1
|
Rozo A, Miskovic V, Rose T, Keersebilck E, Iorio C, Varon C. A Deep Learning Image-to-Image Translation Approach for a More Accessible Estimator of the Healing Time of Burns. IEEE Trans Biomed Eng 2023; 70:2886-2894. [PMID: 37067977 DOI: 10.1109/tbme.2023.3267600] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/18/2023]
Abstract
OBJECTIVE An accurate and timely diagnosis of burn severity is critical to ensure a positive outcome. Laser Doppler imaging (LDI) has become a very useful tool for this task. It measures the perfusion of the burn and estimates its potential healing time. LDIs generate a 6-color palette image, with each color representing a healing time. This technique has very high costs associated. In resource-limited areas, such as low- and middle-income countries or remote locations like space, where access to specialized burn care is inadequate, more affordable and portable tools are required. This study proposes a novel image-to-image translation approach to estimate burn healing times, using a digital image to approximate the LDI. METHODS This approach consists of a U-net architecture with a VGG-based encoder and applies the concept of ordinal classification. Paired digital and LDI images of burns were collected. The performance was evaluated with 10-fold cross-validation, mean absolute error (MAE), and color distribution differences between the ground truth and the estimated LDI. RESULTS Results showed a satisfactory performance in terms of low MAE ( 0.2370 ±0.0086). However, the unbalanced distribution of colors in the data affects this performance. SIGNIFICANCE This novel and unique approach serves as a basis for developing more accessible support tools in the burn care environment in resource-limited areas.
Collapse
|
2
|
Yeh CC, Lin YS, Chen CC, Liu CF. Implementing AI Models for Prognostic Predictions in High-Risk Burn Patients. Diagnostics (Basel) 2023; 13:2984. [PMID: 37761351 PMCID: PMC10528558 DOI: 10.3390/diagnostics13182984] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2023] [Revised: 09/12/2023] [Accepted: 09/15/2023] [Indexed: 09/29/2023] Open
Abstract
BACKGROUND AND OBJECTIVES Burn injuries range from minor medical issues to severe, life-threatening conditions. The severity and location of the burn dictate its treatment; while minor burns might be treatable at home, severe burns necessitate medical intervention, sometimes in specialized burn centers with extended follow-up care. This study aims to leverage artificial intelligence (AI)/machine learning (ML) to forecast potential adverse effects in burn patients. METHODS This retrospective analysis considered burn patients admitted to Chi Mei Medical Center from 2010 to 2019. The study employed 14 features, comprising supplementary information like prior comorbidities and laboratory results, for building models for predicting graft surgery, a prolonged hospital stay, and overall adverse effects. Overall, 70% of the data set trained the AI models, with the remaining 30% reserved for testing. Three ML algorithms of random forest, LightGBM, and logistic regression were employed with evaluation metrics of accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC). RESULTS In this research, out of 224 patients assessed, the random forest model yielded the highest AUC for predictions related to prolonged hospital stays (>14 days) at 81.1%, followed by the XGBoost (79.9%) and LightGBM (79.5%) models. Besides, the random forest model of the need for a skin graft showed the highest AUC (78.8%), while the random forest model and XGBoost model of the occurrence of adverse complications both demonstrated the highest AUC (87.2%) as well. Based on the best models with the highest AUC values, an AI prediction system is designed and integrated into hospital information systems to assist physicians in the decision-making process. CONCLUSIONS AI techniques showcased exceptional capabilities for predicting a prolonged hospital stay, the need for a skin graft, and the occurrence of overall adverse complications for burn patients. The insights from our study fuel optimism for the inception of a novel predictive model that can seamlessly meld with hospital information systems, enhancing clinical decisions and bolstering physician-patient dialogues.
Collapse
Affiliation(s)
- Chin-Choon Yeh
- Department of Plastic Surgery, Chi Mei Medical Center, Tainan 711, Taiwan; (C.-C.Y.); (Y.-S.L.); (C.-C.C.)
| | - Yu-San Lin
- Department of Plastic Surgery, Chi Mei Medical Center, Tainan 711, Taiwan; (C.-C.Y.); (Y.-S.L.); (C.-C.C.)
| | - Chun-Chia Chen
- Department of Plastic Surgery, Chi Mei Medical Center, Tainan 711, Taiwan; (C.-C.Y.); (Y.-S.L.); (C.-C.C.)
| | - Chung-Feng Liu
- Department of Medical Research, Chi Mei Medical Center, Tainan 711, Taiwan
| |
Collapse
|
3
|
Chang CW, Ho CY, Lai F, Christian M, Huang SC, Chang DH, Chen YS. Application of multiple deep learning models for automatic burn wound assessment. Burns 2023; 49:1039-1051. [PMID: 35945064 DOI: 10.1016/j.burns.2022.07.006] [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: 02/16/2022] [Revised: 06/24/2022] [Accepted: 07/14/2022] [Indexed: 11/27/2022]
Abstract
PURPOSE Accurate assessment of the percentage of total body surface area (%TBSA) burned is crucial in managing burn injuries. It is difficult to estimate the size of an irregular shape by inspection. Many articles reported the discrepancy of estimating %TBSA burned by different doctors. We set up a system with multiple deep learning (DL) models for %TBSA estimation, as well as the segmentation of possibly poor-perfused deep burn regions from the entire wound. METHODS We proposed boundary-based labeling for datasets of total burn wound and palm, whereas region-based labeling for the dataset of deep burn wound. Several powerful DL models (U-Net, PSPNet, DeeplabV3+, Mask R-CNN) with encoders ResNet101 had been trained and tested from the above datasets. With the subject distances, the %TBSA burned could be calculated by the segmentation of total burn wound area with respect to the palm size. The percentage of deep burn area could be obtained from the segmentation of deep burn area from the entire wound. RESULTS A total of 4991 images of early burn wounds and 1050 images of palms were boundary-based labeled. 1565 out of 4994 images with deep burn were preprocessed with superpixel segmentation into small regions before labeling. DeeplabV3+ had slightly better performance in three tasks with precision: 0.90767, recall: 0.90065 for total burn wound segmentation; precision: 0.98987, recall: 0.99036 for palm segmentation; and precision: 0.90152, recall: 0.90219 for deep burn segmentation. CONCLUSION Combining the segmentation results and clinical data, %TBSA burned, the volume of fluid for resuscitation, and the percentage of deep burn area can be automatically diagnosed by DL models with a pixel-to-pixel method. Artificial intelligence provides consistent, accurate and rapid assessments of burn wounds.
Collapse
Affiliation(s)
- Che Wei Chang
- Graduate Institute of Biomedical Electronics & Bioinformatics, National Taiwan University, Taipei, Taiwan; Division of Plastic and Reconstructive Surgery, Department of Surgery, Far Eastern Memorial Hospital, New Taipei, Taiwan.
| | - Chun Yee Ho
- Division of Plastic and Reconstructive Surgery, Department of Surgery, Far Eastern Memorial Hospital, New Taipei, Taiwan
| | - Feipei Lai
- Graduate Institute of Biomedical Electronics & Bioinformatics, National Taiwan University, Taipei, Taiwan; Department of Computer Science & Information Engineering, National Taiwan University, Taipei, Taiwan
| | - Mesakh Christian
- Department of Computer Science & Information Engineering, National Taiwan University, Taipei, Taiwan
| | - Shih Chen Huang
- Division of Plastic and Reconstructive Surgery, Department of Surgery, Far Eastern Memorial Hospital, New Taipei, Taiwan
| | - Dun Hao Chang
- Division of Plastic and Reconstructive Surgery, Department of Surgery, Far Eastern Memorial Hospital, New Taipei, Taiwan; Department of Information Management, Yuan Ze University, Taiwan
| | - Yo Shen Chen
- Division of Plastic and Reconstructive Surgery, Department of Surgery, Far Eastern Memorial Hospital, New Taipei, Taiwan
| |
Collapse
|
4
|
Taib BG, Karwath A, Wensley K, Minku L, Gkoutos GV, Moiemen N. Artificial intelligence in the management and treatment of burns: A systematic review and meta-analyses. J Plast Reconstr Aesthet Surg 2023; 77:133-161. [PMID: 36571960 DOI: 10.1016/j.bjps.2022.11.049] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2021] [Revised: 10/17/2022] [Accepted: 11/17/2022] [Indexed: 11/24/2022]
Abstract
INTRODUCTION AND AIM Artificial Intelligence (AI) is already being successfully employed to aid the interpretation of multiple facets of burns care. In the light of the growing influence of AI, this systematic review and diagnostic test accuracy meta-analyses aim to appraise and summarise the current direction of research in this field. METHOD A systematic literature review was conducted of relevant studies published between 1990 and 2021, yielding 35 studies. Twelve studies were suitable for a Diagnostic Test Meta-Analyses. RESULTS The studies generally focussed on burn depth (Accuracy 68.9%-95.4%, Sensitivity 90.8% and Specificity 84.4%), burn segmentation (Accuracy 76.0%-99.4%, Sensitivity 97.9% and specificity 97.6%) and burn related mortality (Accuracy >90%-97.5% Sensitivity 92.9% and specificity 93.4%). Neural networks were the most common machine learning (ML) algorithm utilised in 69% of the studies. The QUADAS-2 tool identified significant heterogeneity between studies. DISCUSSION The potential application of AI in the management of burns patients is promising, especially given its propitious results across a spectrum of dimensions, including burn depth, size, mortality, related sepsis and acute kidney injuries. The accuracy of the results analysed within this study is comparable to current practices in burns care. CONCLUSION The application of AI in the treatment and management of burns patients, as a series of point of care diagnostic adjuncts, is promising. Whilst AI is a potentially valuable tool, a full evaluation of its current utility and potential is limited by significant variations in research methodology and reporting.
Collapse
Affiliation(s)
- Bilal Gani Taib
- Burns and Plastic Surgery Department, Queen Elizabeth Hospital, Mindelsohn Way, Birmingham B15 2TH, United Kingdom.
| | - A Karwath
- Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, United Kingdom; Health Data Research UK Midlands Site, Birmingham, United Kingdom; University Hospitals Birmingham NHS Foundation Trust, Edgbaston, Birmingham, United Kingdom
| | - K Wensley
- Burns and Plastic Surgery Department, Queen Elizabeth Hospital, Mindelsohn Way, Birmingham B15 2TH, United Kingdom
| | - L Minku
- School of Computer Science, University of Birmingham, Birmingham, United Kingdom
| | - G V Gkoutos
- Institute of Cancer and Genomic Sciences, University of Birmingham, Birmingham, United Kingdom; Health Data Research UK Midlands Site, Birmingham, United Kingdom; University Hospitals Birmingham NHS Foundation Trust, Edgbaston, Birmingham, United Kingdom; NIHR Surgical Reconstruction and Microbiology Research Centre, Birmingham, United Kingdom
| | - N Moiemen
- College of Medical and Dental Sciences, University of Birmingham, United Kingdom; Centre for Conflict Wound Research, Scar Free Foundation, Birmingham, United Kingdom; NIHR Surgical Reconstruction and Microbiology Research Centre, Birmingham, United Kingdom
| |
Collapse
|
5
|
Li Y, Pang AW, Zeitouni J, Zeitouni F, Mateja K, Griswold JA, Chong JW. Inhalation Injury Grading Using Transfer Learning Based on Bronchoscopy Images and Mechanical Ventilation Period. SENSORS (BASEL, SWITZERLAND) 2022; 22:9430. [PMID: 36502127 PMCID: PMC9740957 DOI: 10.3390/s22239430] [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: 10/30/2022] [Revised: 11/23/2022] [Accepted: 11/29/2022] [Indexed: 06/17/2023]
Abstract
The abbreviated injury score (AIS) is commonly used as a grading system for inhalation injuries. While inhalation injury grades have inconsistently been shown to correlate positively with the time mechanical ventilation is needed, grading is subjective and relies heavily on the clinicians' experience and expertise. Additionally, no correlation has been shown between these patients' inhalation injury grades and outcomes. In this paper, we propose a novel inhalation injury grading method which uses deep learning algorithms in bronchoscopy images to determine the injury grade from the carbonaceous deposits, blistering, and fibrin casts in the bronchoscopy images. The proposed method adopts transfer learning and data augmentation concepts to enhance the accuracy performance to avoid overfitting. We tested our proposed model on the bronchoscopy images acquired from eighteen patients who had suffered inhalation injuries, with the degree of severity 1, 2, 3, 4, 5, or 6. As performance metrics, we consider accuracy, sensitivity, specificity, F-1 score, and precision. Experimental results show that our proposed method, with both transfer learning and data augmentation components, provides an overall 86.11% accuracy. Moreover, the experimental results also show that the performance of the proposed method outperforms the method without transfer learning or data augmentation.
Collapse
Affiliation(s)
- Yifan Li
- Department of Electrical and Computer Engineering, Texas Tech University, Lubbock, TX 79409, USA
| | - Alan W. Pang
- Department of Surgery, Texas Tech University Health Sciences Center, Lubbock, TX 79430, USA
| | - Jad Zeitouni
- School of Medicine, Texas Tech University Health Sciences Center, Lubbock, TX 79430, USA
| | - Ferris Zeitouni
- School of Medicine, Texas Tech University Health Sciences Center, Lubbock, TX 79430, USA
| | - Kirby Mateja
- School of Medicine, Texas Tech University Health Sciences Center, Lubbock, TX 79430, USA
| | - John A. Griswold
- Department of Surgery, Texas Tech University Health Sciences Center, Lubbock, TX 79430, USA
| | - Jo Woon Chong
- Department of Electrical and Computer Engineering, Texas Tech University, Lubbock, TX 79409, USA
| |
Collapse
|
6
|
Martinez-Millana A, Saez-Saez A, Tornero-Costa R, Azzopardi-Muscat N, Traver V, Novillo-Ortiz D. Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews. Int J Med Inform 2022; 166:104855. [PMID: 35998421 PMCID: PMC9551134 DOI: 10.1016/j.ijmedinf.2022.104855] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2022] [Revised: 08/01/2022] [Accepted: 08/11/2022] [Indexed: 12/04/2022]
Abstract
BACKGROUND Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people's health. It is necessary to assess the current status on the application of AI towards the improvement of people's health in the domains defined by WHO's Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges. OBJECTIVE To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people's health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality. METHODS A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO's PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist. RESULTS The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews. CONCLUSION Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.
Collapse
Affiliation(s)
- Antonio Martinez-Millana
- Instituto Universitario de Investigación de Aplicaciones de las Tecnologías de la Información y de las Comunicaciones Avanzadas (ITACA), Universitat Politècnica de València, Camino de Vera S/N, Valencia 46022, Spain
| | - Aida Saez-Saez
- Instituto Universitario de Investigación de Aplicaciones de las Tecnologías de la Información y de las Comunicaciones Avanzadas (ITACA), Universitat Politècnica de València, Camino de Vera S/N, Valencia 46022, Spain
| | - Roberto Tornero-Costa
- Instituto Universitario de Investigación de Aplicaciones de las Tecnologías de la Información y de las Comunicaciones Avanzadas (ITACA), Universitat Politècnica de València, Camino de Vera S/N, Valencia 46022, Spain
| | - Natasha Azzopardi-Muscat
- Division of Country Health Policies and Systems, World Health Organization, Regional Office for Europe, Copenhagen, Denmark
| | - Vicente Traver
- Instituto Universitario de Investigación de Aplicaciones de las Tecnologías de la Información y de las Comunicaciones Avanzadas (ITACA), Universitat Politècnica de València, Camino de Vera S/N, Valencia 46022, Spain
| | - David Novillo-Ortiz
- Division of Country Health Policies and Systems, World Health Organization, Regional Office for Europe, Copenhagen, Denmark.
| |
Collapse
|
7
|
Park JH, Cho Y, Shin D, Choi SS. Prediction of Mortality after Burn Surgery in Critically Ill Burn Patients Using Machine Learning Models. J Pers Med 2022; 12:jpm12081293. [PMID: 36013242 PMCID: PMC9410169 DOI: 10.3390/jpm12081293] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2022] [Revised: 07/30/2022] [Accepted: 08/04/2022] [Indexed: 11/16/2022] Open
Abstract
Severe burns may lead to a series of pathophysiological processes that result in death. Machine learning models that demonstrate prognostic performance can be used to build analytical models to predict postoperative mortality. This study aimed to identify machine learning models with the best diagnostic performance for predicting mortality in critically ill burn patients after burn surgery, and then compare them. Clinically important features for predicting mortality in patients after burn surgery were selected using a random forest (RF) regressor. The area under the receiver operating characteristic curve (AUC) and classifier accuracy were evaluated to compare the predictive accuracy of different machine learning algorithms, including RF, adaptive boosting, decision tree, linear support vector machine, and logistic regression. A total of 731 patients met the inclusion and exclusion criteria. The 90-day mortality of the critically ill burn patients after burn surgery was 27.1% (198/731). RF showed the highest AUC (0.922, 95% confidence interval = 0.902–0.942) among the models, with sensitivity and specificity of 66.2% and 93.8%, respectively. The most significant predictors for mortality after burn surgery as per machine learning models were total body surface area burned, red cell distribution width, and age. The RF algorithm showed the best performance for predicting mortality.
Collapse
Affiliation(s)
- Ji Hyun Park
- Department of Anesthesiology and Pain Medicine, National Medical Center, Seoul 04564, Korea
| | - Yongwon Cho
- Department of Radiology, Korea University Anam Hospital, University of Korea College of Medicine, Seoul 02841, Korea
| | - Donghyeok Shin
- Department of Anesthesiology and Pain Medicine, National Medical Center, Seoul 04564, Korea
| | - Seong-Soo Choi
- Department of Anesthesiology and Pain Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul 05505, Korea
- Correspondence:
| |
Collapse
|
8
|
Trentino KM, Schwarzbauer K, Mitterecker A, Hofmann A, Lloyd A, Leahy MF, Tschoellitsch T, Böck C, Hochreiter S, Meier J. Machine Learning-Based Mortality Prediction of Patients at Risk During Hospital Admission. J Patient Saf 2022; 18:494-498. [PMID: 35026794 DOI: 10.1097/pts.0000000000000957] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
OBJECTIVES The ability to predict in-hospital mortality from data available at hospital admission would identify patients at risk and thereby assist hospital-wide patient safety initiatives. Our aim was to use modern machine learning tools to predict in-hospital mortality from standardized data sets available at hospital admission. METHODS This was a retrospective, observational study in 3 adult tertiary care hospitals in Western Australia between January 2008 and June 2017. Primary outcome measures were the area under the curve for the receiver operating characteristics curve, the F1 score, and the average precision of the 4 machine learning algorithms used: logistic regression, neural networks, random forests, and gradient boosting trees. RESULTS Using our 4 predictive models, in-hospital mortality could be predicted satisfactorily (areas under the curve for neural networks, logistic regression, random forests, and gradient boosting trees: 0.932, 0.936, 0.935, and 0.935, respectively), with moderate F1 scores: 0.378, 0.367, 0.380, and 0.380, respectively. Average precision values were 0.312, 0.321, 0.334, and 0.323, respectively. It remains unknown whether additional features might improve our models; however, this would result in additional efforts for data acquisition in daily clinical practice. CONCLUSIONS This study demonstrates that using only a limited, standardized data set in-hospital mortality can be predicted satisfactorily at the time point of hospital admission. More parameters describing patient's health are likely needed to improve our model.
Collapse
Affiliation(s)
- Kevin M Trentino
- From the Data and Digital Innovation, East Metropolitan Health Service and Medical School, The University of Western Australia, Perth, Australia
| | - Karin Schwarzbauer
- Institute for Machine Learning, Johannes Kepler University, Linz, Austria
| | | | | | - Adam Lloyd
- Data and Digital Innovation, East Metropolitan Health Service
| | | | - Thomas Tschoellitsch
- Kepler University Hospital, Department of Anesthesiology and Intensive Care Medicine and Johannes Kepler University
| | - Carl Böck
- Kepler University Hospital, Department of Anesthesiology and Intensive Care Medicine and Johannes Kepler University
| | | | - Jens Meier
- Clinic of Anesthesiology and Critical Care Medicine, Kepler University Clinic, Kepler University, Linz, Austria
| |
Collapse
|
9
|
Fransén J, Lundin J, Fredén F, Huss F. A proof-of-concept study on mortality prediction with machine learning algorithms using burn intensive care data. Scars Burn Heal 2022; 8:20595131211066585. [PMID: 35198237 PMCID: PMC8859689 DOI: 10.1177/20595131211066585] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022] Open
Abstract
INTRODUCTION Burn injuries are a common traumatic injury. Large burns have high mortality requiring intensive care and accurate mortality predictions. To assess if machine learning (ML) could improve predictions, ML algorithms were tested and compared with the original and revised Baux score. METHODS Admission data and mortality outcomes were collected from patients at Uppsala University Hospital Burn Centre from 2002 to 2019. Prognostic variables were selected, ML algorithms trained and predictions assessed by analysis of the area under the receiver operating characteristic curve (AUC). Comparison was made with Baux scores using DeLong test. RESULTS A total of 17 prognostic variables were selected from 92 patients. AUCs in leave-one-out cross-validation for a decision tree model, an extreme boosting model, a random forest model, a support-vector machine (SVM) model and a generalised linear regression model (GLM) were 0.83 (95% confidence interval [CI] = 0.72-0.94), 0.92 (95% CI = 0.84-1), 0.92 (95% CI = 0.84-1), 0.92 (95% CI = 0.84-1) and 0.84 (95% CI = 0.74-0.94), respectively. AUCs for the Baux score and revised Baux score were 0.85 (95% CI = 0.75-0.95) and 0.84 (95% CI = 0.74-0.94). No significant differences were observed when comparing ML algorithms with Baux score and revised Baux score. Secondary variable selection was made to analyse model performance. CONCLUSION This proof-of-concept study showed initial credibility in using ML algorithms to predict mortality in burn patients. The sample size was small and future studies are needed with larger sample sizes, further variable selections and prospective testing of the algorithms. LAY SUMMARY Burn injuries are one of the most common traumatic injuries especially in countries with limited prevention and healthcare resources. To treat a patient with large burns who has been admitted to an intensive care unit, it is often necessary to assess the risk of a fatal outcome. Physicians traditionally use simplified scores to calculate risks. One commonly used score, the Baux score, uses age of the patient and the size of the burn to predict the risk of death. Adding the factor of inhalation injury, the score is then called the revised Baux score. However, there are a number of additional causes that can influence the risk of fatal outcomes that Baux scores do not take into account. Machine learning is a method of data modelling where the system learns to predict outcomes based on previous cases and is a branch of artificial intelligence. In this study we evaluated several machine learning methods for outcome prediction in patients admitted for burn injury. We gathered data on 93 patients at admission to the intensive care unit and our experiments show that machine learning methods can reach an accuracy comparable with Baux scores in calculating the risk of fatal outcomes. This study represents a proof of principle and future studies on larger patient series are required to verify our results as well as to evaluate the methods on patients in real-life situations.
Collapse
Affiliation(s)
- Jian Fransén
- Department of Surgical Sciences, Plastic Surgery, Uppsala University, Uppsala, Sweden
- Jian Fransén, Department of Surgical Sciences, Plastic Surgery, Uppsala University, Akademiska sjukhuset, S-751 85, Uppsala, Sweden.
| | - Johan Lundin
- Karolinska Institute Department of Global Public Health, Stockholm, Sweden
- FIMM, Institute for Molecular Medicine, Helsinki, Finland
| | - Filip Fredén
- Department of Anaesthesia and Intensive Care, Uppsala University Hospital, Uppsala, Sweden
| | - Fredrik Huss
- Department of Plastic- and Maxillofacial Surgery, Uppsala University Hospital, Uppsala, Sweden
| |
Collapse
|
10
|
Chang CW, Lai F, Christian M, Chen YC, Hsu C, Chen YS, Chang DH, Roan TL, Yu YC. Deep Learning-Assisted Burn Wound Diagnosis: Diagnostic Model Development Study. JMIR Med Inform 2021; 9:e22798. [PMID: 34860674 PMCID: PMC8686480 DOI: 10.2196/22798] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2020] [Revised: 12/19/2020] [Accepted: 10/15/2021] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND Accurate assessment of the percentage total body surface area (%TBSA) of burn wounds is crucial in the management of burn patients. The resuscitation fluid and nutritional needs of burn patients, their need for intensive unit care, and probability of mortality are all directly related to %TBSA. It is difficult to estimate a burn area of irregular shape by inspection. Many articles have reported discrepancies in estimating %TBSA by different doctors. OBJECTIVE We propose a method, based on deep learning, for burn wound detection, segmentation, and calculation of %TBSA on a pixel-to-pixel basis. METHODS A 2-step procedure was used to convert burn wound diagnosis into %TBSA. In the first step, images of burn wounds were collected from medical records and labeled by burn surgeons, and the data set was then input into 2 deep learning architectures, U-Net and Mask R-CNN, each configured with 2 different backbones, to segment the burn wounds. In the second step, we collected and labeled images of hands to create another data set, which was also input into U-Net and Mask R-CNN to segment the hands. The %TBSA of burn wounds was then calculated by comparing the pixels of mask areas on images of the burn wound and hand of the same patient according to the rule of hand, which states that one's hand accounts for 0.8% of TBSA. RESULTS A total of 2591 images of burn wounds were collected and labeled to form the burn wound data set. The data set was randomly split into training, validation, and testing sets in a ratio of 8:1:1. Four hundred images of volar hands were collected and labeled to form the hand data set, which was also split into 3 sets using the same method. For the images of burn wounds, Mask R-CNN with ResNet101 had the best segmentation result with a Dice coefficient (DC) of 0.9496, while U-Net with ResNet101 had a DC of 0.8545. For the hand images, U-Net and Mask R-CNN had similar performance with DC values of 0.9920 and 0.9910, respectively. Lastly, we conducted a test diagnosis in a burn patient. Mask R-CNN with ResNet101 had on average less deviation (0.115% TBSA) from the ground truth than burn surgeons. CONCLUSIONS This is one of the first studies to diagnose all depths of burn wounds and convert the segmentation results into %TBSA using different deep learning models. We aimed to assist medical staff in estimating burn size more accurately, thereby helping to provide precise care to burn victims.
Collapse
Affiliation(s)
- Che Wei Chang
- Graduate Institute of Biomedical Electronics & Bioinformatics, National Taiwan University, Taipei, Taiwan.,Division of Plastic and Reconstructive Surgery, Department of Surgery, Far Eastern Memorial Hospital, New Taipei, Taiwan
| | - Feipei Lai
- Graduate Institute of Biomedical Electronics & Bioinformatics, National Taiwan University, Taipei, Taiwan
| | - Mesakh Christian
- Department of Computer Science & Information Engineering, National Taiwan University, Taipei, Taiwan
| | - Yu Chun Chen
- Department of Computer Science & Information Engineering, National Taiwan University, Taipei, Taiwan
| | - Ching Hsu
- Graduate Institute of Biomedical Electronics & Bioinformatics, National Taiwan University, Taipei, Taiwan
| | - Yo Shen Chen
- Division of Plastic and Reconstructive Surgery, Department of Surgery, Far Eastern Memorial Hospital, New Taipei, Taiwan
| | - Dun Hao Chang
- Division of Plastic and Reconstructive Surgery, Department of Surgery, Far Eastern Memorial Hospital, New Taipei, Taiwan.,Department of Information Management, Yuan Ze University, Chung-Li, Taiwan
| | - Tyng Luen Roan
- Division of Plastic and Reconstructive Surgery, Department of Surgery, Far Eastern Memorial Hospital, New Taipei, Taiwan
| | - Yen Che Yu
- Division of Plastic and Reconstructive Surgery, Department of Surgery, Far Eastern Memorial Hospital, New Taipei, Taiwan
| |
Collapse
|
11
|
Abstract
INTRODUCTION Burn-related injuries are a leading cause of morbidity across the globe. Accurate assessment and treatment have been demonstrated to reduce the morbidity and mortality. This essay explores the forms of artificial intelligence to be implemented the field of burns management to optimise the care we deliver in the National Health Service (NHS) in the UK. METHODS Machine Learning methods which predict or classify are explored. This includes linear and logistic regression, artificial neural networks, deep learning, and decision tree analysis. DISCUSSION Utilizing Machine Learning in burns care holds potential from prevention, burns assessment, predicting mortality and critical care monitoring to healing time. Establishing a regional or national Machine Learning group would be the first step towards the development of these essential technologies. CONCLUSION The implementation of machine learning technologies will require buy-in from the NHS health boards, with significant implications with cost of investment, implementation, employment of machine learning teams and provision of training to medical professionals.
Collapse
Affiliation(s)
- Lydia Robb
- Core Surgical Trainee, East of Scotland Deanery, Plastic Surgery Department, NHS Lothian, St John's Hospital at Howden, Livingston
| |
Collapse
|
12
|
E Moura FS, Amin K, Ekwobi C. Artificial intelligence in the management and treatment of burns: a systematic review. BURNS & TRAUMA 2021; 9:tkab022. [PMID: 34423054 PMCID: PMC8375569 DOI: 10.1093/burnst/tkab022] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/25/2020] [Revised: 03/08/2021] [Accepted: 04/30/2021] [Indexed: 06/13/2023]
Abstract
BACKGROUND Artificial intelligence (AI) is an innovative field with potential for improving burn care. This article provides an updated review on machine learning in burn care and discusses future challenges and the role of healthcare professionals in the successful implementation of AI technologies. METHODS A systematic search was carried out on MEDLINE, Embase and PubMed databases for English-language articles studying machine learning in burns. Articles were reviewed quantitatively and qualitatively for clinical applications, key features, algorithms, outcomes and validation methods. RESULTS A total of 46 observational studies were included for review. Assessment of burn depth (n = 26), support vector machines (n = 19) and 10-fold cross-validation (n = 11) were the most common application, algorithm and validation tool used, respectively. CONCLUSION AI should be incorporated into clinical practice as an adjunct to the experienced burns provider once direct comparative analysis to current gold standards outlining its benefits and risks have been studied. Future considerations must include the development of a burn-specific common framework. Authors should use common validation tools to allow for effective comparisons. Level I/II evidence is required to produce robust proof about clinical and economic impacts.
Collapse
Affiliation(s)
| | - Kavit Amin
- Department of Plastic Surgery, Manchester University NHS Foundation Trust, UK
- Department of Plastic Surgery, Lancashire Teaching Hospitals NHS Foundation Trust, Royal Preston Hospital, Preston, UK
| | - Chidi Ekwobi
- Department of Plastic Surgery, Lancashire Teaching Hospitals NHS Foundation Trust, Royal Preston Hospital, Preston, UK
| |
Collapse
|
13
|
A systematic review of machine learning and automation in burn wound evaluation: A promising but developing frontier. Burns 2021; 47:1691-1704. [PMID: 34419331 DOI: 10.1016/j.burns.2021.07.007] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2021] [Accepted: 07/09/2021] [Indexed: 12/21/2022]
Abstract
BACKGROUND Visual evaluation is the most common method of evaluating burn wounds. Its subjective nature can lead to inaccurate diagnoses and inappropriate burn center referrals. Machine learning may provide an objective solution. The objective of this study is to summarize the literature on ML in burn wound evaluation. METHODS A systematic review of articles published between January 2000 and January 2021 was performed using PubMed and MEDLINE (OVID). Articles reporting on ML or automation to evaluate burn wounds were included. Keywords included burns, machine/deep learning, artificial intelligence, burn classification technology, and mobile applications. Data were extracted on study design, method of data acquisition, machine learning techniques, and machine learning accuracy. RESULTS Thirty articles were included. Nine studies used machine learning and automation to estimate percent total body surface area (%TBSA) burned, 4 calculated fluid estimations, 19 estimated burn depth, 5 estimated need for surgery, and 2 evaluated scarring. Models calculating %TBSA burned demonstrated accuracies comparable to or better than paper methods. Burn depth classification models achieved accuracies of >83%. CONCLUSION Machine learning provides an objective adjunct that may improve diagnostic accuracy in evaluating burn wound severity. Existing models remain in the early stages with future studies needed to assess their clinical feasibility.
Collapse
|
14
|
Mantelakis A, Assael Y, Sorooshian P, Khajuria A. Machine Learning Demonstrates High Accuracy for Disease Diagnosis and Prognosis in Plastic Surgery. PLASTIC AND RECONSTRUCTIVE SURGERY-GLOBAL OPEN 2021; 9:e3638. [PMID: 34235035 PMCID: PMC8225366 DOI: 10.1097/gox.0000000000003638] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2020] [Accepted: 04/14/2021] [Indexed: 01/25/2023]
Abstract
INTRODUCTION Machine learning (ML) is a set of models and methods that can detect patterns in vast amounts of data and use this information to perform various kinds of decision-making under uncertain conditions. This review explores the current role of this technology in plastic surgery by outlining the applications in clinical practice, diagnostic and prognostic accuracies, and proposed future direction for clinical applications and research. METHODS EMBASE, MEDLINE, CENTRAL and ClinicalTrials.gov were searched from 1990 to 2020. Any clinical studies (including case reports) which present the diagnostic and prognostic accuracies of machine learning models in the clinical setting of plastic surgery were included. Data collected were clinical indication, model utilised, reported accuracies, and comparison with clinical evaluation. RESULTS The database identified 1181 articles, of which 51 articles were included in this review. The clinical utility of these algorithms was to assist clinicians in diagnosis prediction (n=22), outcome prediction (n=21) and pre-operative planning (n=8). The mean accuracy is 88.80%, 86.11% and 80.28% respectively. The most commonly used models were neural networks (n=31), support vector machines (n=13), decision trees/random forests (n=10) and logistic regression (n=9). CONCLUSIONS ML has demonstrated high accuracies in diagnosis and prognostication of burn patients, congenital or acquired facial deformities, and in cosmetic surgery. There are no studies comparing ML to clinician's performance. Future research can be enhanced using larger datasets or utilising data augmentation, employing novel deep learning models, and applying these to other subspecialties of plastic surgery.
Collapse
Affiliation(s)
| | | | | | - Ankur Khajuria
- Kellogg College, University of Oxford
- Department of Surgery and Cancer, Imperial College London, UK
| |
Collapse
|
15
|
Hadjiandreou M, Martin N. Towards artificial intelligence for identifying cases of suspected maltreatment in paediatric burns. Burns 2021; 47:1459-1460. [PMID: 34116871 DOI: 10.1016/j.burns.2021.05.007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2021] [Accepted: 05/07/2021] [Indexed: 11/30/2022]
Affiliation(s)
- Michalis Hadjiandreou
- St. Andrews Centre for Plastic Surgery & Burns, Broomfield University Hospital, Court Road, Chelmsford, Essex CM1 7ET, UK.
| | - Niall Martin
- St. Andrews Centre for Plastic Surgery & Burns, Broomfield University Hospital, Court Road, Chelmsford, Essex CM1 7ET, UK; Centre for Trauma Sciences, Blizard Institute, Queen Mary University of London, London E1 2AT, UK
| |
Collapse
|
16
|
A systematic review of machine learning in logistics and supply chain management: current trends and future directions. BENCHMARKING-AN INTERNATIONAL JOURNAL 2021. [DOI: 10.1108/bij-10-2020-0514] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
PurposeThis paper presents a review of the existing state-of-the-art literature on machine learning (ML) in logistics and supply chain management (LSCM) by analyzing the current literature, contemporary concepts, data and gaps and suggesting potential topics for future research.Design/methodology/approachA systematic/structured literature review in the subject discipline and a bibliometric analysis were organized. Information regarding industry involvement, geographic location, research design and methods, data analysis techniques, university, affiliation, publishers, authors, year of publications is documented. A wide collection of eight databases from 1994 to 2019 were explored using the keywords “Machine Learning” and “Logistics“, “Transportation” and “Supply Chain” in the title and/or abstract. A total of 110 articles were found, and information on a chain of variables was gathered.FindingsOver the last few decades, the application of emerging technologies has attracted significant interest all around the world. Analysis of the collected data shows that only nine literature reviews have been published in this area. Further, key findings show that 53.8 per cent of publications were closely clustered on transportation and manufacturing industries and 54.7 per cent were centred on mathematical models and simulations. Neural network is applied in 22 papers as their exclusive algorithms. Finally, the main focuses of the current literature are on prediction and optimization, where detection is contributed by only seven articles.Research limitations/implicationsThis review is limited to examining only academic sources available from Scopus, Elsevier, Web of Science, Emerald, JSTOR, SAGE, Springer, Taylor and Francis and Wiley which contain the words “Machine Learning” and “Logistics“, “Transportation” and “Supply Chain” in the title and/or abstract.Originality/valueThis paper provides a systematic insight into research trends in ML in both logistics and the supply chain.
Collapse
|
17
|
Andersen NK, Trøjgaard P, Herschend NO, Størling ZM. Automated Assessment of Peristomal Skin Discoloration and Leakage Area Using Artificial Intelligence. Front Artif Intell 2021; 3:72. [PMID: 33733189 PMCID: PMC7861335 DOI: 10.3389/frai.2020.00072] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2020] [Accepted: 08/05/2020] [Indexed: 01/22/2023] Open
Abstract
For people living with an ostomy, development of peristomal skin complications (PSCs) is the most common post-operative challenge. A visual sign of PSCs is discoloration (redness) of the peristomal skin often resulting from leakage of ostomy output under the baseplate. If left unattended, a mild skin condition may progress into a severe disorder; consequently, it is important to monitor discoloration and leakage patterns closely. The Ostomy Skin Tool is current state-of-the-art for evaluation of peristomal skin, but it relies on patients visiting their healthcare professional regularly. To enable close monitoring of peristomal skin over time, an automated strategy not relying on scheduled consultations is required. Several medical fields have implemented automated image analysis based on artificial intelligence, and these deep learning algorithms have become increasingly recognized as a valuable tool in healthcare. Therefore, the main objective of this study was to develop deep learning algorithms which could provide automated, consistent, and objective assessments of changes in peristomal skin discoloration and leakage patterns. A total of 614 peristomal skin images were used for development of the discoloration model, which predicted the area of the discolored peristomal skin with an accuracy of 95% alongside precision and recall scores of 79.6 and 75.0%, respectively. The algorithm predicting leakage patterns was developed based on 954 product images, and leakage area was determined with 98.8% accuracy, 75.0% precision, and 71.5% recall. Combined, these data for the first time demonstrate implementation of artificial intelligence for automated assessment of changes in peristomal skin discoloration and leakage patterns.
Collapse
|
18
|
Stewart BT, Carrougher GJ, Curtis E, Schneider JC, Ryan CM, Amtmann D, Gibran NS. Mortality prognostication scores do not predict long-term, health-related quality of life after burn: A burn model system national database study. Burns 2020; 47:42-51. [PMID: 33092898 PMCID: PMC7533049 DOI: 10.1016/j.burns.2020.09.007] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2020] [Revised: 08/20/2020] [Accepted: 09/23/2020] [Indexed: 11/28/2022]
Abstract
OBJECTIVE Despite improved mortality rates after burn injury, many patients face significant long-term physical and psychosocial disabilities. We aimed to determine whether commonly used mortality prognostication scores predict long-term, health-related quality of life after burn injury. By doing so, we might add evidence to support goals of care discussions and facilitate shared decision-making efforts in the hours and days after a life-changing injury. METHODS We used the multicenter National Institute of Disability, Independent Living and Rehabilitation Research Burn Model System database (1994-2019) to analyze SF-12 physical (PCS) and mental component (MCS) scores among survivors one year after major burn injury. Ninety percent of the observations were randomly assigned to a model development dataset. Multilevel, mixed-effects, linear regression models determined the relationship between revised Baux and Ryan Scores and SF-12 measures. Additionally, we tested a model with disaggregated independent and other covariates easily obtained around the time of index admission: age, sex, race, burn size, inhalation injury. Residuals from the remaining 10% of observations in the validation dataset were examined. RESULTS The analysis included 1606 respondents (median age 42 years, IQR 28-53 years; 70% male). Median burn size was 16% TBSA (IQR 6-30) and 13% of respondents sustained inhalation injury. Higher revised Baux and Ryan Scores and age, burn size, and inhalation injury were significantly correlated with lower PCS, but were not correlated with MCS. Female sex, black race, burn size, and inhalation injury correlated with lower MCS. All models poorly explained the variance in SF-12 scores (adjusted r2 0.01-0.12). CONCLUSION Higher revised Baux and Ryan Scores negatively correlated with long-term physical health, but not mental health, after burn injury. Regardless, the models poorly explained the variance in SF-12 scores one year after injury. More accurate models are needed to predict long-term, health-related quality of life and support shared decision-making during acute burn care.
Collapse
Affiliation(s)
- Barclay T Stewart
- Department of Surgery, University of Washington, Northwest Regional Burn Model System; Northwest Regional Burn Model System.
| | | | - Elleanor Curtis
- Department of Surgery, University of California Davis Health, Department of Palliative Care, University of California Davis Health
| | - Jeffrey C Schneider
- Department of Physical Medicine and Rehabilitation, Harvard Medical School, Boston-Harvard Burn Injury Model System
| | - Colleen M Ryan
- Department of Surgery, Harvard Medical School, Boston-Harvard Burn Injury Model System
| | - Dagmar Amtmann
- Department of Rehabilitation Medicine, University of Washington, Burn Model System
| | - Nicole S Gibran
- Department of Surgery, University of Washington, Northwest Regional Burn Model System; Northwest Regional Burn Model System
| |
Collapse
|
19
|
Convolution neural network for effective burn region segmentation of color images. Burns 2020; 47:854-862. [PMID: 33158632 DOI: 10.1016/j.burns.2020.08.016] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2020] [Revised: 07/29/2020] [Accepted: 08/31/2020] [Indexed: 12/22/2022]
Abstract
BACKGROUND Burn injuries are one of the most severe forms of wounds and trauma across the globe. Automated burn diagnosis methods are needed to provide timely treatment to the concerned patients. Artificial intelligence is playing a vital role in developing automated tools and techniques for medical problems. However, the use of advanced AI techniques for color images based burn region segmentation is not much explored. METHOD In this work, we explore the use of deep learning for the challenging problem of burn region segmentation. We prepared a pixel-wise labelled new burn images dataset for segmentation and investigated the efficacy of existing state-of-the-art color images based semantic image segmentation techniques. Lately, we proposed a new convolution neural network (CNN) that uses atrous convolution for encoding rich contextual information and utilizes pre-trained model ResNet-101 for better extraction of low-level and middle-level layer features. RESULTS The proposed approach achieves the state-of-the-art performance on the prepared burn image dataset with 77.6% of Mathews correlation coefficient (MCC) and 93.4% of accuracy. The improvement of 11.6/5.8/6.9/1.2% is observed in precision, Dice similarity coefficient, Jaccard index and specificity, in comparison to the second best performance. CONCLUSION In this work, we propose a CNN based novel method for performing burn-region segmentation in color images and evaluate it using newly prepared Burn Images dataset. The experimental results illustrate its effectiveness in comparison to existing approaches. Further, the proposed pixel-level segmentation method could be useful in estimating the burn surface area and burn severity in an accurate and time efficient manner.
Collapse
|
20
|
Senanayake S, White N, Graves N, Healy H, Baboolal K, Kularatna S. Machine learning in predicting graft failure following kidney transplantation: A systematic review of published predictive models. Int J Med Inform 2019; 130:103957. [PMID: 31472443 DOI: 10.1016/j.ijmedinf.2019.103957] [Citation(s) in RCA: 44] [Impact Index Per Article: 8.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2019] [Revised: 07/15/2019] [Accepted: 08/21/2019] [Indexed: 01/11/2023]
Abstract
INTRODUCTION Machine learning has been increasingly used to develop predictive models to diagnose different disease conditions. The heterogeneity of the kidney transplant population makes predicting graft outcomes extremely challenging. Several kidney graft outcome prediction models have been developed using machine learning, and are available in the literature. However, a systematic review of machine learning based prediction methods applied to kidney transplant has not been done to date. The main aim of our study was to perform an in-depth systematic analysis of different machine learning methods used to predict graft outcomes among kidney transplant patients, and assess their usefulness as an aid to decision-making. METHODS A systemic review of machine learning methods used to predict graft outcomes among kidney transplant patients was carried out using a search of the Medline, the Cumulative Index to Nursing and Allied Health Literature, EMBASE, PsycINFO and Cochrane databases. RESULTS A total of 295 articles were identified and extracted. Of these, 18 met the inclusion criteria. Most of the studies were published in the United States after 2010. The population size used to develop the models varied from 80 to 92,844, and the number of features in the models ranged from 6 to 71. The most common machine learning methods used were artificial neural networks, decision trees and Bayesian belief networks. Most of the machine learning based predictive models predicted graft failure with high sensitivity and specificity. Only one machine learning based prediction model had modelled time-to-event (survival) information. Seven studies compared the predictive performance of machine learning models with traditional regression methods and the performance of machine learning methods was found to be mixed, when compared with traditional regression methods. CONCLUSION There was a wide variation in the size of the study population and the input variables used. However, the prediction accuracy provided mixed results when machine learning and traditional predictive methods are compared. Based on reported gains in predictive performance, machine learning has the potential to improve kidney transplant outcome prediction and aid medical decision making.
Collapse
Affiliation(s)
- Sameera Senanayake
- Australian Centre for Health Service Innovation, Queensland University of Technology, Australia.
| | - Nicole White
- Australian Centre for Health Service Innovation, Queensland University of Technology, Australia
| | - Nicholas Graves
- Australian Centre for Health Service Innovation, Queensland University of Technology, Australia
| | - Helen Healy
- Royal Brisbane Hospital for Women, Brisbane, Australia; School of Medicine, University of Queensland, Australia
| | - Keshwar Baboolal
- Royal Brisbane Hospital for Women, Brisbane, Australia; School of Medicine, University of Queensland, Australia
| | - Sanjeewa Kularatna
- Australian Centre for Health Service Innovation, Queensland University of Technology, Australia
| |
Collapse
|
21
|
Hassanipour S, Ghaem H, Arab-Zozani M, Seif M, Fararouei M, Abdzadeh E, Sabetian G, Paydar S. Comparison of artificial neural network and logistic regression models for prediction of outcomes in trauma patients: A systematic review and meta-analysis. Injury 2019; 50:244-250. [PMID: 30660332 DOI: 10.1016/j.injury.2019.01.007] [Citation(s) in RCA: 31] [Impact Index Per Article: 6.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/12/2018] [Revised: 12/10/2018] [Accepted: 01/10/2019] [Indexed: 02/02/2023]
Abstract
BACKGROUND Currently, two models of artificial neural network (ANN) and logistic regression (LR) are known as models that extensively used in medical sciences. The aim of this study was to compare the ANN and LR models in prediction of Health-related outcomes in traumatic patients using a systematic review. METHODS The study was planned and conducted based on the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) checklist. A literature search of published studies was conducted using PubMed, Embase, Web of knowledge, Scopus, and Google Scholar in May 2018. Joanna Briggs Institute (JBI) checklists was used for assessing the quality of the included articles. RESULTS The literature searches yielded 326 potentially relevant studies from the primary searches. Overall, the review included 10 unique studies. The results of this study showed that the area under curve (AUC) for the ANN was 0.91, (95% CI 0.89-0.83) and 0.89, (95% CI 0.87-90) for the LR in random effect model. The accuracy rate for ANN and LR in random effect models were 90.5, (95% CI, 87.6-94.2) and 83.2, (95% CI 75.1-91.2), respectively. CONCLUSION The results of our study showed that ANN has better performance than LR in predicting the terminal outcomes of traumatic patients in both the AUC and accuracy rate. Using an ANN to predict the final implications of trauma patients can provide more accurate clinical decisions.
Collapse
Affiliation(s)
- Soheil Hassanipour
- Student Research Committee, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Haleh Ghaem
- Research Center for Health Sciences, Institute of Health, Epidemiology Department, School of Health, Shiraz University of Medical Sciences, Shiraz, Iran.
| | - Morteza Arab-Zozani
- Iranian Center of Excellence in Health Management, School of Management and Medical Informatics, Tabriz University of Medical Sciences, Tabriz, Iran
| | - Mozhgan Seif
- Department of Epidemiology, School of Health, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Mohammad Fararouei
- Department of Epidemiology, School of Health, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Elham Abdzadeh
- Department of Biology, Faculty of Science, University of Guilan, Rasht, Iran
| | - Golnar Sabetian
- Anesthesiology and Critical Care Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Shahram Paydar
- Trauma Research Center, Shahid Rajaee (Emtiaz) Trauma Hospital, Shiraz University of Medical Sciences, Shiraz, Iran
| |
Collapse
|
22
|
Liu NT, Rizzo JA, Shields BA, Serio-Melvin ML, Christy RJ, Salinas J. Predicting the Ability of Wounds to Heal Given Any Burn Size and Fluid Volume: An Analytical Approach. J Burn Care Res 2018; 39:661-669. [DOI: 10.1093/jbcr/iry021] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023]
Affiliation(s)
- Nehemiah T Liu
- U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, Texas
| | - Julie A Rizzo
- U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, Texas
| | - Beth A Shields
- U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, Texas
| | | | - Robert J Christy
- U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, Texas
| | - José Salinas
- U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, Texas
| |
Collapse
|
23
|
Wasiak J, Tyack Z, Ware R, Goodwin N, Faggion CM. Poor methodological quality and reporting standards of systematic reviews in burn care management. Int Wound J 2017; 14:754-763. [PMID: 27990772 PMCID: PMC7949759 DOI: 10.1111/iwj.12692] [Citation(s) in RCA: 32] [Impact Index Per Article: 4.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2016] [Accepted: 11/02/2016] [Indexed: 12/18/2022] Open
Abstract
The methodological and reporting quality of burn-specific systematic reviews has not been established. The aim of this study was to evaluate the methodological quality of systematic reviews in burn care management. Computerised searches were performed in Ovid MEDLINE, Ovid EMBASE and The Cochrane Library through to February 2016 for systematic reviews relevant to burn care using medical subject and free-text terms such as 'burn', 'systematic review' or 'meta-analysis'. Additional studies were identified by hand-searching five discipline-specific journals. Two authors independently screened papers, extracted and evaluated methodological quality using the 11-item A Measurement Tool to Assess Systematic Reviews (AMSTAR) tool and reporting quality using the 27-item Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist. Characteristics of systematic reviews associated with methodological and reporting quality were identified. Descriptive statistics and linear regression identified features associated with improved methodological quality. A total of 60 systematic reviews met the inclusion criteria. Six of the 11 AMSTAR items reporting on 'a priori' design, duplicate study selection, grey literature, included/excluded studies, publication bias and conflict of interest were reported in less than 50% of the systematic reviews. Of the 27 items listed for PRISMA, 13 items reporting on introduction, methods, results and the discussion were addressed in less than 50% of systematic reviews. Multivariable analyses showed that systematic reviews associated with higher methodological or reporting quality incorporated a meta-analysis (AMSTAR regression coefficient 2.1; 95% CI: 1.1, 3.1; PRISMA regression coefficient 6·3; 95% CI: 3·8, 8·7) were published in the Cochrane library (AMSTAR regression coefficient 2·9; 95% CI: 1·6, 4·2; PRISMA regression coefficient 6·1; 95% CI: 3·1, 9·2) and included a randomised control trial (AMSTAR regression coefficient 1·4; 95%CI: 0·4, 2·4; PRISMA regression coefficient 3·4; 95% CI: 0·9, 5·8). The methodological and reporting quality of systematic reviews in burn care requires further improvement with stricter adherence by authors to the PRISMA checklist and AMSTAR tool.
Collapse
Affiliation(s)
- Jason Wasiak
- Epworth HealthCareRichmondVAAustralia
- Department of Epidemiology and Preventive Medicine, School of Public Health and Preventive MedicineMonash UniversityMelbourneVICAustralia
| | - Zephanie Tyack
- Centre for Children's Burns and Trauma Research, Children's Health Research CentreThe University of Queensland & Centre for Functioning and Health Research Metro South HealthBrisbaneQLDAustralia
| | - Robert Ware
- Menzies Health Institute QueenslandGriffith UniversityBrisbaneQLDAustralia
| | | | - Clovis M Faggion
- Department of Periodontology and Restorative Dentistry, Faculty of DentistryUniversity of MunsterMunsterGermany
| |
Collapse
|
24
|
Thatcher JE, Squiers JJ, Kanick SC, King DR, Lu Y, Wang Y, Mohan R, Sellke EW, DiMaio JM. Imaging Techniques for Clinical Burn Assessment with a Focus on Multispectral Imaging. Adv Wound Care (New Rochelle) 2016; 5:360-378. [PMID: 27602255 DOI: 10.1089/wound.2015.0684] [Citation(s) in RCA: 54] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2016] [Accepted: 03/16/2016] [Indexed: 11/13/2022] Open
Abstract
Significance: Burn assessments, including extent and severity, are some of the most critical diagnoses in burn care, and many recently developed imaging techniques may have the potential to improve the accuracy of these evaluations. Recent Advances: Optical devices, telemedicine, and high-frequency ultrasound are among the highlights in recent burn imaging advancements. We present another promising technology, multispectral imaging (MSI), which also has the potential to impact current medical practice in burn care, among a variety of other specialties. Critical Issues: At this time, it is still a matter of debate as to why there is no consensus on the use of technology to assist burn assessments in the United States. Fortunately, the availability of techniques does not appear to be a limitation. However, the selection of appropriate imaging technology to augment the provision of burn care can be difficult for clinicians to navigate. There are many technologies available, but a comprehensive review summarizing the tissue characteristics measured by each technology in light of aiding clinicians in selecting the proper device is missing. This would be especially valuable for the nonburn specialists who encounter burn injuries. Future Directions: The questions of when burn assessment devices are useful to the burn team, how the various imaging devices work, and where the various burn imaging technologies fit into the spectrum of burn care will continue to be addressed. Technologies that can image a large surface area quickly, such as thermography or laser speckle imaging, may be suitable for initial burn assessment and triage. In the setting of presurgical planning, ultrasound or optical microscopy techniques, including optical coherence tomography, may prove useful. MSI, which actually has origins in burn care, may ultimately meet a high number of requirements for burn assessment in routine clinical use.
Collapse
Affiliation(s)
| | - John J. Squiers
- Spectral MD, Inc., Dallas, Texas
- Baylor Research Institute, Baylor Scott & White Health, Dallas, Texas
| | | | | | - Yang Lu
- Spectral MD, Inc., Dallas, Texas
| | | | | | | | - J. Michael DiMaio
- Spectral MD, Inc., Dallas, Texas
- Baylor Research Institute, Baylor Scott & White Health, Dallas, Texas
| |
Collapse
|