Advancements in predicting outcomes in patients with glioma: a surgical perspective

Predicting post-surgical functional status in high-grade glioma with resting state fMRI and machine learning

PURPOSE

High-grade glioma (HGG) is the most common and deadly malignant glioma of the central nervous system. The current standard of care includes surgical resection of the tumor, which can lead to functional and cognitive deficits. The aim of this study is to develop models capable of predicting functional outcomes in HGG patients before surgery, facilitating improved disease management and informed patient care.

METHODS

Adult HGG patients (N = 102) from the neurosurgery brain tumor service at Washington University Medical Center were retrospectively recruited. All patients completed structural neuroimaging and resting state functional MRI prior to surgery. Demographics, measures of resting state network connectivity (FC), tumor location, and tumor volume were used to train a random forest classifier to predict functional outcomes based on Karnofsky Performance Status (KPS < 70, KPS ≥ 70).

RESULTS

The models achieved a nested cross-validation accuracy of 94.1% and an AUC of 0.97 in classifying KPS. The strongest predictors identified by the model included FC between somatomotor, visual, auditory, and reward networks. Based on location, the relation of the tumor to dorsal attention, cingulo-opercular, and basal ganglia networks were strong predictors of KPS. Age was also a strong predictor. However, tumor volume was only a moderate predictor.

CONCLUSION

The current work demonstrates the ability of machine learning to classify postoperative functional outcomes in HGG patients prior to surgery accurately. Our results suggest that both FC and the tumor's location in relation to specific networks can serve as reliable predictors of functional outcomes, leading to personalized therapeutic approaches tailored to individual patients.

Neurosurgical Management of Cerebrospinal Tumors in the Era of Artificial Intelligence : A Scoping Review

Central nervous system tumors are identified as tumors of the brain and spinal cord. The associated morbidity and mortality of cerebrospinal tumors are disproportionately high compared to other malignancies. While minimally invasive techniques have initiated a revolution in neurosurgery, artificial intelligence (AI) is expediting it. Our study aims to analyze AI's role in the neurosurgical management of cerebrospinal tumors. We conducted a scoping review using the Arksey and O'Malley framework. Upon screening, data extraction and analysis were focused on exploring all potential implications of AI, classification of these implications in the management of cerebrospinal tumors. AI has enhanced the precision of diagnosis of these tumors, enables surgeons to excise the tumor margins completely, thereby reducing the risk of recurrence, and helps to make a more accurate prediction of the patient's prognosis than the conventional methods. AI also offers real-time training to neurosurgeons using virtual and 3D simulation, thereby increasing their confidence and skills during procedures. In addition, robotics is integrated into neurosurgery and identified to increase patient outcomes by making surgery less invasive. AI, including machine learning, is rigorously considered for its applications in the neurosurgical management of cerebrospinal tumors. This field requires further research focused on areas clinically essential in improving the outcome that is also economically feasible for clinical use. The authors suggest that data analysts and neurosurgeons collaborate to explore the full potential of AI.

Using machine learning to predict health-related quality of life outcomes in patients with low grade glioma, meningioma, and acoustic neuroma

Background

Predicting reduced health-related quality of life (HRQoL) after resection of a benign or low-grade brain tumour provides the opportunity for early intervention, and targeted expenditure of scarce supportive care resources. We aimed to develop, and evaluate the performance of, machine learning (ML) algorithms to predict HRQoL outcomes in this patient group.

Methods

Using a large prospective dataset of HRQoL outcomes in patients surgically treated for low grade glioma, acoustic neuroma and meningioma, we investigated the capability of ML to predict a) HRQoL-impacting symptoms persisting between 12 and 60 months from tumour resection and b) a decline in global HRQoL by more than the minimum clinically important difference below a normative population mean within 12 and 60 months after resection. Ten-fold cross-validation was used to measure the area under the receiver operating characteristic curve (AUC), area under the precision-recall curve (PR-AUC), sensitivity, and specificity of models. Six ML algorithms were explored per outcome: Random Forest Classifier, Decision Tree Classifier, Logistic Regression, K Neighbours Classifier, Support Vector Machine, and Gradient Boosting Machine.

Results

The final cohort included 262 patients. Outcome measures for which AUC>0.9 were Appetite loss, Constipation, Nausea and vomiting, Diarrhoea, Dyspnoea and Fatigue. AUC was between 0.8 and 0.9 for global HRQoL and Financial difficulty. Pain and Insomnia achieved AUCs below 0.8. PR-AUCs were similar overall to the AUC of each respective classifier.

Conclusions

ML algorithms based on routine demographic and perioperative data show promise in their ability to predict HRQoL outcomes in patients with low grade and benign brain tumours between 12 and 60 months after surgery.

LINC00339: An emerging major player in cancer and metabolic diseases

Long noncoding RNAs (lncRNAs) are a series of RNA molecules without ability to code proteins. LncRNAs have emerged as significant players in almost all aspects of gene function and regulation and play crucial roles in many human diseases. Particular lncRNAs are deemed to be promising molecular biomarkers used for diagnosing diseases and determining patient prognoses and treatment efficacies. LINC00339 is a new budding lncRNA and much of evidence shows that it is abnormally expressed in multifarious diseases, including endometriosis, cardiomyocyte apoptosis, osteoporosis, digestive-system tumors, respiratory-system tumors, nervous-system tumors, and diseases involving other systems. Additionally, LINC00339 is remarkably associated with different clinical features, such as tumor size, TNM stage, and pathological grade. LINC00339 expression has been proved to upregulate in the aforementioned diseases and has been identified to promote disease occurrence and development. It is also reported that LINC00339 is associated with various cellular events, such as tumor cell proliferation, motility and invasiveness, the expression has also been proved that it is closely related to clinical symptoms in cancer patients. This review summarizes the relationships among expression levels, biological features, clinical symptoms, and regulatory mechanisms of LINC00339 in several diseases and discusses the clinical applications of LINC00339 as a cancer diagnostic, prognostic and treatment efficacy biomarker.

Practice of the new supervised machine learning predictive analytics for glioma patient survival after tumor resection: Experiences in a high-volume Chinese center

OBJECTIVE

This study aims to assess the effectiveness of the Gradient Boosting (GB) algorithm on glioma prognosis prediction and to explore new predictive models for glioma patient survival after tumor resection.

METHODS

A cohort of 776 glioma cases (WHO grades II-IV) between 2010 and 2017 was obtained. Clinical characteristics and biomarker information were reviewed. Subsequently, we constructed the conventional Cox survival model and three different supervised machine learning models, including support vector machine (SVM), random survival forest (RSF), Tree GB, and Component GB. Then, the model performance was compared with each other. At last, we also assessed the feature importance of models.

RESULTS

The concordance indexes of the conventional survival model, SVM, RSF, Tree GB, and Component GB were 0.755, 0.787, 0.830, 0.837, and 0.840, respectively. All areas under the cumulative receiver operating characteristic curve of both GB models were above 0.800 at different survival times. Their calibration curves showed good calibration of survival prediction. Meanwhile, the analysis of feature importance revealed Karnofsky performance status, age, tumor subtype, extent of resection, and so on as crucial predictive factors.

CONCLUSION

Gradient Boosting models performed better in predicting glioma patient survival after tumor resection than other models.

MiR-493-5p inhibits the malignant development of gliomas via suppressing E2F3-mediated dysfunctions of P53 and PI3K/AKT pathways

BACKGROUND

Gliomas is a major challenge of current medical system, and thousands of people are struggling in the pain of this disease worldwide. In the last decade, the functions of miRNAs have been revealed by many studies, and the intervention on miRNA dysfunctions has been thought as a promising way to counter cancer. MiR-493-5p has been identified as a tumor inhibitor to suppress the progressions of several tumors while its role in gliomas remains unknown. Hence, the study investigated the expression levels of miR-493-5p in glioma tissues and cell lines.

METHODS

CCK-8 assay, transwell assay and flow cytometry assay were used to observe the effects of miR-493-5p on tumor cells. The downstream targets of miR-493-5p were also searched and verified with online databases and dual-luciferase reporter assay. Moreover, the activities of P53 and PI3K/AKT pathways were also explored by western blot to illustrate the regulation mechanism of miR-493-5p on glioma development.

RESULTS

The results showed that miR-493-5p was significantly downregulated in pathological tissues and glioma cell lines, and the increased miR-493-5p effectively inhibited the malignant behavior and promoted the apoptosis of glioma cells.

CONCLUSIONS

E2F3 was confirmed as a target of miR-493-5p, and the effects of miR-493-5p on the phenotype of glioma cells could be partly reversed by E2F3. Besides, it was also found that miR-493-5p could effectively suppress the expression of E2F3 and then improve the dysfunctions of the P53 and PI3K/AKT pathways.

Preoperative Patient-Reported Outcomes in Suspected Low-Grade Glioma: Markers of Disease Severity and Correlations with Molecular Subtypes

This prospective study aims to determine the overall health-related quality of life (HRQoL), functioning, fatigue, and psychological distress preoperatively in patients with suspected diffuse low-grade glioma (dLGG). We were particularly interested if these parameters differed by molecular tumor subtypes: oligodendroglioma, IDHmut astrocytoma and IDHwt astrocytoma. Fifty-one patients answered self-assessed questionnaires prior to operation (median age 51 years; range 19–75; 19 females [37%]). Thirty-five (69%) patients had IDH-mutated tumors, of which 17 were 1p/19q codeleted (i.e., oligodendroglioma) and 18 non-1p/19q codeleted (i.e., IDHmut astrocytoma). A lower overall generic HRQoL was associated with a high level of fatigue (r_s = −0.49, p < 0.001), visual disorder (r_s = −0.5, p < 0.001), motor dysfunction (r_s = −0.51, p < 0.001), depression (r_s = −0.54, p < 0.001), and reduced functioning. Nearly half of the patients reported high fatigue (23 out of 51 patients) and anxiety (26/51 patients). Patients with IDHwt had worse generic HRQoL, worse functioning, and more severe fatigue, though differences were not statistically significant between the molecular subtypes. In conclusion, fatigue and anxiety are prominent self-assessed symptoms of patients with suspected dLGG in a preoperative setting, but do not seem to be a reliable method to make assumptions of underlying biology or guide treatment decisions.

Prognostic evaluation of serum long non-coding RNA H19 for endoscopic keyhole surgery or craniotomy in glioma

BACKGROUND

Our study aims to explore the effect of serum long non-coding RNA (lncRNA) H19 level on the long-term prognosis of endoscopic keyhole surgery or craniotomy for glioma.

METHODS

A total of 264 glioma patients were selected. Patients were randomly divided into the Craniotomy-high H19 group, the Craniotomy-low H19 group, the Endoscopic keyhole surgery-high H19 group and the Endoscopic keyhole surgery-low H19 group.

RESULTS

Compared with adjacent tissues (5.19 ± 1.42), H19 level in cancer tissues (7.45 ± 1.60) and serum (6.44 ± 1.57) was significantly increased (P < 0.05). Compared with serum, H19 level in cancer tissues was significantly increased (P < 0.05). Pearson correlation analysis found that the relative expression level of serum H19 in glioma patients was positively correlated with cancer tissues (r_Pearson = 0.547, P < 0.001), but had no significant correlation with adjacent tissues (r_Pearson = 0.126, P  =  0.207). The expression of H19 in serum was significantly related to WHO grade (r_Pearson = 0.514, P < 0.001). Compared with the Endoscopic keyhole surgery-high H19 group and the Endoscopic keyhole surgery-low H19 group, the survival rate of patients in the Craniotomy-high H19 group (χ² = 17.115 and log-rank P < 0.001; χ² = 18.406 and log-rank P < 0.001) and the Craniotomy-low H19 group was significantly reduced (χ² = 15.007 and log-rank P < 0.001; χ² = 16.121 and log-rank P < 0.001). Cox regression results showed that serum H19 level, craniotomy and WHO grade were risk factors for glioma. When H19 level was lower than 6.28, the 30-month survival rate of patients with the endoscopic keyhole surgery was 100%.

CONCLUSION

For patients with low H19 level (<5.36), both endoscopic keyhole surgery and craniotomy are available, otherwise, endoscopic keyhole surgery is more recommended.