Marc graduated with a Doctor of Medicine degree from the Lebanese American University, where he consistently strived to bridge the gap between healthcare and data science, focusing on the intersection of artificial intelligence, machine learning, and medical science to develop solutions for optimizing patient care.
Currently, Marc is a Postdoctoral Research Scholar at Stanford University. His work revolves around the application of machine learning to analyze biological and clinical data in a translational setting. Prior to that, Marc was a Research Scholar Collaborator at the Mayo Clinic's Neuro-Informatics Lab. There, he made significant contributions to outcome prediction using machine learning and deep learning models trained on national datasets.
Honors & Awards
Best Capstone Project, Lebanese American University (05/2019)
Mayo Clinic Neuro-Informatics Research Collaboration Award, Mayo Clinic Neuro-Informatics Lab (07/2021)
Excellence in Innovation Award, Lebanese American University (05/2023)
Outstanding Researcher Award, Lebanese American University (05/2023)
Nima Aghaeepour, Postdoctoral Faculty Sponsor
Current Research and Scholarly Interests
Data-driven healthcare and AI research in a translational setting.
Safety and efficacy of the pipeline embolization device for treatment of small vs. large aneurysms: a systematic review and meta-analysis.
2023; 46 (1): 284
Flow diversion with the pipeline embolization device (PED) is increasingly used to treat intracranial aneurysms with high obliteration rates and low morbidity. However, long-term (≥ 1 year) angiographic and clinical outcomes still require further investigation. The aim of this study was to compare the occlusion and complication rates for small (< 10 mm) versus large (10-25 mm) aneurysms at long-term following treatment with PED. A systematic review and meta-analysis were performed in compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses. We conducted a comprehensive search of English language databases including Ovid MEDLINE and Epub Ahead of Print, In-Process, and Daily, Ovid EMBASE, Ovid Cochrane Central Register of Controlled Trials, Ovid Cochrane Database of Systematic Reviews, and Scopus. Our studies included a minimum of 10 patients treated with PED for small vs. large aneurysms and with at least 12 months of follow-up. The primary safety endpoint was the rate of clinical complications measured by the occurrence of symptomatic stroke (confirmed clinically and radiographically), intracranial hemorrhage, or aneurysmal rupture. The primary efficacy endpoint was the complete aneurysm occlusion rate. Our analysis included 19 studies with 1277 patients and 1493 aneurysms. Of those, 1378 aneurysms met our inclusion criteria. The mean age was 53.9 years, and most aneurysms were small (89.75%; N = 1340) in women (79.1%; N = 1010). The long-term occlusion rate was 73% (95%, CI 65 to 80%) in small compared to 84% (95%, CI 76 to 90%) in large aneurysms (p < 0.01). The symptomatic thromboembolic complication rate was 5% (95%, CI 3 to 9%) in small compared to 7% (95%, CI 4 to 13%) in large aneurysms (p = 0.01). The rupture rate was 2% vs. 4% (p = 0.92), and the rate of intracranial hemorrhage was 2% vs. 4% (p = 0.96) for small vs. large aneurysms, respectively; however, these differences were not statistically significant. The long-term occlusion rate after PED treatment is higher in large vs. small aneurysms. Symptomatic thromboembolic rates with stroke are also higher in large vs. small aneurysms. The difference in the rates of aneurysm rupture and intracranial hemorrhage was insignificant. Although the PED seems a safe and effective treatment for small and large aneurysms, further studies are required to clarify how occlusion rate and morbidity are affected by aneurysm size.
View details for DOI 10.1007/s10143-023-02192-0
View details for PubMedID 37882896
View details for PubMedCentralID 7964968
Surgical management of malignant melanotic nerve sheath tumors: an institutional experience and systematic review of the literature.
Journal of neurosurgery. Spine
Malignant melanotic nerve sheath tumors are rare tumors characterized by neoplastic melanin-producing Schwann cells. In this study, the authors report their institution's experience in treating spinal and peripheral malignant melanotic nerve sheath tumors and compare their results with the literature.Data were collected from 8 patients who underwent surgical treatment for malignant melanotic nerve sheath tumors between 1996 and 2023 at Mayo Clinic and 63 patients from the literature. Time-to-event analyses were performed for the combined group of 71 cases to evaluate the risk of recurrence, metastasis, and death based on tumor location and type of treatment received. Unpaired 2-sample t-tests and Fisher's exact tests were used to determine statistical significance between groups.Between 1996 and 2023, 8 patients with malignant melanotic nerve sheath tumors underwent surgery at the authors' institution, while 63 patients were identified in the literature. The authors' patients and those in the literature had the same mean age at diagnosis (43 years). At the authors' institution, 5 patients (63%) experienced metastasis, 6 patients (75%) experienced long-term recurrence, and 5 patients (62.5%) died. In the literature, most patients (60.3%) were males, with a peak incidence between the 4th and 5th decades of life. Nineteen patients (31.1%) were diagnosed with Carney complex. Nerve root tumors accounted for most presentations (n = 39, 61.9%). Moreover, 24 patients (38.1%) had intradural lesions, with 54.2% (n = 13) being intramedullary and 45.8% (n = 11) extramedullary. Most patients underwent gross-total resection (GTR) (n = 41, 66.1%), followed by subtotal resection (STR) (n = 12, 19.4%), STR with radiation therapy (9.7%), and GTR with radiation therapy (4.8%). Sixteen patients (27.6%) experienced metastasis, 23 (39.7%) experienced recurrence, and 13 (22%) died. Kaplan-Meier analyses showed no significant differences among treatment approaches in terms of recurrence-free, metastasis-free, and overall survival (p > 0.05). Similar results were obtained when looking at the differences with respect to intradural versus nerve root location of the tumor (p > 0.05).Malignant melanotic nerve sheath tumors are rare tumors with a high potential for malignancy. They carry a dismal prognosis, with a pooled local recurrence rate of 42%, distant metastasis rate of 27%, and mortality rate of 26%. The findings from this study suggest a trend favoring the use of GTR alone or STR with radiation therapy over STR alone. Mortality was similar regardless, which highlights the need for the development of effective treatment options to improve survival in patients with melanotic schwannomas.
View details for DOI 10.3171/2023.8.SPINE23427
View details for PubMedID 37862711
General Versus Nongeneral Anesthesia for Spinal Surgery: A Comparative National Analysis of Reimbursement Trends Over 10 Years.
Nongeneral anesthesia (non-GA) spine surgery is growing in popularity and has facilitated earlier postoperative recovery, reduced cost, and fewer complications compared with spine surgery under general anesthesia (GA). Changes in reimbursement policies have been demonstrated to correlate with clinical practice; however, they have yet to be studied for GA vs non-GA spine procedures. We aimed to investigate trends in physician reimbursement for GA vs non-GA spine surgery in the United States.We queried the ACS-NSQIP for GA and non-GA (regional, epidural, spinal, and anesthesia care/intravenous sedation) spine surgeries during 2011-2020. Work relative value units per operative hour (wRVUs/h) were retrieved for decompression or stabilization of the cervical, thoracic, and lumbar spine. Propensity score matching (1:1) was performed using all baseline variables.We included 474 706 patients who underwent spine decompression or stabilization procedures. GA was used in 472 248 operations, whereas 2458 operations were non-GA. The proportion of non-GA spine operations significantly increased during the study period. Operative times (P < .001) and length of stays (P < .001) were shorter in non-GA when compared with GA procedures. Non-GA lumbar procedures had significantly higher wRVUs/h when compared with the same procedures performed under GA (decompression; P < .001 and stabilization; P = .039). However, the same could not be said about cervicothoracic procedures. Lumbar decompression surgeries using non-GA witnessed significant yearly increase in wRVUs/h (P < .01) contrary to GA (P = .72). Physician reimbursement remained stable for procedures of the cervical or thoracic spine regardless of the anesthesia.Non-GA lumbar decompressions and stabilizations are associated with higher and increasing reimbursement trends (wRVUs/h) compared with those under GA. Reimbursement for cervical and thoracic surgeries was equal regardless of the type of anesthesia and being relatively stable during the study period. The adoption of a non-GA technique relative to the GA increased significantly during the study period.
View details for DOI 10.1227/neu.0000000000002670
View details for PubMedID 37856210
The Rate and Predictors of 30-Day Readmission in Patients Treated for Unruptured Cerebral Aneurysms: A Large Single-Center Study.
Numerous studies of various populations and diseases have shown that unplanned 30-day readmission rates are positively correlated with increased morbidity and all-cause mortality. In this study, we aim to provide the rate and predictors of 30-day readmission in patients undergoing treatment for unruptured intracranial aneurysms.This is a retrospective study of 525 patients presenting for aneurysm treatment between 2017 and 2022. All patients who were admitted and underwent a successful treatment of their unruptured intracerebral aneurysms were included in the study. The primary outcome was the rate and predictors of 30-day readmission.The rate of 30-day readmission was 6.3%, and the mean duration to readmission was 7.8 days ± 6.9. On univariate analysis, factors associated with 30-day readmission were antiplatelet use on admission (odds ratio [OR]: 0.4, P = .009), hemorrhagic rupture (OR: 15.8, P = .007), surgical treatment of aneurysms (OR: 2.2, P = .035), disposition to rehabilitation (OR: 9.5, P < .001), and increasing length of stay (OR: 1.1, P = .0008). On multivariate analysis, antiplatelet use on admission was inversely correlated with readmission (OR: 0.4, P = .045), whereas hemorrhagic rupture (OR: 9.5, P = .04) and discharge to rehabilitation (OR: 4.5, P = .029) were independent predictors of 30-day readmission.In our study, risk factors for 30-day readmission were aneurysm rupture during the hospital stay and disposition to rehabilitation, whereas the use of antiplatelet on admission was inversely correlated with 30-day readmission. Although aneurysm rupture is a nonmodifiable risk factor, more studies are encouraged to focus on the correlation of antiplatelet use and rehabilitation disposition with 30-day readmission rates.
View details for DOI 10.1227/neu.0000000000002663
View details for PubMedID 37681971
Transverse Venous Stenting for the Treatment of Idiopathic Intracranial Hypertension With a Pressure Gradient of 70 mm Hg: A Technical Note and Systematic Review.
Operative neurosurgery (Hagerstown, Md.)
BACKGROUND AND IMPORTANCE: Venous sinus stenosis is believed to play a role in the pathogenesis of idiopathic intracranial hypertension (IIH). Venous stenting has emerged as a promising treatment option for patients with IIH because of venous sinus stenosis refractory to medical management or unsuitable for shunt placement. In this technical note, we present a case of IIH with the highest recorded pressure gradient to date.CLINICAL PRESENTATION: This technical note presents the successful use of intracranial venous stenting in a patient with IIH because of severe venous sinus stenosis, leading to significant improvement in vision and reduction in intracranial pressure. A meticulous review of the literature revealed that our patient exhibited the highest recorded pressure gradient (70 cm of H2O). This remarkable finding underscores the potential effectiveness of venous stenting as a viable treatment approach. The procedure involved the placement of a Zilver stent (Cook Medical) and balloon angioplasty after stenting of the right transverse sinus stenosis, resulting in a substantial decrease in pressure gradient. Following the procedure, another venous manometry showed no more gradient with a uniform pressure in the whole venous system at 18 cm of H2O.CONCLUSION: To our knowledge, this case presents the highest pressure gradient reported in the literature and contributes to the growing evidence supporting venous stenting in patients with IIH and venous sinus stenosis.
View details for DOI 10.1227/ons.0000000000000858
View details for PubMedID 37589472
Predictors of Transfemoral Access Site Complications in Neuroendovascular Procedures: A large Single-Center Cohort Study.
Clinical neurology and neurosurgery
2023; 233: 107916
The transfemoral (TF) route has historically been the preferred access site for endovascular procedures. However, despite its widespread use, TF procedures may confer morbidity as a result of access site complications. The aim of this study is to provide the rate and predictors of TF access site complications for neuroendovascular procedures.This is a single center retrospective study of TF neuroendovascular procedures performed between 2017 and 2022. The incidence of complications and associated risk factors were analyzed across a large cohort of patients.The study comprised of 2043 patients undergoing transfemoral neuroendovascular procedures. The composite rate of access site complications was 8.6 % (n = 176). These complications were divided into groin hematoma formation (n = 118, 5.78 %), retroperitoneal hematoma (n = 14, 0.69 %), pseudoaneurysm formation (n = 40, 1.96 %), and femoral artery occlusion (n = 4, 0.19 %). The cross-over to trans radial access rate was 1.1 % (n = 22). On univariate analysis, increasing age (OR=1.0, p = 0.06) coronary artery disease (OR=1.7, p = 0.05) peripheral vascular disease (OR=1.9, p = 0.07), emergent mechanical thrombectomy procedures (OR=2.1, p < 0.001) and increasing sheath size (OR=1.3, p < 0.001) were associated with higher TF access site complications. On multivariate analysis, larger sheath size was an independent risk factor for TF access site complications (OR=1.8, p = 0.02).Several pertinent factors contribute towards the incidence of TF access site complications. Factors associated with TF access site complications include patient demographics (older age) and clinical risk factors (vascular disease), as well as periprocedural factors (sheath size).
View details for DOI 10.1016/j.clineuro.2023.107916
View details for PubMedID 37651797
Effect of race, sex, and socioeconomic factors on overall survival following the resection of intramedullary spinal cord tumors.
Journal of neuro-oncology
INTRODUCTION: Intramedullary spinal cord tumors (IMSCTs) account for 2-4% of all primary CNS tumors. Given their low prevalence and the intricacy of their diagnosis and management, it is critical to address the surrounding racial and socioeconomic factors that impact the care of patients with IMSCTs. This study aimed to investigate the association between race and socioeconomic factors with overall 5year mortality following the resection of IMSCTs.METHODS: The study used the National Cancer Database to retrospectively analyze patients who underwent resection of IMSCTs from 2004 to 2017. Patients were divided into four cohorts by race/ethnicity, facility type, insurance, median income quartiles, and living area. The primary outcome of interest was 5year survival, and secondary outcomes included postoperative length of stay and 30day readmission. Descriptive and multivariable analyses were used to identify independent factors associated with mortality, with statistical significance assessed at a 2-sided p<0.05.RESULTS: We evaluated the patient characteristics and outcomes for 8,028 patients who underwent surgical treatment for IMSCTs between 2004 and 2017. Most patients were white males (52.4%) with a mean age of 44 years where 7.17% of patients were Black, 7.6% were Hispanic, and 3% were Asian. Most were treated in an academic/research program (72.4%) and had private insurance (69.2%). Black patients had a higher odd of 5year mortality (OR 1.4; 95% CI 1.1 to 1.77; p=0.04) compared to white patients, while no significant differences in mortality were observed among other races. Factors associated with lower odds of mortality included being female (OR 0.89; 95% CI 0.78 to 1.02; p<0.01), receiving treatment in an academic/research program (OR 0.51; 95% CI 0.33 to 0.79; p=0.04), having private insurance (OR 0.65; 95% CI 0.45 to 0.93; p=0.02), and having higher income quartiles (OR 0.77; 95% CI 0.62 to 0.96; p=0.02).CONCLUSION: Our study sheds light on the healthcare disparities that exist in the surgical management of IMSCTs. Our findings indicate that race, sex, socioeconomic status, and treatment facility are independent predictors of 5year mortality, with Black patients, males, those with lower socioeconomic status, and those treated at non-academic centers experiencing significantly higher mortality rates. These alarming disparities underscore the urgent need for policymakers and researchers to address the underlying factors contributing to these discrepancies and provide equal access to high-quality surgical care for patients with IMSCTs.
View details for DOI 10.1007/s11060-023-04373-9
View details for PubMedID 37479956
Resuming Anticoagulants in Patients With Intracranial Hemorrhage: A Meta-Analysis and Literature Review.
Intracerebral hemorrhage (ICH) is one of the most disabling cerebrovascular events. Several studies have discussed oral anticoagulant (OAC)-related ICH; however, the optimal timing of resuming OAC in patients with ICH is still a dilemma. In this literature review/meta-analysis, we will summarize, discuss, and provide the results of studies pertaining to OAC resumption in patients with ICH.Using PubMed, Ovid Medline, and Web science, a systemic literature review was performed in accordance with the Preferred Reporting Items for Systemic Reviews and Meta-Analyses statement on December 20, 2022. Inclusion criteria for the meta-analysis were all studies reporting mean, median, and standard deviation for the duration of anticoagulants resumption after ICH. Thirteen studies met the above criteria and were included in the meta-analysis.Of the 271 articles found in the literature, pooled analysis was performed in 13 studies that included timing of OAC resumption after ICH. The pooled mean duration to OAC resumption after the index ICH was 31 days (95% CI: 13.7-48.3). There was significant variation among the mean duration to OAC resumption reported by the studies as observed in the heterogeneity test (P-value ≈0).Based on our meta-analysis, the average time of resuming OAC in patients with ICH is around 30 days. Several factors including the type of intracranial hemorrhage, the type of OAC, and the indication for OACs should be taken into consideration for future studies to try and identify the best time to resume OAC in patients with ICH.
View details for DOI 10.1227/neu.0000000000002625
View details for PubMedID 37459580
Deep Learning Approaches for Glioblastoma Prognosis in Resource-Limited Settings: A Study Using Basic Patient Demographic, Clinical, and Surgical Inputs.
2023; 175: e1089-e1109
Glioblastoma (GBM) is the most common brain tumor in the United States, with an annual incidence rate of 3.21 per 100,000. It is the most aggressive type of diffuse glioma and has a median survival of months after treatment. This study aims to assess the accuracy of different novel deep learning models trained on a set of simple clinical, demographic, and surgical variables to assist in clinical practice, even in areas with constrained health care infrastructure.Our study included 37,095 patients with GBM from the SEER (Surveillance Epidemiology and End Results) database. All predictors were based on demographic, clinicopathologic, and treatment information of the cases. Our outcomes of interest were months of survival and vital status. Concordance index (C-index) and integrated Brier scores (IBS) were used to evaluate the performance of the models.The patient characteristics and the statistical analyses were consistent with the epidemiologic literature. The models C-index and IBS ranged from 0.6743 to 0.6918 and from 0.0934 to 0.1034, respectively. Probabilistic matrix factorization (0.6918), multitask logistic regression (0.6916), and logistic hazard (0.6916) had the highest C-index scores. The models with the lowest IBS were the probabilistic matrix factorization (0.0934), multitask logistic regression (0.0935), and logistic hazard (0.0936). These models had an accuracy (1-IBS) of 90.66%; 90.65%, and 90.64%, respectively. The deep learning algorithms were deployed on an interactive Web-based tool for practical use available via https://glioblastoma-survanalysis.herokuapp.com/.Novel deep learning algorithms can better predict GBM prognosis than do baseline methods and can lead to more personalized patient care regardless of extensive electronic health record availability.
View details for DOI 10.1016/j.wneu.2023.04.072
View details for PubMedID 37088416
Using machine learning to predict 30-day readmission and reoperation following resection of supratentorial high-grade gliomas: an ACS NSQIP study involving 9418 patients.
2023; 54 (6): E12
OBJECTIVE: High-grade gliomas (HGGs) are among the rarest yet most aggressive tumor types in neurosurgical practice. In the current literature, few studies have assessed the drivers of early outcomes following resection of these tumors and investigated their association with quality of care. The authors aimed to identify the clinical predictors for 30-day readmission and reoperation following HGG surgery using the American College of Surgeons (ACS) National Surgical Quality Improvement Project (NSQIP) database and sought to create web-based applications predicting each outcome.METHODS: Using the ACS NSQIP database, the authors conducted a retrospective, multicenter cohort analysis of patients who underwent resection of supratentorial HGGs between January 1, 2016, and December 31, 2020. Demographics and comorbidities were extracted. The primary outcomes were 30-day unplanned readmission and reoperation. A stratified 80:20 split of the available data was carried out. Supervised machine learning algorithms were trained to predict 30-day outcomes.RESULTS: A total of 9418 patients were included in our cohort. The observed rate of unplanned readmission within 30 days of surgery was 13.0% (n = 1221). In terms of predictors, weight, chronic steroid use, preoperative blood urea nitrogen level, and white blood cell count were associated with a higher risk of readmission. The observed rate of unplanned reoperation within 30 days of surgery was 5.2% (n = 489). In terms of predictors, increased weight, longer operative time, and more days between hospital admission and operation were associated with an increased risk of early reoperation. The random forest algorithm showed the highest predictive performance for early readmission (area under the curve [AUC] = 0.967), while the XGBoost algorithm showed the highest predictive performance for early reoperation (AUC = 0.985). Web-based tools for both outcomes were deployed (https://glioma-readmission.herokuapp.com/ and https://glioma-reoperation.herokuapp.com/).CONCLUSIONS: In this study, the authors provide the first nationwide analysis for short-term outcomes in patients undergoing resection of supratentorial HGGs. Multiple patient, hospital, and admission factors were associated with readmission and reoperation, confirmed by machine learning predicting patients' prognosis, leading to better planning preoperatively and subsequently improved personalized patient care.
View details for DOI 10.3171/2023.3.FOCUS22652
View details for PubMedID 37552633
Transradial versus Transfemoral Approaches in Diagnostic and Therapeutic Neuroendovascular Interventions: A Meta-Analysis of Current Literature
2022; 164: E694-E705
The adoption of the transradial approach (TRA) has been increasing in popularity as a primary method to conduct both diagnostic and therapeutic interventions. As this technique gains broader acceptance and use within the neuroendovascular community, comparing its complication profile with a better-established alternative technique, the transfemoral approach (TFA), becomes more important. This study aimed to evaluate the safety of TRA compared with TFA in patients undergoing diagnostic, therapeutic, and combined neuroendovascular procedures.A systematic review and meta-analysis was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. A literature search of PubMed and other databases was conducted for studies from all available dates. To compare TRA and TFA, we performed an indirect meta-analysis between studies that mentioned the complications of the procedures.Our search yielded 532 studies, of which 108 met full inclusion criteria. A total of 54,083 patients (9137 undergoing TRA and 44,946 undergoing TFA) were included. Access site complication rate was lower in TRA (1.62%) compared with TFA (3.31%) (P < 0.01). Neurological complication rate was lower in TRA (1.64%) compared with TFA (3.82%) (P = 0.02 and P < 0.01, respectively). Vascular spasm rate was higher in TRA (3.65%) compared with TFA (0.88%) (P < 0.01). Wound infection complication rate was higher in TRA (0.32%) compared with TFA (0.2%) (P < 0.01).Patients undergoing TFA are significantly more likely to experience access site complications and neurological complications compared with patients undergoing TRA. Patients undergoing TRA are more likely to experience complications such as wound infections and vascular spasm.
View details for DOI 10.1016/j.wneu.2022.05.031
View details for Web of Science ID 000863280500002
View details for PubMedID 35580777