Application of an artificial neural network model for early outcome prediction of gamma knife radiosurgery in patients with trigeminal neuralgia and determining the relative importance of risk factors

OBJECTIVES

Stereotactic radiosurgery (SRS) is a minimally invasive modality for the treatment of trigeminal neuralgia (TN). Outcome prediction of this modality is very important for proper case selection. The aim of this study was to create artificial neural networks (ANN) to predict the clinical outcomes after gamma knife radiosurgery (GKRS) in patients with TN, based on preoperative clinical factors.

PATIENTS AND METHODS

We used the clinical findings of 155 patients who were underwent GKRS (from March 2000 to march 2015) at Iran Gamma Knife center, Teheran, Iran. Univariate analysis was performed for a long list of risk factors, and those with P-Value < 0.2 were used to create back-propagation ANN models to predict pain reduction and hypoesthesia after GKRS. Pain reduction was defined as BNI score 3a or lower and hypoesthesia was defined as BNI score 3 or 4.

RESULTS

Typical trigeminal neuralgia (TTN) (P-Value = 0.018) and age>65 (P-Value = 0.040) were significantly associated with successful pain reduction and three other variables including radiation dosage >85 (P-Value = 0.098), negative history of diabetes mellitus (P-Value = 0.133) and depression (P-Value = 0.190). On the other hand, radio dosage>85 (P-Value = 0.008) was significantly associated with hypoesthesia, other related risk factors (with p-Value<0.2), were history of multiple sclerosis (P-Value = 0.106), pain duration more than 10 years before GKRS (P-Value = 0.115), history of depression (P-Value = 0.139), history of percutaneous ablative procedures (P-Value = 0.148) and history of diabetes mellitus (P-Value = 0.169).ANN models could predict pain reduction and hypoesthesia with the accuracy of 84.5% and 91.5% respectively. By mutual elimination of each factor in this model we could also evaluate the contribution of each factor in the predictive performance of ANN.

CONCLUSIONS

The findings show that artificial neural networks can predict post operative outcomes in patients who underwent GKRS with a high level of accuracy. Also the contribution of each factor in the prediction of outcomes can be determined using the trained network.

Granulocyte-colony stimulating factor administration for neurological improvement in patients with postrehabilitation chronic incomplete traumatic spinal cord injuries: a double-blind randomized controlled clinical trial

OBJECTIVE

Granulocyte-colony stimulating factor (G-CSF) is a major growth factor for activation and differentiation of granulocyte colonies in the bone marrow. This cytokine has been widely and safely employed in different conditions over many years. The purpose of this study was to investigate the efficacy of G-CSF administration for traumatic spinal cord injury (TSCI).

METHODS

This double-blind parallel randomized, placebo-controlled, clinical trial, a phase III study, was performed from June 2013 to June 2016 in the Brain and Spinal Cord Injury Research (BASIR) center at Tehran University of Medical Sciences (TUMS). It included 120 patients with incomplete chronic TSCI, American Spinal Injury Association (ASIA) Impairment Scale (AIS) B, C, or D, of at least 6 months’ duration. Sixty patients were allocated into the treatment group and 60 patients into the control group. All the patients had completed an outpatient rehabilitation program in the postacute period and were in a neurological and functional plateau. Patients were assessed with the ASIA grading system, the Spinal Cord Independence Measure (SCIM-III), and the International Association of Neurorestoratology-Spinal Cord Injury Functional Rating Scale (IANR-SCIFRS) just before intervention and at 1, 3, and 6 months after 7 subcutaneous administrations of 300 μg/day of G-CSF in the treatment group and placebo in the control group (administered once per day over the course of 1 week). Randomization was performed with randomized block design, and the patients and evaluators were blinded regarding the treatment groups. One patient did not receive the entire allocated intervention and 5 patients were lost to follow-up. Thus data from 114 patients were included in the analysis.

RESULTS

One hundred twenty patients were randomized and allocated into the study groups. Among them, 56 patients (93.3%) in the G-CSF group and 58 patients (96.6%) in the placebo group completed the study protocol. After 6 months of follow-up, AIS in the placebo group remained unchanged, whereas in the G-CSF group, 1 patient improved from AIS B to C, and 4 patients improved from AIS C to D. The mean (± SE) improvement in ASIA motor score in the G-CSF group was 5.5 ± 0.62, which was significantly more than in the placebo group (0.77 ± 0.20) (p < 0.001). The mean light touch and pinprick sensory scores, respectively, increased by 6.1 ± 1.1 and 8.7 ± 1.5 in the G-CSF group and by 1.3 ± 0.52 and 0.89 ± 0.44 scores in the placebo group (p < 0.001). Evaluation of functional improvement by the IANR-SCIFRS instrument revealed significantly more improvement in the G-CSF group (3.5 ± 0.37) than in the placebo group (0.41 ± 0.12) (p < 0.001). Also, a significant difference was observed in functional improvement between the 2 groups as measured by SCIM-III instrument (7.5 ± 0.95 vs 2.1 ± 0.51, p < 0.001).

CONCLUSIONS

Administration of G-CSF for incomplete chronic spinal cord injuries is associated with significant motor, sensory, and functional improvement.

Clinical trial registration no.: IRCT201108297441N1 (www.irct.ir)

Adaptation of Traumatic Brain Injury Guidelines in Iran

CONTEXT

The National institute for health and care excellence (NICE) and scottish intercollegiate guidelines network (SIGN) are two well-known sources of clinical guideline development. In the past years, they have developed clinical guidelines for the management of head injury. In this report, we will highlight our modifications to these guidelines according to the domestic situation in a developing country.

EVIDENCE ACQUISITION

The guidelines were appraised using the appraisal of guidelines for research and evaluation (AGREE) instrument. All key recommendations were reviewed by 14 prominent Iranian neurosurgeons; levels of evidence were evaluated and items with limited evidence were determined. Available evidence for selected items were reviewed and discussed.

RESULTS

The following items were the most challenging when accounting for the domestic situation in Iran: age as a risk factor for referral, computed tomography scan, the impact of medical comorbidities, pregnancy, consultation, referral to a neurosurgical unit, and teleconsulting and observation before discharge.

CONCLUSIONS

The evidence in the discussed topics was limited and controversial. This report is important because it exposes the current knowledge gap in head trauma studies in Iran.

Pituitary macroadenoma coexistent with a posterior circulation aneurysm leading to subarachnoidal hemorrhage during transsphenoidal surgery

The coexistence of cerebral aneurysm and pituitary adenoma has been described previously. Most of such cases harbor functional tumors and anterior circulation aneurysms, with very rare cases of posterior circulation aneurysms. In this report, we present a case of subarachnoidal hemorrhage due to rupture of an undetected basilar apex aneurysm during microscopic transsphenoidal surgery for a nonfunctional pituitary adenoma. Subarachnoidal hemorrhage following transsphenoidal surgery is a rare event. The concurrence of posterior circulation aneurysm and nonfunctional adenoma is uncommon too. Neuroimaging of cerebrovascular circulation before surgical treatment of pituitary adenoma, although controversial, would be helpful to evaluate vascular involvement and rule out any potential concurrent cerebrovascular diseases. Open or endovascular treatment of unruptured intracranial aneurysms carries relatively low morbidity and may be considered prior to other elective intracranial procedures like transsphenoidal surgery.