1
|
Brunese MC, Avella P, Cappuccio M, Spiezia S, Pacella G, Bianco P, Greco S, Ricciardelli L, Lucarelli NM, Caiazzo C, Vallone G. Future Perspectives on Radiomics in Acute Liver Injury and Liver Trauma. J Pers Med 2024; 14:572. [PMID: 38929793 PMCID: PMC11204538 DOI: 10.3390/jpm14060572] [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: 04/02/2024] [Revised: 05/02/2024] [Accepted: 05/09/2024] [Indexed: 06/28/2024] Open
Abstract
Background: Acute liver injury occurs most frequently due to trauma, but it can also occur because of sepsis or drug-induced injury. This review aims to analyze artificial intelligence (AI)'s ability to detect and quantify liver injured areas in adults and pediatric patients. Methods: A literature analysis was performed on the PubMed Dataset. We selected original articles published from 2018 to 2023 and cohorts with ≥10 adults or pediatric patients. Results: Six studies counting 564 patients were collected, including 170 (30%) children and 394 adults. Four (66%) articles reported AI application after liver trauma, one (17%) after sepsis, and one (17%) due to chemotherapy. In five (83%) studies, Computed Tomography was performed, while in one (17%), FAST-UltraSound was performed. The studies reported a high diagnostic performance; in particular, three studies reported a specificity rate > 80%. Conclusions: Radiomics models seem reliable and applicable to clinical practice in patients affected by acute liver injury. Further studies are required to achieve larger validation cohorts.
Collapse
Affiliation(s)
- Maria Chiara Brunese
- Department of Medicine and Health Science “V. Tiberio”, University of Molise, 86100 Campobasso, Italy; (M.C.B.)
| | - Pasquale Avella
- Department of Clinical Medicine and Surgery, University of Naples Federico II, 80131 Naples, Italy
- Hepatobiliary and Pancreatic Surgery Unit, Pineta Grande Hospital, 81030 Castel Volturno, Italy
| | - Micaela Cappuccio
- Department of Clinical Medicine and Surgery, University of Naples Federico II, 80131 Naples, Italy
| | - Salvatore Spiezia
- Department of Medicine and Health Science “V. Tiberio”, University of Molise, 86100 Campobasso, Italy; (M.C.B.)
| | - Giulia Pacella
- Department of Medicine and Health Science “V. Tiberio”, University of Molise, 86100 Campobasso, Italy; (M.C.B.)
| | - Paolo Bianco
- Hepatobiliary and Pancreatic Surgery Unit, Pineta Grande Hospital, 81030 Castel Volturno, Italy
| | - Sara Greco
- Interdisciplinary Department of Medicine, Section of Radiology and Radiation Oncology, University of Bari “Aldo Moro”, 70124 Bari, Italy
| | | | - Nicola Maria Lucarelli
- Interdisciplinary Department of Medicine, Section of Radiology and Radiation Oncology, University of Bari “Aldo Moro”, 70124 Bari, Italy
| | - Corrado Caiazzo
- Department of Medicine and Health Science “V. Tiberio”, University of Molise, 86100 Campobasso, Italy; (M.C.B.)
| | - Gianfranco Vallone
- Department of Medicine and Health Science “V. Tiberio”, University of Molise, 86100 Campobasso, Italy; (M.C.B.)
| |
Collapse
|
2
|
Paydar S, Dalfardi B, Zangbar-Sabegh B, Heidaripour H, Pourandi L, Shakibafard A, Tahmtan M, Shayan L, Niakan MH. The Predictive Value of Repeated Abdominal Ultrasonography in Patients with Multiple Trauma and Decreased Level of Consciousness: The Experience of a Resource-Limited Centre. Bull Emerg Trauma 2018; 6:26-30. [PMID: 29379806 DOI: 10.29252/beat-060104] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/31/2022] Open
Abstract
Objective To determine the predictive value of repeated abdominal ultrasonography in patients with multiple trauma and decreased level of consciousness (LOC). Methods This prospective cross-sectional study was conducted over a six-month period at Shahid Rajaee Trauma Hospital, Shiraz, Iran. We included hemodynamically stable blunt abdominal trauma patients with a decreased LOC (Glasgow Coma Scale ≤ 13) who were referred to the neurosurgery ICU ward. Included cases underwent 1 contrast-enhanced CT scan and two-time ultrasonographic study of the abdomen with an interval of 48 hours. The diagnostic accuracy of the ultrasonography was determined according to the CT-scan results. Results Overall 80 patients with mean age of 37.75 ± 18.67 years were included. There were 17 (21.3%) women and 63 (78.8%) men among the patients. Compared with the CT-Scan, the first ultrasonography showed a sensitivity of 60%, specificity of 80%, PPV of 16.60%, NPV of 96.80%, and a diagnostic accuracy of 70%. The same values for the second ultrasonographic study were 80%, 79%, 20%, 98%, and 79%, respectively. In 4 (5%) patients whose first ultrasonography and CT scan results were negative, the second ultrasonography was positive for injury. Conclusion In patients with blunt trauma to the abdomen, when the only indication of abdominal CT scan is a decreased LOC, two ultrasonographic studies can replace a CT imaging.
Collapse
Affiliation(s)
- Shahram Paydar
- Trauma Research Center, Shahid Rajaee (Emtiaz) Trauma Hospital, Shiraz University of Medical Sciences, Shiraz, Iran.,Department of General Surgery, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Behnam Dalfardi
- Student Research Committee, Shiraz University of Medical Sciences, Shiraz, Iran.,Department of Internal Medicine, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Bardia Zangbar-Sabegh
- Division of Trauma, Critical Care, Burns, and Emergency Surgery, Department of Surgery, University of Arizona, Tucson, Arizona
| | - Hossein Heidaripour
- Trauma Research Center, Shahid Rajaee (Emtiaz) Trauma Hospital, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Leila Pourandi
- Trauma Research Center, Shahid Rajaee (Emtiaz) Trauma Hospital, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Alireza Shakibafard
- Trauma Research Center, Shahid Rajaee (Emtiaz) Trauma Hospital, Shiraz University of Medical Sciences, Shiraz, Iran.,Department of Radiology, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Mehdi Tahmtan
- Trauma Research Center, Shahid Rajaee (Emtiaz) Trauma Hospital, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Leila Shayan
- Trauma Research Center, Shahid Rajaee (Emtiaz) Trauma Hospital, Shiraz University of Medical Sciences, Shiraz, Iran
| | - Mohammad Hadi Niakan
- Trauma Research Center, Shahid Rajaee (Emtiaz) Trauma Hospital, Shiraz University of Medical Sciences, Shiraz, Iran.,Department of General Surgery, Shiraz University of Medical Sciences, Shiraz, Iran
| |
Collapse
|
3
|
Juo YY, Quach C, Hiatt J, Hines OJ, Tillou A, Burruss S. Comparative Analysis of Simulated versus Live Patient-Based FAST (Focused Assessment With Sonography for Trauma) Training. JOURNAL OF SURGICAL EDUCATION 2017; 74:1012-1018. [PMID: 28457876 DOI: 10.1016/j.jsurg.2017.04.001] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/16/2016] [Revised: 03/30/2017] [Accepted: 04/03/2017] [Indexed: 06/07/2023]
Abstract
OBJECTIVE To investigate whether simulated patient (SP)-based training has comparable efficacy as live patient (LP)-based training in teaching Focused Abdominal Sonography for Trauma (FAST) knowledge and skill competencies to surgical residents. DESIGN A randomized pretest/intervention/posttest controlled study design was employed to compare the participants' performance in written and practical examinations regarding FAST examination after SP-based versus LP-based training. SETTING University-based general residency program at a single institution. PARTICIPANTS A total of 29 general surgery residents of various training levels and sonographic experience were recruited by convenience sampling. RESULTS There was no correlation between subjects' baseline training level or sonographic experience with either the posttest-pretest score difference or the percentage of subjects getting all 4 windows with adequate quality. There was no significant difference between the improvement in written posttest-pretest scores for SP and LP group, which were 33 ± 9.6 and 31 ± 6.8 (p = 0.40), respectively. With regard to performance-based learning efficacy, a statistically higher proportion of subjects were able to obtain all 4 windows with adequate quality among the LP than the SP group (6/8 vs 1/8, p = 0.01). CONCLUSION SP- and LP-based FAST training for surgical residents were associated with similar knowledge-based competency acquisition, but residents receiving LP-based training were better at acquiring adequate FAST windows on live patients. Simulation training appeared to be a valid adjunct to LP practice but cannot replace LP training. Future investigations on how to improve simulation fidelity and its training efficacy for skill-based competencies are warranted.
Collapse
Affiliation(s)
- Yen-Yi Juo
- Department of Surgery, David Geffen School of Medicine at the University of California, Los Angeles, California; Center for Advanced Surgical and Interventional Technology, University of California, Los Angeles, California
| | - Chi Quach
- Department of Surgery, David Geffen School of Medicine at the University of California, Los Angeles, California
| | - Jonathan Hiatt
- Department of Surgery, David Geffen School of Medicine at the University of California, Los Angeles, California
| | - O Joe Hines
- Department of Surgery, David Geffen School of Medicine at the University of California, Los Angeles, California
| | - Areti Tillou
- Department of Surgery, David Geffen School of Medicine at the University of California, Los Angeles, California.
| | - Sigrid Burruss
- Department of Surgery, Loma Linda University Medical Center, Loma Linda, California
| |
Collapse
|
4
|
Dubois L, Leslie K, Parry N. FACTS survey: focused assessment with sonography in trauma use among Canadian residents training in general surgery. ACTA ACUST UNITED AC 2010; 69:765-9. [PMID: 20938264 DOI: 10.1097/ta.0b013e3181edbea0] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
BACKGROUND A survey of all Canadian residents training in general surgery was conducted to determine the prevalence and nature of focused assessment with sonography in trauma (FAST) training. METHODS A cross-sectional survey of all 549 residents in 16 Canadian general surgery programs was administered using the Tailored Design Method between December 2008 and February 2009. RESULTS With a response rate of 58.5% (321 of 549), the prevalence of FAST training among Canadian residents was 21.2% (95% confidence interval: 17.2-25.2). The median number of practice and patient examinations completed was 5 (interquartile range [IQR]: 2-10.5) and 11.5 (IQR: 1.75-50), respectively. Only 38.8% of residents with training felt comfortable making treatment decisions based on their FAST examinations. Those residents who were comfortable had completed more practice and patient examinations (median, 12.5 vs. 4, p = 0.001 and 30 vs. 4.5, p ≤ 0.001, respectively) and were less likely to have didactic only training (7.7% vs. 19.5%, p = 0.002). Most residents (80%) indicated that they would need 20 practice examinations or more (median, 30 examinations; IQR, 20-40) before they would feel comfortable. Residents with FAST training were more likely to be from a program that offered FAST training (54.5% vs. 10%, p ≤ 0.001) and were less likely to perceive a turf war with other specialties over FAST use (29.9% vs. 48.2%, p = 0.007). CONCLUSIONS The situation with FAST training in Canada seems inadequate with few general surgery residents being trained, and of those trained, only a few are comfortable with the technique. If FAST skills are to be expected of future surgeons, initiatives must be put in place to address barriers and improve training opportunities.
Collapse
Affiliation(s)
- Luc Dubois
- Division of General Surgery, Department of Surgery, The Schulich School of Medicine and Dentistry, The University of Western Ontario, London, Ontario, Canada.
| | | | | |
Collapse
|
5
|
Melniker LA. The value of focused assessment with sonography in trauma examination for the need for operative intervention in blunt torso trauma: a rebuttal to “emergency ultrasound-based algorithms for diagnosing blunt abdominal trauma (review)”, from the Cochrane Collaboration. Crit Ultrasound J 2009. [DOI: 10.1007/s13089-009-0014-7] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022] Open
Abstract
Abstract
Background and significance
The Cochrane Database of Systematic Reviews published a manuscript critical of the use of the FAST examination. The reference is Stengel D. Bauwens K. Sehouli J. Rademacher G. Mutze S. Ekkernkamp A. Porzsolt F. Emergency ultrasound-based algorithms for diagnosing blunt abdominal trauma. Cochrane Database of Systematic Reviews. (2):CD004446, 2005. UI: 15846717. The stated objective was the assessment of the “efficiency and effectiveness” of ultrasound-inclusive evaluative algorithms in patients with suspected blunt abdominal trauma (BAT). The primary outcome measures explored were Mortality, CT and DPL use, and laparotomy rates. Little or no benefit was seen and the conclusion was that “there is insufficient evidence from randomized controlled trials to justify promotion” of FAST in patients with BAT. While the review used the same rigorous methods employed in all Cochrane Reviews, it appears that several serious flaws plagued the manuscript. The finest methodological rigor cannot yield usable results, if it is not applied to a clinically relevant question. In a world of increasingly conservative management of BAT, do we need FAST, a rapid, repeatable screening modality at the point-of-care to visualize any amount of free fluid or any degree of organ injury? The obvious answer is no. However, quantifying the value of FAST to predict the need for immediate operative intervention (OR) is essential.
Methods
To rebut this recurrent review, a systematic literature review was conducted using verbatim methodologies as described in the Cochrane Review with the exception of telephone contacts. Data were tabulated and presented descriptively.
Results
Out of 487 citations, 163 articles were fully screened, 11 contained prospectively derived data with FAST results, patient disposition and final diagnoses, and a description of cases considered false negatives or false positives. Of the 2,755 patients, 448 (16%) went to the OR. There were a total of 5 patients with legitimately false-negative diagnoses made based on the FAST: 3 involving inadequate scans and 2 of blunt trauma-induced small bowel perforations without hemoperitoneum.
Conclusion
The FAST examination, adequately completed, is a nearly perfect test for predicting a “Need for OR” in patients with blunt torso trauma.
Collapse
|
6
|
Diagnostic Peritoneal Lavage Remains a Valuable Adjunct to Modern Imaging Techniques. ACTA ACUST UNITED AC 2009; 67:330-4; discussion 334-6. [DOI: 10.1097/ta.0b013e3181ae9b1d] [Citation(s) in RCA: 12] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
7
|
Christie-Large M, Michaelides D, James SLJ. Focused assessment with sonography for trauma: the FAST scan. TRAUMA-ENGLAND 2008. [DOI: 10.1177/1460408608090919] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Focused assessment with sonography for trauma or focused abdominal sonography for trauma — the FAST scan, has become a useful modality for the initial evaluation of patients with blunt abdominal trauma. The technique is used to identify free fluid in the abdomen and pelvis and to detect the presence of a pericardial effusion. FAST can be performed by any trained individual, not necessarily a sonographer or radiologist, aiding in the immediate availability of this technique in the emergency situation. We will discuss the applications and sensitivity of this technique in trauma and review the potential pitfalls and limitations which need to be understood if this technique is to be safely applied. The use of FAST for the detection of pneumothoraces in trauma and other advances in FAST scanning, such as scoring systems and paediatric FAST are also reviewed.
Collapse
Affiliation(s)
- M. Christie-Large
- Department of Radiology, The Royal Orthopaedic Hospital Foundation Trust, Bristol Road South, Northfield, Birmingham, B31 2AP, UK,
| | - D. Michaelides
- Department of Radiology, University Hospital Birmingham NHS Foundation Trust, Selly Oak Hospital, Raddlebarn Road, Birmingham, B29 6JD, UK
| | - SLJ James
- Department of Radiology, The Royal Orthopaedic Hospital Foundation Trust, Bristol Road South, Northfield, Birmingham, B31 2AP, UK, Department of Radiology, University Hospital Birmingham NHS Foundation Trust, Selly Oak Hospital, Raddlebarn Road, Birmingham, B29 6JD, UK
| |
Collapse
|