1
|
Fuller AT, Haglund MM. Partnering in Global Health: What Is a Successful Dyad? The Duke Experience. Neurosurg Clin N Am 2024; 35:421-428. [PMID: 39244314 DOI: 10.1016/j.nec.2024.05.004] [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: 09/09/2024]
Abstract
This article explores the transformative partnership between Duke Global Neurosurgery and Neurology (DGNN) and Uganda, emphasizing the power of dyads in international collaboration. It details the partnership's focus on service, research, and training, highlighting key accomplishments like the establishment of a neurosurgery residency program, expansion of services, and an epilepsy clinic. Challenges such as resource constraints and cross-cultural collaboration are addressed. Recommendations are provided for developing similar partnerships, underlining the importance of mutual respect, shared goals, and long-term commitment. The DGNN-Uganda dyad is a blueprint for leveraging collaboration to improve global neurosurgical care and reduce health care inequities.
Collapse
Affiliation(s)
- Anthony T Fuller
- Duke Global Neurosurgery and Neurology, Durham, NC, USA; Fuller Health Solutions, Salt Lake City, UT, USA
| | - Michael M Haglund
- Duke Global Neurosurgery and Neurology, Durham, NC, USA; Duke University Global Health Institute, Durham, NC, USA; Department of Neurosurgery, Duke Health, 4508 Hospital South, Durham, NC 27710, USA.
| |
Collapse
|
2
|
Shyalika C, Wickramarachchi R, El Kalach F, Harik R, Sheth A. Evaluating the Role of Data Enrichment Approaches towards Rare Event Analysis in Manufacturing. SENSORS (BASEL, SWITZERLAND) 2024; 24:5009. [PMID: 39124055 PMCID: PMC11315056 DOI: 10.3390/s24155009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/26/2024] [Revised: 07/24/2024] [Accepted: 07/26/2024] [Indexed: 08/12/2024]
Abstract
Rare events are occurrences that take place with a significantly lower frequency than more common, regular events. These events can be categorized into distinct categories, from frequently rare to extremely rare, based on factors like the distribution of data and significant differences in rarity levels. In manufacturing domains, predicting such events is particularly important, as they lead to unplanned downtime, a shortening of equipment lifespans, and high energy consumption. Usually, the rarity of events is inversely correlated with the maturity of a manufacturing industry. Typically, the rarity of events affects the multivariate data generated within a manufacturing process to be highly imbalanced, which leads to bias in predictive models. This paper evaluates the role of data enrichment techniques combined with supervised machine learning techniques for rare event detection and prediction. We use time series data augmentation and sampling to address the data scarcity, maintaining its patterns, and imputation techniques to handle null values. Evaluating 15 learning models, we find that data enrichment improves the F1 measure by up to 48% in rare event detection and prediction. Our empirical and ablation experiments provide novel insights, and we also investigate model interpretability.
Collapse
Affiliation(s)
- Chathurangi Shyalika
- Artificial Intelligence Institute, College of Engineering and Computing, University of South Carolina, Columbia, SC 29208, USA;
| | - Ruwan Wickramarachchi
- Artificial Intelligence Institute, College of Engineering and Computing, University of South Carolina, Columbia, SC 29208, USA;
| | - Fadi El Kalach
- McNair Center for Aerospace Innovation and Research, Department of Mechanical Engineering, College of Engineering and Computing, University of South Carolina, Columbia, SC 29201, USA; (F.E.K.); (R.H.)
| | - Ramy Harik
- McNair Center for Aerospace Innovation and Research, Department of Mechanical Engineering, College of Engineering and Computing, University of South Carolina, Columbia, SC 29201, USA; (F.E.K.); (R.H.)
| | - Amit Sheth
- Artificial Intelligence Institute, College of Engineering and Computing, University of South Carolina, Columbia, SC 29208, USA;
| |
Collapse
|
3
|
Raja HAA, Chaurasia B. Prognostication in traumatic brain injury. Neurosurg Rev 2024; 47:314. [PMID: 38990432 DOI: 10.1007/s10143-024-02574-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2024] [Revised: 07/02/2024] [Accepted: 07/08/2024] [Indexed: 07/12/2024]
Affiliation(s)
| | - Bipin Chaurasia
- Department of Neurosurgery, Neurosurgery Clinic, Birgunj, Nepal.
| |
Collapse
|
4
|
Halimi RA, Fuadi I, Alby D. The Use of Corticosteroid Randomisation after Significant Head Injury (CRASH) Prognostic Model as Mortality Predictor of Traumatic Brain Injury Patients Underwent Surgery in Low-Middle Income Countries. Anesthesiol Res Pract 2024; 2024:5241605. [PMID: 38948334 PMCID: PMC11213633 DOI: 10.1155/2024/5241605] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2024] [Revised: 05/17/2024] [Accepted: 06/07/2024] [Indexed: 07/02/2024] Open
Abstract
Background Traumatic brain injury (TBI) is a disruption to normal brain functions caused by traumas such as collisions, blows, or penetrating injuries. There are factors affecting patient outcomes that also have a predictive value. Limited data from low-middle income countries showed a high number of poor outcomes in TBI patients. The corticosteroid randomisation after significant head injury (CRASH) prognostic model is a predictive model that uses such factors and is often used in developed countries. The model has an excellent discriminative ability. However, there is still a lack of studies on its use in surgical patients in low-middle income countries. This study aimed to evaluate the CRASH model's validity to predict 14-day mortality of TBI patients who underwent surgery in low-middle income countries. Methods This retrospective analytical observational study employed total sampling including all TBI patients who underwent surgery with general anesthesia from January to December 2022. Statistical analysis was performed by applying Mann-Whitney and Fisher exact tests, while the model's discriminative ability was determined through the area under the curve (AUC) calculations. Results 112 TBI patients were admitted during the study period, and 74 patients were included. Independent statistical analysis showed that 14-day mortality risk, age, Glasgow Coma Scale score, TBI severity, pupillary response, and major extracranial trauma had a significant individual correlation with patients' actual mortality outcome (p < 0.05). The AUC analysis revealed an excellent mortality prediction (AUC 0.838; CI 95%). Conclusion The CRASH prognostic model performs well in predicting the 14-day mortality of TBI patients who underwent surgery in low-middle income countries.
Collapse
Affiliation(s)
- Radian A. Halimi
- Department of Anesthesiology and Intensive Therapy, Faculty of Medicine Padjadjaran University/Hasan Sadikin Central General Hospital, Bandung, West Java, Indonesia
| | - Iwan Fuadi
- Department of Anesthesiology and Intensive Therapy, Faculty of Medicine Padjadjaran University/Hasan Sadikin Central General Hospital, Bandung, West Java, Indonesia
| | - Dionisius Alby
- Department of Anesthesiology and Intensive Therapy, Faculty of Medicine Padjadjaran University/Hasan Sadikin Central General Hospital, Bandung, West Java, Indonesia
| |
Collapse
|
5
|
Zhu G, Ozkara BB, Chen H, Zhou B, Jiang B, Ding VY, Wintermark M. Enhancing hospital course and outcome prediction in patients with traumatic brain injury: A machine learning study. Neuroradiol J 2024; 37:74-83. [PMID: 37921691 PMCID: PMC10863571 DOI: 10.1177/19714009231212364] [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: 11/04/2023] Open
Abstract
PURPOSE We aimed to use machine learning (ML) algorithms with clinical, lab, and imaging data as input to predict various outcomes in traumatic brain injury (TBI) patients. METHODS In this retrospective study, blood samples were analyzed for glial fibrillary acidic protein (GFAP) and ubiquitin C-terminal hydrolase L1 (UCH-L1). The non-contrast head CTs were reviewed by two neuroradiologists for TBI common data elements (CDE). Three outcomes were designed to predict: discharged or admitted for further management (prediction 1), deceased or not deceased (prediction 2), and admission only, prolonged stay, or neurosurgery performed (prediction 3). Five ML models were trained. SHapley Additive exPlanations (SHAP) analyses were used to assess the relative significance of variables. RESULTS Four hundred forty patients were used to predict predictions 1 and 2, while 271 patients were used in prediction 3. Due to Prediction 3's hospitalization requirement, deceased and discharged patients could not be utilized. The Random Forest model achieved an average accuracy of 1.00 for prediction 1 and an accuracy of 0.99 for prediction 2. The Random Forest model achieved a mean accuracy of 0.93 for prediction 3. Key features were extracranial injury, hemorrhage, UCH-L1 for prediction 1; The Glasgow Coma Scale, age, GFAP for prediction 2; and GFAP, subdural hemorrhage volume, and pneumocephalus for prediction 3, per SHAP analysis. CONCLUSION Combining clinical and laboratory parameters with non-contrast CT CDEs allowed our ML models to accurately predict the designed outcomes of TBI patients. GFAP and UCH-L1 were among the significant predictor variables, demonstrating the importance of these biomarkers.
Collapse
Affiliation(s)
- Guangming Zhu
- Department of Neurology, The University of Arizona, USA
| | - Burak B Ozkara
- Department of Neuroradiology, MD Anderson Cancer Center, USA
| | - Hui Chen
- Department of Neuroradiology, MD Anderson Cancer Center, USA
| | - Bo Zhou
- Neuroradiology Division, Department of Radiology, Stanford University, USA
| | - Bin Jiang
- Neuroradiology Division, Department of Radiology, Stanford University, USA
| | - Victoria Y Ding
- Quantitative Sciences Unit, Department of Medicine, Stanford University, USA
| | - Max Wintermark
- Department of Neuroradiology, MD Anderson Cancer Center, USA
| |
Collapse
|
6
|
Schonfeld E, Mordekai N, Berg A, Johnstone T, Shah A, Shah V, Haider G, Marianayagam NJ, Veeravagu A. Machine Learning in Neurosurgery: Toward Complex Inputs, Actionable Predictions, and Generalizable Translations. Cureus 2024; 16:e51963. [PMID: 38333513 PMCID: PMC10851045 DOI: 10.7759/cureus.51963] [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: 08/27/2023] [Accepted: 01/08/2024] [Indexed: 02/10/2024] Open
Abstract
Machine learning can predict neurosurgical diagnosis and outcomes, power imaging analysis, and perform robotic navigation and tumor labeling. State-of-the-art models can reconstruct and generate images, predict surgical events from video, and assist in intraoperative decision-making. In this review, we will detail the neurosurgical applications of machine learning, ranging from simple to advanced models, and their potential to transform patient care. As machine learning techniques, outputs, and methods become increasingly complex, their performance is often more impactful yet increasingly difficult to evaluate. We aim to introduce these advancements to the neurosurgical audience while suggesting major potential roadblocks to their safe and effective translation. Unlike the previous generation of machine learning in neurosurgery, the safe translation of recent advancements will be contingent on neurosurgeons' involvement in model development and validation.
Collapse
Affiliation(s)
- Ethan Schonfeld
- Neurosurgery, Stanford University School of Medicine, Stanford, USA
| | | | - Alex Berg
- Neurosurgery, Stanford University School of Medicine, Stanford, USA
| | - Thomas Johnstone
- Neurosurgery, Stanford University School of Medicine, Stanford, USA
| | - Aaryan Shah
- School of Humanities and Sciences, Stanford University, Stanford, USA
| | - Vaibhavi Shah
- Neurosurgery, Stanford University School of Medicine, Stanford, USA
| | - Ghani Haider
- Neurosurgery, Stanford University School of Medicine, Stanford, USA
| | | | - Anand Veeravagu
- Neurosurgery, Stanford University School of Medicine, Stanford, USA
| |
Collapse
|
7
|
Fonseca J, Liu X, Oliveira HP, Pereira T. Mortality prediction using medical time series on TBI patients. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 242:107806. [PMID: 37832428 DOI: 10.1016/j.cmpb.2023.107806] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/28/2022] [Revised: 07/29/2023] [Accepted: 09/08/2023] [Indexed: 10/15/2023]
Abstract
BACKGROUND AND OBJECTIVE Traumatic Brain Injury (TBI) is one of the leading causes of injury-related mortality in the world, with severe cases reaching mortality rates of 30-40%. It is highly heterogeneous both in causes and consequences making more complex the medical interpretation and prognosis. Gathering clinical, demographic, and laboratory data to perform a prognosis requires time and skill in several clinical specialties. Artificial intelligence (AI) methods can take advantage of existing data by performing helpful predictions and guiding physicians toward a better prognosis and, consequently, better healthcare. The objective of this work was to develop learning models and evaluate their capability of predicting the mortality of TBI. The predictive model would allow the early assessment of the more serious cases and scarce medical resources can be pointed toward the patients who need them most. METHODS Long Short Term Memory (LSTM) and Transformer architectures were tested and compared in performance, coupled with data imbalance, missing data, and feature selection strategies. From the Medical Information Mart for Intensive Care III (MIMIC-III) dataset, a cohort of TBI patients was selected and an analysis of the first 48 hours of multiple time series sequential variables was done to predict hospital mortality. RESULTS The best performance was obtained with the Transformer architecture, achieving an AUC of 0.907 with the larger group of features and trained with class proportion class weights and binary cross entropy loss. CONCLUSIONS Using the time series sequential data, LSTM and Transformers proved to be both viable options for predicting TBI hospital mortality in 48 hours after admission. Overall, using sequential deep learning models with time series data to predict TBI mortality is viable and can be used as a helpful indicator of the well-being of patients.
Collapse
Affiliation(s)
- João Fonseca
- INESC TEC - Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal; FEUP - Faculty of Engineering, University of Porto, Porto, Portugal
| | - Xiuyun Liu
- Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China; Department of Biomedical Engineering, College of Precision Instruments and Optoelectronics Engineering, Tianjin, China
| | - Hélder P Oliveira
- INESC TEC - Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal; FCUP - Faculty of Science, University of Porto, Porto, Portugal
| | - Tania Pereira
- INESC TEC - Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal; FEUP - Faculty of Engineering, University of Porto, Porto, Portugal.
| |
Collapse
|
8
|
Habibzadeh A, Khademolhosseini S, Kouhpayeh A, Niakan A, Asadi MA, Ghasemi H, Tabrizi R, Taheri R, Khalili HA. Machine learning-based models to predict the need for neurosurgical intervention after moderate traumatic brain injury. Health Sci Rep 2023; 6:e1666. [PMID: 37908638 PMCID: PMC10613807 DOI: 10.1002/hsr2.1666] [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: 07/25/2023] [Revised: 09/14/2023] [Accepted: 10/16/2023] [Indexed: 11/02/2023] Open
Abstract
Background and Aims Traumatic brain injury (TBI) is a widespread global health issue with significant economic consequences. However, no existing model exists to predict the need for neurosurgical intervention in moderate TBI patients with positive initial computed tomography scans. This study determines the efficacy of machine learning (ML)-based models in predicting the need for neurosurgical intervention. Methods This is a retrospective study of patients admitted to the neuro-intensive care unit of Emtiaz Hospital, Shiraz, Iran, between January 2018 and December 2020. The most clinically important variables from patients that met our inclusion and exclusion criteria were collected and used as predictors. We developed models using multilayer perceptron, random forest, support vector machines (SVM), and logistic regression. To evaluate the models, their F1-score, sensitivity, specificity, and accuracy were assessed using a fourfold cross-validation method. Results Based on predictive models, SVM showed the highest performance in predicting the need for neurosurgical intervention, with an F1-score of 0.83, an area under curve of 0.93, sensitivity of 0.82, specificity of 0.84, a positive predictive value of 0.83, and a negative predictive value of 0.83. Conclusion The use of ML-based models as decision-making tools can be effective in predicting with high accuracy whether neurosurgery will be necessary after moderate TBIs. These models may ultimately be used as decision-support tools to evaluate early intervention in TBI patients.
Collapse
Affiliation(s)
- Adrina Habibzadeh
- Student Research CommitteeFasa University of Medical SciencesFasaIran
- USERN OfficeFasa University of Medical SciencesFasaIran
- Shiraz Trauma Research CenterShirazIran
| | | | - Amin Kouhpayeh
- Department of PharmacologyFasa University of Medical SciencesFasaIran
| | - Amin Niakan
- Shiraz Trauma Research CenterShirazIran
- Shiraz Neurosurgery DepartmentShiraz University of Medical SciencesShirazIran
| | - Mohammad Ali Asadi
- Department of Computer Engineering, Shiraz BranchIslamic Azad University, Shiraz UniversityShirazIran
| | - Hadis Ghasemi
- Biology and Medicine FacultyTaras Shevchenko National University of KyivKyivUkraine
| | - Reza Tabrizi
- USERN OfficeFasa University of Medical SciencesFasaIran
- Noncommunicable Diseases Research CenterFasa University of Medical SciencesFasaIran
- Clinical Research Development Unit, Valiasr HospitalFasa University of Medical SciencesFasaIran
| | - Reza Taheri
- Shiraz Trauma Research CenterShirazIran
- Clinical Research Development Unit, Valiasr HospitalFasa University of Medical SciencesFasaIran
- Shiraz Neuroscience Research CenterShiraz University of Medical SciencesShirazIran
| | - Hossein Ali Khalili
- Shiraz Trauma Research CenterShirazIran
- Shiraz Neurosurgery DepartmentShiraz University of Medical SciencesShirazIran
| |
Collapse
|
9
|
Van Deynse H, Cools W, De Deken VJ, Depreitere B, Hubloue I, Kimpe E, Moens M, Pien K, Tisseghem E, Van Belleghem G, Putman K. Predicting return to work after traumatic brain injury using machine learning and administrative data. Int J Med Inform 2023; 178:105201. [PMID: 37657205 DOI: 10.1016/j.ijmedinf.2023.105201] [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: 03/20/2023] [Revised: 07/02/2023] [Accepted: 08/23/2023] [Indexed: 09/03/2023]
Abstract
BACKGROUND Accurate patient-specific predictions on return-to-work after traumatic brain injury (TBI) can support both clinical practice and policymaking. The use of machine learning on large administrative data provides interesting opportunities to create such prognostic models. AIM The current study assesses whether return-to-work one year after TBI can be predicted accurately from administrative data. Additionally, this study explores how model performance and feature importance change depending on whether a distinction is made between mild and moderate-to-severe TBI. METHODS This study used a population-based dataset that combined discharge, claims and social security data of patients hospitalized with a TBI in Belgium during the year 2016. The prediction of TBI was attempted with three algorithms, elastic net logistic regression, random forest and gradient boosting and compared in their performance by their accuracy, sensitivity, specificity and area under the receiver operator curve (ROC AUC). RESULTS The distinct modelling algorithms resulted in similar results, with 83% accuracy (ROC AUC 85%) for a binary classification of employed vs. not employed and up to 76% (ROC AUC 82%) for a multiclass operationalization of employment outcome. Modelling mild and moderate-to-severe TBI separately did not result in considerable differences in model performance and feature importance. The features of main importance for return-to-work prediction were related to pre-injury employment. DISCUSSION While clearly offering some information beneficial for predicting return-to-work, administrative data needs to be supplemented with additional information to allow further improvement of patient-specific prognose.
Collapse
Affiliation(s)
- Helena Van Deynse
- Interuniversity Centre for Health Economics Research (I-CHER), Vrije Universiteit Brussel, Brussels, Belgium.
| | - Wilfried Cools
- Support for Quantitative and Qualitative Research (SQUARE), Vrije Universiteit Brussel, Brussels, Belgium
| | - Viktor-Jan De Deken
- Interuniversity Centre for Health Economics Research (I-CHER), Vrije Universiteit Brussel, Brussels, Belgium
| | - Bart Depreitere
- Department of Neurosurgery, Universitair Ziekenhuis Leuven, Katholieke Universiteit Leuven, Leuven, Belgium
| | - Ives Hubloue
- Department of Emergency Medicine, Universitair Ziekenhuis Brussel, Vrije Universiteit Brussel, Brussels, Belgium
| | - Eva Kimpe
- Interuniversity Centre for Health Economics Research (I-CHER), Vrije Universiteit Brussel, Brussels, Belgium
| | - Maarten Moens
- Department of Neurosurgery, Universitair Ziekenhuis Brussel, Brussels, Belgium; Department of Radiology, Universitair Ziekenhuis Brussel, Brussels, Belgium
| | - Karen Pien
- Department of Medical Registration, Universitair Ziekenhuis Brussel, Brussels, Belgium
| | - Ellen Tisseghem
- Interuniversity Centre for Health Economics Research (I-CHER), Vrije Universiteit Brussel, Brussels, Belgium
| | - Griet Van Belleghem
- Interuniversity Centre for Health Economics Research (I-CHER), Vrije Universiteit Brussel, Brussels, Belgium
| | - Koen Putman
- Interuniversity Centre for Health Economics Research (I-CHER), Vrije Universiteit Brussel, Brussels, Belgium
| |
Collapse
|
10
|
Matsuo K, Aihara H, Hara Y, Morishita A, Sakagami Y, Miyake S, Tatsumi S, Ishihara S, Tohma Y, Yamashita H, Sasayama T. Machine Learning to Predict Three Types of Outcomes After Traumatic Brain Injury Using Data at Admission: A Multi-Center Study for Development and Validation. J Neurotrauma 2023; 40:1694-1706. [PMID: 37029810 DOI: 10.1089/neu.2022.0515] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/09/2023] Open
Abstract
The difficulty of accurately identifying patients who would benefit from promising treatments makes it challenging to prove the efficacy of novel treatments for traumatic brain injury (TBI). Although machine learning is being increasingly applied to this task, existing binary outcome prediction models are insufficient for the effective stratification of TBI patients. The aim of this study was to develop an accurate 3-class outcome prediction model to enable appropriate patient stratification. To this end, retrospective balanced data of 1200 blunt TBI patients admitted to six Japanese hospitals from January 2018 onwards (200 consecutive cases at each institution) were used for model training and validation. We incorporated 21 predictors obtained in the emergency department, including age, sex, six clinical findings, four laboratory parameters, eight computed tomography findings, and an emergency craniotomy. We developed two machine learning models (XGBoost and dense neural network) and logistic regression models to predict 3-class outcomes based on the Glasgow Outcome Scale-Extended (GOSE) at discharge. The prediction models were developed using a training dataset with n = 1000, and their prediction performances were evaluated over two validation rounds on a validation dataset (n = 80) and a test dataset (n = 120) using the bootstrap method. Of the 1200 patients in aggregate, the median patient age was 71 years, 199 (16.7%) exhibited severe TBI, and emergency craniotomy was performed on 104 patients (8.7%). The median length of stay was 13.0 days. The 3-class outcomes were good recovery/moderate disability for 709 patients (59.1%), severe disability/vegetative state in 416 patients (34.7%), and death in 75 patients (6.2%). XGBoost model performed well with 69.5% sensitivity, 82.5% accuracy, and an area under the receiver operating characteristic curve of 0.901 in the final validation. In terms of the receiver operating characteristic curve analysis, the XGBoost outperformed the neural network-based and logistic regression models slightly. In particular, XGBoost outperformed the logistic regression model significantly in predicting severe disability/vegetative state. Although each model predicted favorable outcomes accurately, they tended to miss the mortality prediction. The proposed machine learning model was demonstrated to be capable of accurate prediction of in-hospital outcomes following TBI, even with the three GOSE-based categories. As a result, it is expected to be more impactful in the development of appropriate patient stratification methods in future TBI studies than conventional binary prognostic models. Further, outcomes were predicted based on only clinical data obtained from the emergency department. However, developing a robust model with consistent performance in diverse scenarios remains challenging, and further efforts are needed to improve generalization performance.
Collapse
Affiliation(s)
- Kazuya Matsuo
- Department of Neurosurgery, Hyogo Emergency Medical Center and Kobe Red Cross Hospital, Kobe, Japan
- Department of Neurosurgery, Kobe University Graduate School of Medicine, Kobe, Japan
| | - Hideo Aihara
- Department of Neurosurgery, Hyogo Prefectural Himeji Cardiovascular Center, Himeji, Japan
| | - Yoshie Hara
- Department of Neurosurgery, Hyogo Emergency Medical Center and Kobe Red Cross Hospital, Kobe, Japan
| | - Akitsugu Morishita
- Department of Neurosurgery, Hyogo Prefectural Kakogawa Medical Center, Kakogawa, Japan
| | - Yoshio Sakagami
- Department of Neurosurgery, Hyogo Prefectural Awaji Medical Center, Sumoto, Japan
| | - Shigeru Miyake
- Department of Neurosurgery, Kita-harima Medical Center, Ono, Japan
| | - Shotaro Tatsumi
- Department of Neurosurgery, Hirohata Steel Memorial Hospital, Himeji, Japan
| | - Satoshi Ishihara
- Department of Emergency and Critical Care Medicine, Hyogo Emergency Medical Center, Kobe, Japan
| | - Yoshiki Tohma
- Acute Care Medical Center, Hyogo Prefectural Kakogawa Medical Center, Kakogawa, Japan
| | - Haruo Yamashita
- Department of Neurosurgery, Hyogo Emergency Medical Center and Kobe Red Cross Hospital, Kobe, Japan
| | - Takashi Sasayama
- Department of Neurosurgery, Kobe University Graduate School of Medicine, Kobe, Japan
| |
Collapse
|
11
|
Rajaei F, Cheng S, Williamson CA, Wittrup E, Najarian K. AI-Based Decision Support System for Traumatic Brain Injury: A Survey. Diagnostics (Basel) 2023; 13:diagnostics13091640. [PMID: 37175031 PMCID: PMC10177859 DOI: 10.3390/diagnostics13091640] [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: 03/28/2023] [Revised: 04/22/2023] [Accepted: 04/29/2023] [Indexed: 05/15/2023] Open
Abstract
Traumatic brain injury (TBI) is one of the major causes of disability and mortality worldwide. Rapid and precise clinical assessment and decision-making are essential to improve the outcome and the resulting complications. Due to the size and complexity of the data analyzed in TBI cases, computer-aided data processing, analysis, and decision support systems could play an important role. However, developing such systems is challenging due to the heterogeneity of symptoms, varying data quality caused by different spatio-temporal resolutions, and the inherent noise associated with image and signal acquisition. The purpose of this article is to review current advances in developing artificial intelligence-based decision support systems for the diagnosis, severity assessment, and long-term prognosis of TBI complications.
Collapse
Affiliation(s)
- Flora Rajaei
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USA
| | - Shuyang Cheng
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USA
| | - Craig A Williamson
- Department of Neurosurgery, University of Michigan, Ann Arbor, MI 48109, USA
- Max Harry Weil Institute for Critical Care Research and Innovation, University of Michigan, Ann Arbor, MI 48109, USA
| | - Emily Wittrup
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USA
| | - Kayvan Najarian
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI 48109, USA
- Max Harry Weil Institute for Critical Care Research and Innovation, University of Michigan, Ann Arbor, MI 48109, USA
- Michigan Institute for Data Science, University of Michigan, Ann Arbor, MI 48109, USA
- Department of Emergency Medicine, University of Michigan, Ann Arbor, MI 48109, USA
- Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI 48109, USA
- Center for Data-Driven Drug Development and Treatment Assessment (DATA), University of Michigan, Ann Arbor, MI 48109, USA
| |
Collapse
|
12
|
Kn BP, Cs A, Mohammed A, Chitta KK, To XV, Srour H, Nasrallah F. An end-end deep learning framework for lesion segmentation on multi-contrast MR images-an exploratory study in a rat model of traumatic brain injury. Med Biol Eng Comput 2023; 61:847-865. [PMID: 36624356 DOI: 10.1007/s11517-022-02752-4] [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: 02/07/2022] [Accepted: 12/24/2022] [Indexed: 01/11/2023]
Abstract
Traumatic brain injury (TBI) engenders traumatic necrosis and penumbra-areas of secondary neural injury which are crucial targets for therapeutic interventions. Segmenting manually areas of ongoing changes like necrosis, edema, hematoma, and inflammation is tedious, error-prone, and biased. Using the multi-parametric MR data from a rodent model study, we demonstrate the effectiveness of an end-end deep learning global-attention-based UNet (GA-UNet) framework for automatic segmentation and quantification of TBI lesions. Longitudinal MR scans (2 h, 1, 3, 7, 14, 30, and 60 days) were performed on eight Sprague-Dawley rats after controlled cortical injury was performed. TBI lesion and sub-regions segmentation was performed using 3D-UNet and GA-UNet. Dice statistics (DSI) and Hausdorff distance were calculated to assess the performance. MR scan variations-based (bias, noise, blur, ghosting) data augmentation was performed to develop a robust model.Training/validation median DSI for U-Net was 0.9368 with T2w and MPRAGE inputs, whereas GA-UNet had 0.9537 for the same. Testing accuracies were higher for GA-UNet than U-Net with a DSI of 0.8232 for the T2w-MPRAGE inputs.Longitudinally, necrosis remained constant while oligemia and penumbra decreased, and edema appearing around day 3 which increased with time. GA-UNet shows promise for multi-contrast MR image-based segmentation/quantification of TBI in large cohort studies.
Collapse
Affiliation(s)
- Bhanu Prakash Kn
- Clinical Data Analytics & Radiomics, Cellular Image Informatics, Bioinformatics Institute, A*STAR, 30 Biopolis St Matrix, Singapore, 138671, Singapore. .,Cellular Image Informatics, Bioinformatics Institute, A*STAR Horizontal Technology Centers, Singapore, Singapore.
| | - Arvind Cs
- Clinical Data Analytics & Radiomics, Cellular Image Informatics, Bioinformatics Institute, A*STAR, 30 Biopolis St Matrix, Singapore, 138671, Singapore
| | - Abdalla Mohammed
- Queensland Brain Institute, The University of Queensland, Building 79, Upland Road, Saint Lucia, Brisbane, QLD, 4072, Australia
| | - Krishna Kanth Chitta
- Signal and Image Processing Group, Laboratory of Molecular Imaging, Singapore Bioimaging Consortium, A*STAR, 02-02 Helios 11, Biopolis Way, Singapore, 138667, Singapore
| | - Xuan Vinh To
- Queensland Brain Institute, The University of Queensland, Building 79, Upland Road, Saint Lucia, Brisbane, QLD, 4072, Australia
| | - Hussein Srour
- Queensland Brain Institute, The University of Queensland, Building 79, Upland Road, Saint Lucia, Brisbane, QLD, 4072, Australia
| | - Fatima Nasrallah
- Queensland Brain Institute, The University of Queensland, Building 79, Upland Road, Saint Lucia, Brisbane, QLD, 4072, Australia
| |
Collapse
|