Andrew T Hale

Dr. Andrew T Hale


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2018 in Neurosurgical Focus
Verified
Journal Article
Open access
PDF file
AHAndrew T Hale
Andrew T Hale
DSDavid P. Stonko
David P. Stonko
ABAmber Brown
Amber Brown
JLJaims Lim
Jaims Lim
DVDavid J. Voce
David J. Voce
CSChevis N. Shannon
Chevis N. Shannon
OBJECTIVE: Modern surgical planning and prognostication requires the most accurate outcomes data to practice evidence-based medicine. For clinicians treating children following traumatic brain injury (TBI) these data are severely lacking. The first aim of this study was to assess published CT classification systems in the authors’ pediatric cohort. A pediatric-specific machine-learning algorithm called an artificial neural network (ANN) was then created that robustly outperformed traditional CT classification systems in predicting TBI outcomes in children. METHODS: The clinical records of children under the age of 18 who suffered a TBI and underwent head CT within 24 hours after TBI (n = 565) were retrospectively reviewed. RESULTS: “Favorable” outcome (alive with Glasgow Outcome Scale [GOS] score ≥ 4 at 6 months postinjury, n = 533) and “unfavorable” outcome (death at 6 months or GOS score ≤ 3 at 6 months postinjury, n = 32) were used as the primary outcomes. The area under the receiver operating characteristic (ROC) curve (AUC) was used to delineate the strength of each CT grading system in predicting survival (Helsinki, 0.814; Rotterdam, 0.838; and Marshall, 0.781). The AUC for CT score in predicting GOS score ≤ 3, a measure of overall functionality, was similarly predictive (Helsinki, 0.717; Rotterdam, 0.748; and Marshall, 0.663). An ANN was then constructed that was able to predict 6-month outcomes with profound accuracy (AUC = 0.9462 ± 0.0422). CONCLUSIONS: This study showed that machine-learning can be leveraged to more accurately predict TBI outcomes in children.

1 February 2018 in Journal of Clinical Neuroscience
Verified
Journal Article
Closed access
AHAndrew T Hale
Andrew T Hale
LWLi Wang
Li Wang
MSMegan K. Strother
Megan K. Strother
LCLola B. Chambless
Lola B. Chambless

5 November 2018 in Neurosurgical Review
Verified
Journal Article
Closed access
PDF file
AHAndrew T Hale
Andrew T Hale
MMMeredith A. Monsour
Meredith A. Monsour
John RolstonJohn Rolston
John Rolston
RNRobert P. Naftel
Robert P. Naftel
DEDario J. Englot
Dario J. Englot

1 November 2018 in Neurosurgical Focus
Verified
Journal Article
Open access
PDF file
AHAndrew T Hale
Andrew T Hale
DSDavid P. Stonko
David P. Stonko
LWLi Wang
Li Wang
MSMegan K. Strother
Megan K. Strother
LCLola B. Chambless
Lola B. Chambless
OBJECTIVE: Prognostication and surgical planning for WHO grade I versus grade II meningioma requires thoughtful decision-making based on radiographic evidence, among other factors. Although conventional statistical models such as logistic regression are useful, machine learning (ML) algorithms are often more predictive, have higher discriminative ability, and can learn from new data. The authors used conventional statistical models and an array of ML algorithms to predict atypical meningioma based on radiologist-interpreted preoperative MRI findings. The goal of this study was to compare the performance of ML algorithms to standard statistical methods when predicting meningioma grade. METHODS: The cohort included patients aged 18–65 years with WHO grade I (n = 94) and II (n = 34) meningioma in whom preoperative MRI was obtained between 1998 and 2010. A board-certified neuroradiologist, blinded to histological grade, interpreted all MR images for tumor volume, degree of peritumoral edema, presence of necrosis, tumor location, presence of a draining vein, and patient sex. The authors trained and validated several binary classifiers: k -nearest neighbors models, support vector machines, naïve Bayes classifiers, and artificial neural networks as well as logistic regression models to predict tumor grade. The area under the curve–receiver operating characteristic curve was used for comparison across and within model classes. All analyses were performed in MATLAB using a MacBook Pro. RESULTS: The authors included 6 preoperative imaging and demographic variables: tumor volume, degree of peritumoral edema, presence of necrosis, tumor location, patient sex, and presence of a draining vein to construct the models. The artificial neural networks outperformed all other ML models across the true-positive versus false-positive (receiver operating characteristic) space (area under curve = 0.8895). CONCLUSIONS: ML algorithms are powerful computational tools that can predict meningioma grade with great accuracy.

19 March 2019 in Neurosurgery
Verified
Journal Article
Closed access
PDF file
AHAndrew T Hale
Andrew T Hale
SSSonali Sen
Sonali Sen
AHAli S Haider
Ali S Haider
FPFreedom F Perkins
Freedom F Perkins
DCDave F Clarke
Dave F Clarke
LTLuke D Tomycz
Luke D Tomycz
BACKGROUND: Various studies suggest that the insular cortex may play an underappreciated role in pediatric frontotemporal/parietal epilepsy. Here, we report on the postsurgical outcomes in 26 pediatric patients with confirmed insular involvement by depth electrode monitoring. OBJECTIVE: To describe one of the largest series of pediatric patients with medically refractory epilepsy undergoing laser interstitial thermal therapy (LITT) or surgical resection of at least some portion of the insular cortex. METHODS: Pediatric patients in whom invasive insular sampling confirmed insular involvement and who subsequently underwent a second stage surgery (LITT or open resection) were included. Complications and Engel Class outcomes at least 1 yr postsurgery were compiled as well as pathology results in the open surgical cases. RESULTS: The average age in our cohort was 10.3 yr, 58% were male, and the average length of follow-up was 2.43 ± 0.20 (SEM) yr. A total of 14 patients underwent LITT, whereas 12 patients underwent open resection. Complications in patients undergoing either LITT or open resection were mostly minimal and generally transient. Forty-three percent of patients who underwent LITT were Engel Class I, compared to 50% of patients who underwent open insular resection. CONCLUSION: Both surgical resection and LITT are valid management options in the treatment of medically refractory insular/opercular epilepsy in children. Although LITT may be a less invasive alternative to craniotomy, further studies are needed to determine its noninferiority in terms of complication rates and seizure freedom, especially in cases of cortical dysplasia that may involve extensive regions of the brain.

1 May 2021 in Cell Reports
Verified
Journal Article
Open access
AHAndrew T Hale
Andrew T Hale
LBLisa Bastarache
Lisa Bastarache
DMDiego M. Morales
Diego M. Morales
JWJohn C. Wellons
John C. Wellons
DLDavid D. Limbrick
David D. Limbrick
EGEric Gamazon
Eric Gamazon
We conducted PrediXcan analysis of hydrocephalus risk in ten neurological tissues and whole blood. Decreased expression of MAEL in the brain was significantly associated (Bonferroni-adjusted p < 0.05) with hydrocephalus. PrediXcan analysis of brain imaging and genomics data in the independent UK Biobank (N = 8,428) revealed that MAEL expression in the frontal cortex is associated with white matter and total brain volumes. Among the top differentially expressed genes in brain, we observed a significant enrichment for gene-level associations with these structural phenotypes, suggesting an effect on disease risk through regulation of brain structure and integrity. We found additional support for these genes through analysis of the choroid plexus transcriptome of a murine model of hydrocephalus. Finally, differential protein expression analysis in patient cerebrospinal fluid recapitulated disease-associated expression changes in neurological tissues, but not in whole blood. Our findings provide convergent evidence highlighting the importance of tissue-specific pathways and mechanisms in the pathophysiology of hydrocephalus.