The Diagnostic Value of a Short Memory Test: The TNI-93

Background: The TNI-93 is a quick memory test designed for all patients regardless of their education level. A significant proportion of patients with Alzheimer’s disease (AD) are illiterate or poorly educated, and only a few memory tests are adapted for these patients. Objective: In this study we aimed at assessing the diagnostic value of the TNI-93 for diagnosis of patients with biologically confirmed amyloid status. Methods: We included all patients who had an analysis of AD cerebrospinal fluid biomarkers, a neuropsychological assessment including a TNI-93 and an anatomical brain imaging at Avicenne Hospital between January 2009 and November 2019. We compared the TNI-93 scores in patients with amyloid abnormalities (A+) and patients without amyloid abnormalities (A-) according to the AT(N) diagnostic criteria. Results: 108 patients were included (mean age: 66.9±8.5 years old, mean education level: 8.9±5.2 years). Patients from the A + group (N= 80) were significantly more impaired than patients from the A- group (N= 28) on immediate recall (A+: 5.9±2.8; A-: 7.4±2.6; p = 0.001), free recall (A+: 3.5±2.7; A-: 5.9±2.8; p ≤ 0.001), total recall (A+: 5.7±3.5; A-:7.8±2.8; p ≤ 0.001), and on number of intrusions during the recall phase (A+: 1±1.8; A-: 0.1±0.3; p = 0.002). ROC curves revealed that the best scores to discriminate A + from A- patients were immediate recall (Area under curve (AUC): 0.70), number of encoding trials (AUC: 0.73), free recall (AUC: 0.74), and total recall (AUC: 0.74). Conclusion: The TNI-93’s immediate, free, and total recalls are valuable tools for the 39 diagnosis of AD.

Vehicle Counting Accuracy Improvement By Identity Sequences Detection Based on Yolov4 Deep Neural Networks

Models for vehicle detection, classification, and counting based on computer vision and artificial intelligence are constantly evolving. In this study, we present the Yolov4-based vehicle detection, classification, and counting model approach. The number of vehicles was calculated by generating the serial number of the identity of each vehicle. The object is detected and classified, marked by the display of bounding boxes, classes, and confidence scores. The system input is a video dataset that considers the camera position, light intensity, and vehicle traffic density. The method has counted the number of vehicles: cars, motorcycles, buses, and trucks. Evaluation of model performance is based on accuracy, precision, and total recall of the confusion matrix. The results of the dataset test and the calculation of the model performance parameters had obtained the best accuracy, precision. Total recall values when the model testing was carried out during the day where the camera position was at the height of 6 m and the loss of 500 was 83%, 93%, and 94%. Meanwhile, the lowest total accuracy, precision, and recall were obtained when the model was tested at night. The camera position was at the height of 1.5 m, and 900 losses were 68%, 77%, and 78%.

The diagnostic value of the TNI-93: a memory test suitable for both literate and illiterate patients.

Background: A significant proportion of Alzheimer disease (AD) patients are illiterate or poorly educated, and only a few memory tests are adapted for these patients. The TNI-93 is a quick memory test that was designed for all patients regardless of their education level. In the present study we aimed at assessing the diagnostic value of the TNI-93 for the screening and diagnosis of patients with biologically confirmed amyloid status.Method: We included all patients who had a lumbar puncture (LP) for the analysis of AD cerebrospinal fluid (CSF) biomarkers, a full neuropsychological assessment that included the TNI-93 and an anatomical brain imaging (MRI/CT scan) at Avicenne Hospital between January 2009 and November 2019. We compared the TNI-93 scores in A+ patients (patients with amyloid abnormalities) and A- patients according to the A T (N) criteria (NIA-AA 2018). We also compared A+T+ patients to A-T- patients.Results: 108 patients were included with a mean age of 66.9 ± 8.5 years old, and mean education level of 8.9 ± 5.16 years, illiterate patients represented 27% of the population. Patients from the A+ group (N= 80) were significantly more impaired than patients from the A- group (N=28) on immediate recall (A+: 5.9±2.8; A-: 7.4±2.6; p=0.001), free recall (A+: 3.5±2.7; A-: 5.9±2.8; p< 0.001), total recall (A+: 5.7±3.5; A-: 7.8±2.8; p< 0.001) and on number of intrusions during the recall phase (A+: 1±1.8; A-: 0.1±0.3; p=0.002). Similar results were observed in the memory subgroup but not in patients with presentation other than memory complaint (ie language impairment or others presentation such as behavioural and hallucination). Similar results with increased significance were observed when we compared A+T+ patients (N=50) to A-T- patients (N=26). Analyses of the ROC curves revealed that the best scores of the TNI-93 test to discriminate A+ patients from A- were immediate recall (Area under curve (AUC): 0.70), free recall (AUC: 0.74) and total recall (AUC: 0.74).Conclusion: We found that the TNI-93’s immediate recall, free and total recall are valuable for the diagnosis of amyloid pathology suggestive of AD.

CTNI-51. NEUROCOGNITIVE FUNCTION (NCF) OUTCOMES OF RTOG FOUNDATION 3508: A PHASE 3 TRIAL OF ABT-414 WITH CONCURRENT CHEMORADIATION AND ADJUVANT TEMOZOLOMIDE IN PATIENTS WITH EGFR-AMPLIFIED NEWLY DIAGNOSED GBM

RTOG 3508/AbbVie M13-813/INTELLANCE-1 was a phase 3 trial of depatuximab-mafodotin (depatux-m, formerly ABT-414) that accrued 639 patients with EGFR-amplified newly diagnosed GBM. At the pre-specified interim OS analysis, the futility criteria were met and there was no survival benefit from adding depatux-m to SOC. Pre-specified secondary NCF analyses included time to decline in verbal learning and memory as assessed by the HVLT-R Total Recall based on the reliable change index. Exploratory NCF analyses examined changes in other HVLT-R outcomes over time. As corneal epitheliopathy causing visual impairment is a known toxicity of depatux-m, NCF tests that did not depend on visual acuity were employed. NCF testing occurred at baseline, day 1 of the first cycle of adjuvant depatux-m, every other cycle (i.e., 8 weeks) thereafter, and at progression. Compliance with test completion was 95% at screening and 80%, 70%, 58%, 51%, 47% thereafter through cycle 9. The most common reasons for missing data was site error. Time to HVLT-R Total Recall decline trended worse in the depatux-m arm compared to placebo but the difference was not significant (12 month deterioration: 41.2%, 95% CI: 3.50–47.2 vs 32.4%, 95% CI: 26.6- 38.4, p=0.052). The depatux-m arm, in comparison to the placebo arm, showed greater decline from baseline on the HVLT-R at the following time points: cycle 3 (Total Recall: mean= -1.8, SD=5.7 vs mean= -0.5, SD=5.5, respectively, p=0.046; Delayed Recall: mean= -1.1, SD=3.0 vs. mean= -0.2, SD=2.7, respectively, p=0.01), cycle 7 (Total Recall: mean= -0.6, SD=5.1 vs mean= 1.4, SD=5.0, respectively, p=0.009; Delayed Recall: mean -0.6, SD=3.0 vs. mean= 0.5, SD=2.7, respectively, p=0.01), and cycle 9 (Delayed Recall: mean=-0.4, SD=2.7 vs. mean= 0.8, SD=2.4, respectively, p=0.003). Depatux-m added to concurrent chemoradiation and adjuvant temozolomide was associated with faster time to deterioration and worse episodic learning and memory over time than placebo.