapse
|
30
|
A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal Pain. Diagnostics (Basel) 2021; 12:diagnostics12010082. [PMID: 35054249 PMCID: PMC8775134 DOI: 10.3390/diagnostics12010082] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2021] [Revised: 12/28/2021] [Accepted: 12/29/2021] [Indexed: 12/12/2022] Open
Abstract
Seventy-two-hour unscheduled return visits (URVs) by emergency department patients are a key clinical index for evaluating the quality of care in emergency departments (EDs). This study aimed to develop a machine learning model to predict 72 h URVs for ED patients with abdominal pain. Electronic health records data were collected from the Chang Gung Research Database (CGRD) for 25,151 ED visits by patients with abdominal pain and a total of 617 features were used for analysis. We used supervised machine learning models, namely logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGB), and voting classifier (VC), to predict URVs. The VC model achieved more favorable overall performance than other models (AUROC: 0.74; 95% confidence interval (CI), 0.69–0.76; sensitivity, 0.39; specificity, 0.89; F1 score, 0.25). The reduced VC model achieved comparable performance (AUROC: 0.72; 95% CI, 0.69–0.74) to the full models using all clinical features. The VC model exhibited the most favorable performance in predicting 72 h URVs for patients with abdominal pain, both for all-features and reduced-features models. Application of the VC model in the clinical setting after validation may help physicians to make accurate decisions and decrease URVs.
Collapse
|