Article
Critical Care Medicine
Sidish S. Venkataraman, Joseph P. Herbert, Vijay M. Ravindra, Bangning N. Yu, Robert J. Bollo, Charles S. Cox Jr, Stephen R. Gannon, David D. Limbrick Jr, Robert P. Naftel, Irma T. Ugalde, Brian K. Yorkgitis, Howard L. Weiner, Manish N. Shah
Summary: Blunt cerebrovascular injury (BCVI) refers to blunt trauma that damages the vertebral and/or carotid arteries in the head and neck. The debate revolves around identifying high-risk pediatric trauma patients who require angiographic/vessel imaging for BCVI. This study aims to validate the McGovern score, a screening tool proposed previously, by pooling data from multiple pediatric trauma centers. The results show that the McGovern score is a reliable screening tool with high sensitivity and negative predictive value for pediatric BCVI.
JOURNAL OF NEUROTRAUMA
(2023)
Article
Medicine, General & Internal
Jeff Choi, Edward B. Vendrow, Michael Moor, David A. Spain
Summary: In this study, a practical model was developed using a limited number of injury patterns to quantify injury severity through 3 intuitive outcomes.
Article
Emergency Medicine
Saptarshi Mukerji, Eunicia Tan, Charlotte May, Christina Micanovic, Paul Blakemore, Kelly Phelps, Hannah Melville, Peter Jones
Summary: The STUMBL score was assessed for complications of blunt chest trauma in New Zealand, showing better performance in predicting prolonged length of stay and mortality at specific cut-off points, but insufficient predictive ability for general complications. The score is more accurate in the New Zealand Pakeha population and caution is needed when using it in Maori and Pasifika populations. Further validation with a larger prospective study is necessary.
EMERGENCY MEDICINE AUSTRALASIA
(2021)
Article
Pediatrics
Chiaki Toida, Takashi Muguruma, Masayasu Gakumazawa, Mafumi Shinohara, Takeru Abe, Ichiro Takeuchi
Summary: This study aimed to develop a model for predicting the survival of Japanese pediatric patients with blunt trauma and compare its validity with that of the conventional TRISS model. Logistic regression analysis was performed and it was found that Model 11 had the best performance in patients with lower survival probability and neonates/infants. However, the predictive ability of the newly modified models was not superior to that of the current TRISS model.
Article
Clinical Neurology
Keita Shibahashi, Hidenori Hoda, Takuto Ishida, Takayuki Motoshima, Kazuhiro Sugiyama, Yuichi Hamabe
Summary: A new screening model using a nomogram was developed and validated in a nationwide Japanese database to quantify the risk of blunt cerebrovascular injury (BCVI). The model includes 13 significant factors associated with arterial BCVI, with a high discriminatory ability in predicting carotid and vertebral artery injuries.
JOURNAL OF NEUROSURGERY
(2021)
Review
Medicine, General & Internal
Daniela Mazzaccaro, Paolo Righini, Fabiana Fancoli, Matteo Giannetta, Alfredo Modafferi, Giovanni Malacrida, Giovanni Nano
Summary: Blunt thoracic aortic injury (BTAI) is a potentially fatal condition that requires prompt recognition and urgent management. Clinical manifestations of BTAI are not straightforward and may lead to misdiagnosis. The severity of aortic injury is crucial in determining mortality and morbidity rates, as well as guiding treatment decisions, especially when other organs are also involved. Delayed endovascular repair has become the mainstay of treatment for hemodynamically stable patients, providing lower perioperative mortality and morbidity rates compared to open surgical repair. However, concerns exist regarding long-term surveillance and radiation exposure, especially in younger patients. This paper aims to provide an update on diagnostic modalities and treatment strategies for BTAI patients.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Medicine, General & Internal
Elena Callisto, Giorgio Costantino, Andrew Tabner, Dean Kerslake, Matthew J. Reed
Summary: The STUMBL score, a new prognostic score for blunt chest trauma, was compared to the clinical judgement of emergency department (ED) clinicians. The study found that a STUMBL score >= 11 did not perform better than clinical judgement in predicting complications and resulted in more patients being admitted to the hospital.
INTERNAL AND EMERGENCY MEDICINE
(2022)
Article
Medicine, General & Internal
Ligang Xu, Zhaofeng Kang, Dongfang Wang, Yukun Liu, Chuntao Wang, Zhanfei Li, Xiangjun Bai, Yuchang Wang
Summary: This study established an accurate and easily implementable PIICS risk prediction model, which provides a novel approach for prognostic prediction in severe trauma patients during hospitalization.
FRONTIERS IN MEDICINE
(2023)
Article
Medicine, Research & Experimental
David Forner, Christopher W. Noel, Matthew P. Guttman, Barbara Haas, Danny Enepekides, Matthew H. Rigby, Avery B. Nathens, Antoine Eskander
Summary: This study investigated the impact of blunt and penetrating neck injuries on mortality and length of hospital stay, finding that blunt neck injuries are associated with lower mortality rates and shorter hospital stays.
Article
Critical Care Medicine
Jacopo Davide Giamello, Gianpiero Martini, Davide Prato, Marco Santoro, Ylenia Arese, Remo Melchio, Luca Bertolaccini, Ceri Elisabeth Battle, Timothy Driscoll, Andrea Sciolla, Giuseppe Lauria
Summary: This study validated the STUMBL score in predicting outcomes of patients with blunt thoracic trauma in an Italian emergency department. The results showed that the score had excellent discrimination and calibration.
INJURY-INTERNATIONAL JOURNAL OF THE CARE OF THE INJURED
(2023)
Article
Biochemistry & Molecular Biology
Alexander Maitz, Felix Haussner, Sonja Braumueller, Andrea Hoffmann, Ludmila Lupu, Ulrich Wachter, Peter Radermacher, Christian K. Braun, Hans-Joachim Wilke, Morten Vogt, Anita Ignatius, Rebecca Halbgebauer, Lucas Bettac, Thomas F. E. Barth, Markus Huber-Lang, Annette Palmer
Summary: The study investigated the organ and immune response after blast-induced blunt abdominal trauma in mice. A reproducible model with severity-dependent organ injury patterns, systemic inflammatory response, and multi-organ dysfunction was established. Trauma severity was associated with survival rate, hemodynamic changes, and systemic damage, indicating early impairment of organ functions post-injury.
Article
Surgery
Christopher J. Dente, Michael J. Mina, Bryan C. Morse, Hannah Hensman, Seth Schobel, Rondi B. Gelbard, Arnaud Belard, Timothy G. Buchman, Allan D. Kirk, Eric A. Elster
Summary: A smartphone application with a predictive algorithm was designed to assist surgeons in assessing the need for massive transfusion protocol activation. The algorithm demonstrated high accuracy in predicting the need for massive transfusion and influencing surgeons' decision-making.
Article
Critical Care Medicine
Felix Haussner, Alexander Maitz, Volker Rasche, Andrea Hoffmann, Sonja Braumuller, Ludmila Lupu, Anita Ignatius, Thomas A. Neff, Annette Palmer, Markus Huber-Lang
Summary: Abdominal trauma is a major global issue, and the consequences of blast injuries are often underestimated. In this study using a mouse model, early intestinal damage and impairment of the gut-blood barrier were observed after blunt abdominal trauma. This research provides a sufficient model for further understanding the immunopathophysiological consequences of abdominal trauma and evaluating new therapeutic approaches.
Article
Critical Care Medicine
Alan Costa, Pierre-Nicolas Carron, Tobias Zingg, Ian Roberts, Francois-Xavier Ageron
Summary: Early identification of bleeding is crucial for injured patients. This study compared the performance of different bleeding scores and found that the BATT score accurately estimates the risk of early death. However, scores predicting massive transfusion had a high undertriage rate, and the outcome of massive transfusion may not be appropriate for stratifying the risk of life-threatening bleeding.
Article
Radiology, Nuclear Medicine & Medical Imaging
Hannes Ruhnke, Bertram Jehs, Florian Schwarz, Mark Haerting, Katharina Rippel, Ramona Wudy, Thomas J. Kroencke, Christian Scheurig-Muenkler
Summary: In the management of medium-grade blunt splenic trauma, non-operative treatment has a high success rate, with active bleeding being the most important predictor of NOM failure. SAE should be reserved for high-grade injuries and visible vascular pathology or active bleeding to avoid a significant increase in NNT.
EUROPEAN JOURNAL OF RADIOLOGY
(2021)
Article
Surgery
Tyler J. Loftus, Alexander P. J. Vlaar, Andrew J. Hung, Azra Bihorac, Bradley M. Dennis, Catherine Juillard, Daniel A. Hashimoto, Haytham M. A. Kaafarani, Patrick J. Tighe, Paul C. Kuo, Shuhei Miyashita, Steven D. Wexner, Kevin E. Behrns
Summary: As opportunities for artificial intelligence to augment surgical care expand, there is both enthusiasm and concern regarding its safety and efficacy. Surgeons and surgical data scientists must understand the state-of-the-art, recognize gaps in knowledge and technology, and critically evaluate the published literature.
Article
Critical Care Medicine
Phillip Joseph, Rosa Pari, Sarah Miller, Arabella Warren, Mary Catherine Stovall, Johanna Squires, Chia-Jung Chang, Wenzhong Xiao, Aaron B. Waxman, David M. Systrom
Summary: The study found that neurovascular dysregulation may contribute to exercise intolerance in ME/CFS, and pharmacologic cholinergic stimulation can improve exercise capacity in these patients.
Article
Urology & Nephrology
Kia Khezeli, Scott Siegel, Benjamin Shickel, Tezcan Ozrazgat-Baslanti, Azra Bihorac, Parisa Rashidi
CLINICAL JOURNAL OF THE AMERICAN SOCIETY OF NEPHROLOGY
(2023)
Article
Urology & Nephrology
Benjamin Shickel, Tyler J. Loftus, Yuanfang Ren, Parisa Rashidi, Azra Bihorac, Tezcan Ozrazgat-Baslanti
CLINICAL JOURNAL OF THE AMERICAN SOCIETY OF NEPHROLOGY
(2023)
Article
Multidisciplinary Sciences
Benjamin Shickel, Tyler J. Loftus, Matthew Ruppert, Gilbert R. Upchurch, Tezcan Ozrazgat-Baslanti, Parisa Rashidi, Azra Bihorac
Summary: Accurate prediction of postoperative complications is important for shared decision-making regarding prognosis, risk-reduction, and resource allocation. This study compared the performance of deep learning models with traditional machine learning models in predicting postoperative complications using patient data. The results showed that deep learning models were more efficient and provided more precise representations of patient health. The interpretability mechanisms identified modifiable risk factors, and the uncertainty metrics enhanced clinical trust. These findings suggest the potential of deep learning for effective clinical implementation.
SCIENTIFIC REPORTS
(2023)
Article
Cardiac & Cardiovascular Systems
Mohammad A. Al-Ani, Chen Bai, Maisara Bledsoe, Mustafa M. Ahmed, Juan R. Vilaro, Alex M. Parker, Juan M. Aranda Jr, Eric Jeng, Benjamin Shickel, Azra Bihorac, Giles J. Peek, Mark S. Bleiweis, Jeffrey P. Jacobs, Mamoun T. Mardini
Summary: This study aimed to explore the impact of device selection on heart transplantation outcomes, taking into account regional practice variation. The results showed that patients using Impella devices had higher medical acuity and lower success rate of transplantation as status 2 compared to those using IABP. The utilization ratio of IABP to Impella varied widely between regions, but this difference was not justified by medical acuity or other factors.
JOURNAL OF HEART AND LUNG TRANSPLANTATION
(2023)
Article
Surgery
Esra Adiyeke, Yuanfang Ren, Matthew M. Ruppert, Benjamin Shickel, Sandra L. Kane-Gill, Raghavan Murugan, Parisa Rashidi, Azra Bihorac, Tezcan Ozrazgat-Baslanti
Summary: This study used a recurrent neural network-based model to predict the risk and status of postoperative acute kidney injury, and the results showed that this model was more accurate compared to logistic regression and random forest models. The study demonstrates that temporal processing of patient information can lead to more accurate prediction of acute kidney injury and improve model explainability.
Article
Biochemistry & Molecular Biology
Daniel A. Reich, Esra Adiyeke, Tezcan Ozrazgat-Baslanti, Andrew K. Rabley, Shahab Bozorgmehri, Azra Bihorac, Vincent G. Bird
Summary: The study aimed to determine the prevalence and severity of postoperative acute kidney injury (AKI) in patients with nephrolithiasis undergoing percutaneous nephrolithotomy (PCNL), identify risk factors, and understand the resulting outcomes. Among 417 encounters, 24.9% had AKI and approximately one-quarter of AKI patients progressed to Stage 2 or higher AKI. Hypertension, peripheral vascular disease, chronic kidney disease, and chronic anemia were significant risk factors. AKI patients had higher percentages of cardiovascular, neurologic complications, sepsis, and prolonged ICU stay. The length of hospital and ICU stay was also greater in the AKI group.
Article
Surgery
Amanda C. Filiberto, Shunshun Miao, Yuanfang Ren, Tezcan Ozrazgat-Baslanti, Sara E. Hensley, Christopher R. Jacobs, M. Libby Weaver, Gilbert R. Upchurch Jr, Azra Bihorac, Michol Cooper
Summary: This study found that bilateral atherosclerotic renal artery stenosis (RAS) is associated with increased incidence of postoperative AKI and mortality. It suggests that bilateral RAS may serve as a marker of poor outcomes and should be considered in preoperative risk stratification.
SURGERY OPEN SCIENCE
(2023)
Article
Critical Care Medicine
Philip A. Efron, Scott C. Brakenridge, Alicia M. Mohr, Evan L. Barrios, Valerie E. Polcz, Stephen Anton, Tezcan Ozrazgat-Baslanti, Azra Bihorac, Faheem Guirgis, Tyler J. Loftus, Martin Rosenthal, Christian Leeuwenburgh, Robert Mankowski, Lyle L. Moldawer, Frederick A. Moore
JOURNAL OF TRAUMA AND ACUTE CARE SURGERY
(2023)
Review
Medical Informatics
Jeremy A. Balch, Matthew M. Ruppert, Tyler J. Loftus, Ziyuan Guan, Yuanfang Ren, Gilbert R. Upchurch, Tezcan Ozrazgat-Baslanti, Parisa Rashidi, Azra Bihorac
Summary: This study evaluates and compares the functionalities, strengths, and weaknesses of existing ML-CISs and proposes guidelines for future work optimization. The articles on FHIR-based ML-CISs were categorized into clinical decision support systems, data management and analytic platforms, or auxiliary modules and APIs. Shortcomings in current ML-CISs include lack of EHR interoperability and clinical efficacy validation.
JMIR MEDICAL INFORMATICS
(2023)
Review
Urology & Nephrology
Nabihah Amatullah, Britney A. Stottlemyer, Isabelle Zerfas, Cole Stevens, Tezcan Ozrazgat-Baslanti, Azra Bihorac, Sandra L. Kane-Gill
Summary: This study reviewed the variability in criteria for drug-associated acute kidney injury (D-AKI) and emphasized the importance of establishing minimum reporting expectations and criteria for standardized pharmacovigilance strategies.
Article
Health Care Sciences & Services
Tyler J. Loftus, Matthew M. Ruppert, Benjamin Shickel, Tezcan Ozrazgat-Baslanti, Jeremy A. Balch, Philip A. Efron, Gilbert R. Upchurch, Parisa Rashidi, Christopher Tignanelli, Jiang Bian, Azra Bihorac
Summary: In healthcare AI applications, maintaining generalizability, external validity, and reproducibility is crucial. Traditional approaches of sharing patient data can compromise data privacy and security. Federated learning techniques offer an alternative by sharing knowledge instead of data, preserving both data privacy and availability.
Review
Health Care Sciences & Services
Anis Davoudi, Benjamin Shickel, Patrick James Tighe, Azra Bihorac, Parisa Rashidi
Summary: Patients in critical care need detailed and continuous monitoring, which current practices fail to capture important functional and behavioral indices. However, recent advances in non-invasive sensing technology, high throughput computing, and deep learning techniques are expected to change this situation.
FRONTIERS IN DIGITAL HEALTH
(2022)
Article
Urology & Nephrology
Danielle E. Soranno, Azra Bihorac, Stuart L. Goldstein, Kianoush B. Kashani, Shina Menon, Girish N. Nadkarni, Javier A. Neyra, Neesh Pannu, Karandeep Singh, Jorge Cerda, Jay L. Koyner