Artificial intelligence in neurology: opportunities, challenges, and policy implications.

Neurological conditions are the leading cause of disability and mortality combined, demanding innovative, scalable, and sustainable solutions. Brain health has become a global priority with adoption of the World Health Organization's Intersectoral Global Action Plan in 2022. Simultaneously, rapid advancements in artificial intelligence (AI) are revolutionizing neurological research and practice. This scoping review of 66 original articles explores the value of AI in neurology and brain health, systematizing the landscape for emergent clinical opportunities and future trends across the care trajectory: prevention, risk stratification, early detection, diagnosis, management, and rehabilitation. AI's potential to advance personalized precision neurology and global brain health directives hinges on resolving core challenges across four pillars-models, data, feasibility/equity, and regulation/innovation-through concerted pursuit of targeted recommendations. Paramount actions include swift, ethical, equity-focused integration of novel technologies into clinical workflows, mitigating data-related issues, counteracting digital inequity gaps, and establishing robust governance frameworks balancing safety and innovation.

Long-Term Intracranial Outcomes With Combination Dual Immune-Checkpoint Blockade and Stereotactic Radiosurgery in Patients With Melanoma and Non-Small Cell Lung Cancer Brain Metastases.

PURPOSE: The intracranial benefit of offering dual immune-checkpoint inhibition (D-ICPI) with ipilimumab and nivolumab to patients with melanoma or non-small cell lung cancer (NSCLC) receiving stereotactic radiosurgery (SRS) for brain metastases (BMs) is unknown. We hypothesized that D-ICPI improves local control compared with SRS alone. METHODS AND MATERIALS: Patients with melanoma or NSCLC treated with SRS from 2014 to 2022 were evaluated. Patients were stratified by treatment with D-ICPI, single ICPI (S-ICPI), or SRS alone. Local recurrence, intracranial progression (IP), and overall survival were estimated using competing risk and Kaplan-Meier analyses. IP included both local and distant intracranial recurrence. RESULTS: Two hundred eighty-eight patients (44% melanoma, 56% NSCLC) with 1,704 BMs were included. Fifty-three percent of patients had symptomatic BMs. The median follow-up was 58.8 months. Twelve-month local control rates with D-ICPI, S-ICPI, and SRS alone were 94.73% (95% CI, 91.11%-96.90%), 91.74% (95% CI, 89.30%-93.64%), and 88.26% (95% CI, 84.07%-91.41%). On Kaplan-Meier analysis, only D-ICPI was significantly associated with reduced local recurrence (P = .0032). On multivariate Cox regression, D-ICPI (hazard ratio [HR], 0.4003; 95% CI, 0.1781-0.8728; P = .0239) and planning target volume (HR, 1.022; 95% CI, 1.004-1.035; P = .0059) correlated with local control. One hundred seventy-three (60%) patients developed IP. The 12-month cumulative incidence of IP was 41.27% (95% CI, 30.27%-51.92%), 51.86% (95% CI, 42.78%-60.19%), and 57.15% (95% CI, 44.98%-67.59%) after D-ICPI, S-ICPI, and SRS alone. On competing risk analysis, only D-ICPI was significantly associated with reduced IP (P = .0408). On multivariate Cox regression, D-ICPI (HR, 0.595; 95% CI, 0.373-0.951; P = .0300) and presentation with >10 BMs (HR, 2.492; 95% CI, 1.668-3.725; P < .0001) remained significantly correlated with IP. The median overall survival after D-ICPI, S-ICPI, and SRS alone was 26.1 (95% CI, 15.5-40.7), 21.5 (16.5-29.6), and 17.5 (11.3-23.8) months. S-ICPI, fractionation, and histology were not associated with clinical outcomes. There was no difference in hospitalizations or neurologic adverse events between cohorts. CONCLUSIONS: The addition of D-ICPI for patients with melanoma and NSCLC undergoing SRS is associated with improved local and intracranial control. This appears to be an effective strategy, including for patients with symptomatic or multiple BMs.

Mitigating Radiotoxicity in the Central Nervous System: Role of Proton Therapy.

OPINION STATEMENT: Central nervous system (CNS) radiotoxicity remains a challenge in neuro-oncology. Dose distribution advantages of protons over photons have prompted increased use of brain-directed proton therapy. While well-recognized among pediatric populations, the benefit of proton therapy among adults with CNS malignancies remains controversial. We herein discuss the role of protons in mitigating late CNS radiotoxicities in adult patients. Despite limited clinical trials, evidence suggests toxicity profile advantages of protons over conventional radiotherapy, including retention of neurocognitive function and brain volume. Modelling studies predict superior dose conformality of protons versus state-of-the-art photon techniques reduces late radiogenic vasculopathies, endocrinopathies, and malignancies. Conversely, potentially higher brain tissue necrosis rates following proton therapy highlight a need to resolve uncertainties surrounding the impact of variable biological effectiveness of protons on dose distribution. Clinical trials comparing best photon and particle-based therapy are underway to establish whether protons substantially improve long-term treatment-related outcomes in adults with CNS malignancies.

Long-term outcomes with reduced-dose whole-brain radiotherapy and a stereotactic radiosurgery boost for primary central nervous system lymphoma.

Background: Primary central nervous system lymphoma (PCNSL) is an aggressive diffuse large B-cell lymphoma. Treatment approaches are historically associated with neurotoxicity, particularly with high-dose whole-brain radiotherapy (WBRT). We hypothesized that reduced dose-WBRT (rd-WBRT) followed by a stereotactic radiosurgery (SRS) boost could provide durable disease control without significant adverse effects. Methods: We retrospectively reviewed PCNSL patients treated with rd-WBRT plus an SRS boost at Duke University between 2008 and 2021. Progression-free survival and overall survival (OS) were estimated using competing risk and Kaplan-Meier methods. Results: We identified 23 patients with pathologically confirmed PCNSL. Median age at diagnosis was 69 years (Q1Q3: 52-74) and median Karnofsky Performance Scale (KPS) was 80 (Q1Q3: 70-80). Median follow-up was 21 months. Median doses for rd-WBRT and SRS were 23.4 Gy (Q1Q3: 23.4-23.4) and 12 Gy (Q1Q3: 12-12.5), respectively. The cumulative incidence of intracranial progression at 2 years was 23% (95% CI: 8-42). Six patients (26%) developed distant radiographic progression while 2 patients (9%) developed both distant and local progression. Ten patients (44%) were alive without progression at last follow-up. By Kaplan-Meier estimate, the 2-year OS was 69% (95% CI: 46-84). There were no reported grade 3 + radiation-induced toxicities. Conclusions: The combination of rd-WBRT with an SRS boost appears well-tolerated with durable intracranial control. This approach may represent a treatment option for select patients, such as those with progressive or refractory disease. Further prospective studies are needed to validate these findings and determine whether this approach could be incorporated into consolidation strategies.

Novel Mechanisms and Future Opportunities for the Management of Radiation Necrosis in Patients Treated for Brain Metastases in the Era of Immunotherapy.

Radiation necrosis, also known as treatment-induced necrosis, has emerged as an important adverse effect following stereotactic radiotherapy (SRS) for brain metastases. The improved survival of patients with brain metastases and increased use of combined systemic therapy and SRS have contributed to a growing incidence of necrosis. The cyclic GMP-AMP (cGAMP) synthase (cGAS) and stimulator of interferon genes (STING) pathway (cGAS-STING) represents a key biological mechanism linking radiation-induced DNA damage to pro-inflammatory effects and innate immunity. By recognizing cytosolic double-stranded DNA, cGAS induces a signaling cascade that results in the upregulation of type 1 interferons and dendritic cell activation. This pathway could play a key role in the pathogenesis of necrosis and provides attractive targets for therapeutic development. Immunotherapy and other novel systemic agents may potentiate activation of cGAS-STING signaling following radiotherapy and increase necrosis risk. Advancements in dosimetric strategies, novel imaging modalities, artificial intelligence, and circulating biomarkers could improve the management of necrosis. This review provides new insights into the pathophysiology of necrosis and synthesizes our current understanding regarding the diagnosis, risk factors, and management options of necrosis while highlighting novel avenues for discovery.

Erratum to "E.C. Lerner, E.S. Srinivasan, G. Broadwater, et al. Factors Associated With New-Onset Seizures Following Stereotactic Radiosurgery for Newly Diagnosed Brain Metastases. Adv Radiat Oncol. 2022;7:101054."

[This corrects the article DOI: 10.1016/j.adro.2022.101054.].

Risk of Tract Seeding Following Laser Interstitial Thermal Therapy for Brain Tumors.

BACKGROUND: The management of intracranial oncological disease remains a significant challenge despite advances in systemic cancer therapy. Laser interstitial thermal therapy (LITT) represents a novel treatment for local control of brain tumors through photocoagulation with a stereotactically implanted laser fiber. Because the use of laser interstitial thermal therapy continues to increase within neurosurgery, characterization of LITT is necessary to improve outcomes. OBJECTIVE: To quantify the risk of tumor seeding along the laser fiber tract in patients receiving LITT for primary or metastatic brain tumors at a high-volume treatment center. METHODS: We retrospectively reviewed all patients receiving LITT from 2015 to 2021 at our medical center. Patients with biopsy-confirmed tumors were included in this study. Tract seeding was identified as discontinuous, newly enhancing tumor along the LITT tract. RESULTS: Fifty-six patients received LITT for biopsy-confirmed tumors from 2015 to 2021, with tract seeding identified in 3 (5.4%). Twenty-nine (51.8%) patients had gliomas, while the remainder had metastases, of which lung was the most common histology (20 patients, 74%). Tract seeding was associated with ablation proceeding inward from superficial tumor margin closest to the cranial entry point ( P = .03). Patients with tract seeding had a shorter median time to progression of 1.1 (0.1-1.3) months vs 4.2 (2.2-8.6) months ( P = .03). CONCLUSION: Although the risk of tract seeding after LITT is reassuringly low, it is associated with decreased progression-free survival. This risk may be related to surgical technique or experience. Follow-up radiosurgery to the LITT tract has the potential to prevent this complication.

Factors Associated With New-Onset Seizures Following Stereotactic Radiosurgery for Newly Diagnosed Brain Metastases.

Purpose: Stereotactic radiosurgery (SRS) is a highly effective therapy for newly diagnosed brain metastases. Prophylactic antiepileptic drugs are no longer routinely used in current SRS practice, owing to a perceived low overall frequency of new-onset seizures and potential side effects of medications. It is nonetheless desirable to prevent unwanted side effects following SRS. Risk factors for new-onset seizures after SRS have not been well established. As such, we aimed to characterize variables associated with increased seizure risk. Methods and Materials: Patients treated with SRS for newly diagnosed brain metastases between 2013 and 2016 were retrospectively reviewed at a single institution. Data on baseline demographics, radiation parameters, and clinical courses were collected. Results: The cohort consisted of 305 patients treated with SRS without prior seizure history. Median age and baseline Karnofsky Performance Scale score were 64 years (interquartile range, 55-70) and 80 (interquartile range, 80-90), respectively. Twenty-six (8.5%) patients developed new-onset seizures within 3 months of SRS. There was no association between new-onset seizures and median baseline Karnofsky Performance Scale score, prior resection, or prior whole brain radiation therapy. There were significant differences in the combined total irradiated volume (12.5 vs 3.7 cm3, P < .001), maximum single lesion volume (8.8 vs 2.8 cm3, P = .003), lesion diameter (3.2 vs 2.0 cm, P = .003), and number of lesions treated (3 vs 1, P = .018) between patients with and without new-onset seizures, respectively. On multivariate logistic regression, total irradiated volume (odds ratio, 1.09 for every 1-cm1 increase in total volume; confidence interval, 1.02-1.17; P = .016) and pre-SRS neurologic symptoms (odds ratio, 3.08; 95% confidence interval, 1.19-7.99; P = .020) were both significantly correlated with odds of seizures following SRS. Conclusions: Our data suggest that larger total treatment volume and the presence of focal neurologic deficits at presentation are associated with new-onset seizures within 3 months of SRS. High-risk patients undergoing SRS may benefit from counseling or prophylactic antiseizure therapy.

Combination laser interstitial thermal therapy plus stereotactic radiotherapy increases time to progression for biopsy-proven recurrent brain metastases.

Background: Improved survival for patients with brain metastases has been accompanied by a rise in tumor recurrence after stereotactic radiotherapy (SRT). Laser interstitial thermal therapy (LITT) has emerged as an effective treatment for SRT failures as an alternative to open resection or repeat SRT. We aimed to evaluate the efficacy of LITT followed by SRT (LITT+SRT) in recurrent brain metastases. Methods: A multicenter, retrospective study was performed of patients who underwent treatment for biopsy-proven brain metastasis recurrence after SRT at an academic medical center. Patients were stratified by "planned LITT+SRT" versus "LITT alone" versus "repeat SRT alone." Index lesion progression was determined by modified Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) criteria. Results: Fifty-five patients met inclusion criteria, with a median follow-up of 7.3 months (range: 1.0-30.5), age of 60 years (range: 37-86), Karnofsky Performance Status (KPS) of 80 (range: 60-100), and pre-LITT/biopsy contrast-enhancing volume of 5.7 cc (range: 0.7-19.4). Thirty-eight percent of patients underwent LITT+SRT, 45% LITT alone, and 16% SRT alone. Median time to index lesion progression (29.8, 7.5, and 3.7 months [P = .022]) was significantly improved with LITT+SRT. When controlling for age in a multivariate analysis, patients treated with LITT+SRT remained significantly less likely to have index lesion progression (P = .004). Conclusions: These data suggest that LITT+SRT is superior to LITT or repeat SRT alone for treatment of biopsy-proven brain metastasis recurrence after SRT failure. Prospective trials are warranted to validate the efficacy of using combination LITT+SRT for treatment of recurrent brain metastases.

Resolution of radiation necrosis with bevacizumab following radiation therapy for primary CNS lymphoma.

IMPORTANCE: Radiation necrosis (RN) is a rare but serious adverse effect following treatment with radiation therapy. No standard of care exists for the management of RN, and efforts to prevent and treat RN are limited by a lack of insight into the pathomechanics and molecular drivers of RN. This case series describes the outcomes of treatment with bevacizumab (BV) in two primary CNS lymphoma (PCNSL) patients who developed symptomatic biopsy-proven RN after whole brain radiation (WBRT) with a stereotactic radiosurgery (SRS) boost. OBSERVATIONS: Patient 1 is a 52 year-old female with PCNSL treated with WBRT followed by an SRS boost. She developed symptomatic biopsy-proven RN, and initial treatment with tocopherol and pentoxifylline was unsuccessful. A 100% clinical and radiographic response was achieved with 4 cycles of BV. Patient 2, a 48 year-old male with PCNSL, presented with seizures and biopsy-proven RN after radiation therapy. Initial empiric treatment with tocopherol and pentoxifylline was unsuccessful. A 100% clinical and radiographic response was achieved with 3 cycles of BV. CONCLUSIONS AND RELEVANCE: Monitoring for RN in patients with PCNSL treated with radiation therapy is warranted. BV is an efficacious treatment and a viable alternative to corticosteroids or surgical intervention.

Central nervous system injury from novel cancer immunotherapies.

PURPOSE OF REVIEW: Neurotoxicity from antineoplastic treatment remains a challenge in oncology. Cancer treatment-induced central nervous system (CNS) injury can be therapy-limiting, severely disabling, and even fatal. While emerging cancer immunotherapies have revolutionized oncology during the past decade, their immunomodulatory properties can cause immune-related adverse effects (IRAE) across organ systems, including the nervous system. Central neurologic IRAEs from chimeric antigen receptor T cells (CAR-T) and immune checkpoint inhibitors (ICPI) are challenging complications of such therapies.We aim to provide clinicians with a comprehensive review of the relevant forms of CAR-T and ICPI-associated CNS toxicity, focusing on clinical features of such complications, diagnostic workup, predictive biomarkers, and management considerations in affected patients. RECENT FINDINGS: Unique forms of CAR-T and ICPI-related CNS toxicity have been characterized in the recent literature. CAR-T-related neurotoxicity is common and clinically well delineated. ICPI-related CNS toxicity is relatively rare but includes a heterogenous spectrum of severe and diagnostically challenging conditions. While putative risk factors, neurotoxicity biomarkers, imaging correlates and treatment strategies have been put forward, development of tailored diagnostic and management consensus guidelines awaits further clinical investigation. SUMMARY: As CAR-T and ICPI become more widely adopted, early recognition, documentation, and management of immunotherapy-related CNS toxicity are of paramount importance in the clinical setting.

Eosinophil and lymphocyte counts predict bevacizumab response and survival in recurrent glioblastoma.

BACKGROUND: There is a lack of biomarkers to identify glioblastoma (GBM) patients who may benefit from specific salvage therapies, such as the anti-angiogenic agent bevacizumab. We hypothesized that circulating blood counts may serve as biomarkers for treatment response and clinical outcomes. METHODS: Complete blood counts, clinical data, and radiographic information were collected retrospectively from 84 recurrent GBM patients receiving bevacizumab (10 mg/kg every 2 weeks). Significant biomarkers were categorized into quartiles and the association with clinical outcomes was assessed using the Kaplan-Meier method. RESULTS: The median treatment duration and survival on bevacizumab (OS-A) was 88 and 192 days, respectively. On multivariate analysis, MGMT promoter methylation (hazard ratio [HR] 0.504, P = .031), increases in red blood cells (HR 0.496, P = .035), and increases in eosinophils (HR 0.048, P = .054) during treatment predicted improved OS-A. Patients in the first and fourth quartiles of eosinophil changes had a 12-month survival probability of 5.6% and 41.2% (P < .0001), respectively. Treatment response was associated with increases in eosinophil counts (P = .009) and improved progression-free survival (P = .013). On multivariate analysis, increases in lymphocyte counts among responders predicted improved OS-A (HR 0.389, P = .044). Responders in the first and fourth quartiles of lymphocyte changes had a 12-month survival probability of 0% and 44.4% (P = .019), respectively. Changes in platelet counts differed before and after radiographic response (P = .014). CONCLUSIONS: Changes in circulating eosinophil, lymphocyte, and platelet counts may predict treatment response and clinical outcomes in patients with recurrent GBM receiving bevacizumab.

Defining Treatment-Related Adverse Effects in Patients with Glioma: Distinctive Features of Pseudoprogression and Treatment-Induced Necrosis.

BACKGROUND: Pseudoprogression (PP) and treatment-induced brain tissue necrosis (TN) are challenging cancer treatment-related effects. Both phenomena remain insufficiently defined; differentiation from recurrent disease frequently necessitates tissue biopsy. We here characterize distinctive features of PP and TN to facilitate noninvasive diagnosis and clinical management. MATERIALS AND METHODS: Patients with glioma and confirmed PP (defined as appearance <5 months after radiotherapy [RT] completion) or TN (>5 months after RT) were retrospectively compared using clinical, radiographic, and histopathological data. Each imaging event/lesion (region of interest [ROI]) diagnosed as PP or TN was longitudinally evaluated by serial imaging. RESULTS: We identified 64 cases of mostly (80%) biopsy-confirmed PP (n = 27) and TN (n = 37), comprising 137 ROIs in total. Median time of onset for PP and TN was 1 and 11 months after RT, respectively. Clinically, PP occurred more frequently during active antineoplastic treatment, necessitated more steroid-based interventions, and was associated with glioblastoma (81 vs. 40%), fewer IDH1 mutations, and shorter median overall survival. Radiographically, TN lesions often initially manifested periventricularly (n = 22/37; 60%), were more numerous (median, 2 vs. 1 ROIs), and contained fewer malignant elements upon biopsy. By contrast, PP predominantly developed around the tumor resection cavity as a non-nodular, ring-like enhancing structure. Both PP and TN lesions almost exclusively developed in the main prior radiation field. Presence of either condition appeared to be associated with above-average overall survival. CONCLUSION: PP and TN occur in clinically distinct patient populations and exhibit differences in spatial radiographic pattern. Increased familiarity with both conditions and their unique features will improve patient management and may avoid unnecessary surgical procedures. IMPLICATIONS FOR PRACTICE: Pseudoprogression (PP) and treatment-induced brain tissue necrosis (TN) are challenging treatment-related effects mimicking tumor progression in patients with brain cancer. Affected patients frequently require surgery to guide management. PP and TN remain arbitrarily defined and insufficiently characterized. Lack of clear diagnostic criteria compromises treatment and may adversely affect outcome interpretation in clinical trials. The present findings in a cohort of patients with glioma with PP/TN suggest that both phenomena exhibit unique clinical and imaging characteristics, manifest in different patient populations, and should be classified as distinct clinical conditions. Increased familiarity with PP and TN key features may guide clinicians toward timely noninvasive diagnosis, circumvent potentially unnecessary surgical procedures, and improve response assessment in neuro-oncology.

Proton beam radiotherapy for anal and rectal cancers.

Gastrointestinal cancers are bordered by radiosensitive visceral organs, resulting in a narrow therapeutic window. The search for more efficacious and tolerable therapies raises the possibility that proton beam therapy's (PBT) physical and dosimetric differences from conventional therapy may be better suited to treat both primary and recurrent disease, which carries its own unique challenges. Currently, the maximal efficacy of radiation plans for primary and recurrent anorectal cancer is constrained by delivery techniques and modalities which must consider feasibility challenges and toxicity secondary to exposure of organs at risk (OARs). Studies using volumetric modulated arc therapy (VMAT) and intensity modulated radiation therapy (IMRT) demonstrate that more precise dose delivery to target volumes improves local control rates and reduces complications. By reducing the low-to-moderate radiation dose-bath to bone marrow, small and large bowel, and skin, PBT may offer an improved side-effect profile. The potential to reduce toxicity, increase patient compliance, minimize treatment breaks, and enable dose escalation or hypofractionation is appealing. In cases where prognosis is favorable, PBT may mitigate long-term morbidity such as secondary malignancies, femoral fractures, and small bowel obstruction.

Bone marrow response as a potential biomarker of outcomes in glioblastoma patients.

OBJECTIVE Glioblastoma (GBM) is a highly aggressive malignancy that requires a multidisciplinary therapeutic approach of surgery, chemotherapy, and radiation therapy, but therapy is frequently limited by side effects. The most common adverse effect of chemotherapy with temozolomide (TMZ) is myelosuppression. It remains unclear whether the degree of bone-marrow suppression might serve as a biomarker for treatment outcome. The aim of the current study was to investigate whether the degree of bone-marrow toxicity in patients treated with TMZ correlates with overall survival (OS) and MRI-based time to progression (progression-free survival [PFS]). METHODS Complete blood counts and clinical and imaging information were collected retrospectively from 86 cases involving GBM patients who had completed both radiation therapy and at least 6 monthly cycles of chemotherapy with TMZ. RESULTS Using a multivariate Cox proportional hazard model, it was observed that MGMT promoter methylation, wild-type EGFR, younger patient age at diagnosis, and treatment-induced decreases in white blood cell counts were associated with improved OS. The 2-year survival rate was 25% and 58% for patients with increases and decreases, respectively, in white blood cell counts from baseline over 6 months of TMZ treatment. Consistent with the literature, IDH mutation and MGMT promoter methylation were associated with better PFS and OS. IDH mutation and MGMT promoter methylation were not correlated with changes in peripheral red blood cell or white blood cell counts. CONCLUSIONS Decreases in white blood cell counts might serve as a potential biomarker for OS and PFS in malignant glioma patients treated with radiation therapy and TMZ. It remains unclear whether treatment-induced changes in white blood cell counts correlate with drug-induced antitumor activity or represent an independent factor of the altered local and systemic tumor environment. Additional studies will be needed to determine dose dependence for chemotherapy based upon peripheral blood counts.