Ocular Injuries in Pediatric Patients Admitted With Abusive Head Trauma

Weiss, Rebecca; He, Catherine; Khan, Sabine; Parsikia, Afshin; Mbekeani, Joyce N.

doi:10.1016/j.pediatrneurol.2021.11.004

Cited by 9 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Subdural hematoma is the most frequent intracranial hemorrhage in AHT and has been highly correlated with RH in prior studies. 4,5,[24][25][26] Several authors Given that the results of 23% to 84% of retinal examinations conducted for abuse evaluation are positive for hemorrhages 3,5 and that retinal examinations should be performed within 48 hours of presentation before hemorrhages begin to resolve, 31 this technology could also offer timely decision support about who urgently needs a direct fundoscopic examination. In the near term, deep learning-assisted RH detection would not replace the fundoscopic examination, which remains the criterion standard of evidence for medical and legal evaluation.…”

Section: Discussionmentioning

confidence: 99%

“…When risk prediction from our deep learning model was added as a feature in our combined light GBM model, the presence of subdural hematoma contributed minimally. Subdural hematoma is the most frequent intracranial hemorrhage in AHT and has been highly correlated with RH in prior studies . Several authors have made an evidence-based argument for forgoing dilated retinal examinations in children without intracranial hemorrhage, even if physical abuse is suspected, which raises the question of why deep learning should be applied to this problem.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Development of a Deep Learning Model for Retinal Hemorrhage Detection on Head Computed Tomography in Young Children

Gunturkun,

Bakir-Batu,

Siddiqui

et al. 2023

JAMA Netw Open

View full text Add to dashboard Cite

ImportanceAbusive head trauma (AHT) in children is often missed in medical encounters, and retinal hemorrhage (RH) is considered strong evidence for AHT. Although head computed tomography (CT) is obtained routinely, all but exceptionally large RHs are undetectable on CT images in children.ObjectiveTo examine whether deep learning–based image analysis can detect RH on pediatric head CT.Design, Setting, and ParticipantsThis diagnostic study included 301 patients diagnosed with AHT who underwent head CT and dilated fundoscopic examinations at a quaternary care children’s hospital. The study assessed a deep learning model using axial slices from 218 segmented globes with RH and 384 globes without RH between May 1, 2007, and March 31, 2021. Two additional light gradient boosting machine (GBM) models were assessed: one that used demographic characteristics and common brain findings in AHT and another that combined the deep learning model’s risk prediction plus the same demographic characteristics and brain findings.Main Outcomes and MeasuresSensitivity (recall), specificity, precision, accuracy, F1 score, and area under the curve (AUC) for each model predicting the presence or absence of RH in globes were assessed. Globe regions that influenced the deep learning model predictions were visualized in saliency maps. The contributions of demographic and standard CT features were assessed by Shapley additive explanation.ResultsThe final study population included 301 patients (187 [62.1%] male; median [range] age, 4.6 [0.1-35.8] months). A total of 120 patients (39.9%) had RH on fundoscopic examinations. The deep learning model performed as follows: sensitivity, 79.6%; specificity, 79.2%; positive predictive value (precision), 68.6%; negative predictive value, 87.1%; accuracy, 79.3%; F1 score, 73.7%; and AUC, 0.83 (95% CI, 0.75-0.91). The AUCs were 0.80 (95% CI, 0.69-0.91) for the general light GBM model and 0.86 (95% CI, 0.79-0.93) for the combined light GBM model. Sensitivities of all models were similar, whereas the specificities of the deep learning and combined light GBM models were higher than those of the light GBM model.Conclusions and RelevanceThe findings of this diagnostic study indicate that a deep learning–based image analysis of globes on pediatric head CTs can predict the presence of RH. After prospective external validation, a deep learning model incorporated into CT image analysis software could calibrate clinical suspicion for AHT and provide decision support for which patients urgently need fundoscopic examinations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Development of a Deep Learning Model for Retinal Hemorrhage Detection on Head Computed Tomography in Young Children

Gunturkun,

Bakir-Batu,

Siddiqui

et al. 2023

JAMA Netw Open

View full text Add to dashboard Cite

show abstract

“…There are limited data on ocular injuries in the context of major trauma [6][7][8][9][10][16][17][18][19][20][21][22], and none of these studies have investigated changes over time within a defined population. The most recent UK-based study examining ocular trauma in this setting was almost 20 years ago [8], and little is known about current demographics and injury patterns.…”

Section: Introductionmentioning

confidence: 99%

Ocular injuries among patients with major trauma in England and Wales from 2004 to 2021

Bashir,

Bouamra,

Kirwan

et al. 2024

Eye

View full text Add to dashboard Cite

Background Ocular trauma is a significant cause of blindness and is often missed in polytrauma. No contemporary studies report eye injuries in the setting of severe trauma in the UK. We investigated ocular injury epidemiology and trends among patients suffering major trauma in England and Wales from 2004 to 2021. Methods We conducted a retrospective study utilising the Trauma Audit and Research Network (TARN) registry. Major trauma cases with concomitant eye injuries were included. Major trauma was defined as Injury Severity Score >15. Ocular injuries included globe, cranial nerve II, III, IV, and VI, and tear duct injuries. Orbital fractures and adnexal and lid injuries were not included. Demographics, injury profiles, and outcomes were extracted. We report descriptive statistics and 3-yearly trends. Results Of 287 267 major trauma cases, 2368 (0.82%) had ocular injuries: prevalence decreased from 1.87% to 0.66% over the 2004–2021 period (P < 0.0001). Males comprised 72.2% of ocular injury cases, median age was 34.5 years. The proportion of ocular injuries from road traffic collisions fell from 43.1% to 25.3% while fall-related injuries increased and predominated (37.6% in 2019/21). Concomitant head injury occurred in 86.6%. The most common site of ocular injury was the conjunctiva (29.3%). Compared to previous TARN data (1989–2004), retinal injuries were threefold more prevalent (5.9% vs 18.5%), while corneal injuries were less (31.0% vs 6.6%). Conclusions Whilst identifying eye injuries in major trauma is challenging, it appears ocular injury epidemiology in this setting has shifted, though overall prevalence is low. These findings may inform prevention strategies, guideline development and resource allocation.

show abstract

“…Wie korrekterweise geschrieben wird, wird heute in der englischsprachigen Literatur der Begriff des „Abusive Head Trauma“/AHT gegenüber dem STS bzw. „Shaken Baby Syndrome“/SBS favorisiert, um über das Schütteltrauma hinausgehende Gewalteinwirkungen mit zu erfassen 8 . Das „reine“ STS mit Netzhautblutungen spielt bei der Misshandlung insbesondere von Kindern im 1.…”

unclassified

“…Noch 2002 gaben 17% befragter Eltern an, dass eine „Tracht Prügel vertretbar“ sei 9 . Die erste Beschreibung einer KM soll auf Ambroise Tardieu und das Jahr 1860 zurückgehen, zitiert nach 8 . Über das Vorkommen von retinalen Blutungen bei KM soll J. Aikman 1928 berichtet haben, zitiert nach 22 .…”

unclassified

Immer noch Raum für Disput: zum STS und AHT (Abusive Head Trauma)

Rohrbach

2024

Klin Monbl Augenheilkd

View full text Add to dashboard Cite

Ocular Injuries in Pediatric Patients Admitted With Abusive Head Trauma

Cited by 9 publications

References 38 publications

Development of a Deep Learning Model for Retinal Hemorrhage Detection on Head Computed Tomography in Young Children

Development of a Deep Learning Model for Retinal Hemorrhage Detection on Head Computed Tomography in Young Children

Ocular injuries among patients with major trauma in England and Wales from 2004 to 2021

Immer noch Raum für Disput: zum STS und AHT (Abusive Head Trauma)

Contact Info

Product

Resources

About