Chandan Saha

Machine learning (ML) models have been commonly utilized to predict various opioid-related outcomes and risks, including post-operative opioid use, opioid use disorder (OUD), misuse, or overdose. Despite their promising performance, the clinical utility and cross-study comparability of ML models are constrained. This is mainly due to variability in outcome definitions, data heterogeneity, class imbalance and analysis concerns, inadequate external or prospective validation, and limited real-world deployment and ethical concerns. Herein, we present an updated overview of these challenges in predicting opioid-related outcomes and outline strategies to improve the clinically meaningful applications of ML in this domain.

The efficacy of repetitive transcranial magnetic stimulation (rTMS) as a treatment for Alzheimer’s disease (AD) is uncertain at baseline. Herein, we aimed to investigate whether radiomic features from the pre-treatment MRI data could predict rTMS efficacy for AD treatment. Out of 110 participants with AD in the active (n = 75) and sham (n = 35) rTMS treatment groups having T1-weighted brain MRI data, we had two groups of responders (active = 55 and sham = 24) and non-responders (active = 20 and sham = 11). We extracted histogram-based radiomic features from MRI data using 3D Slicer software; the most important features were selected utilizing a combination of a two-sample t-test, correlation test, least absolute shrinkage, and selection operator. The support vector machine classified rTMS responders and non-responders with a cross-validated mean accuracy/AUC of 81.9%/90.0% in the active group and 87.4%/95.8% in the sham group. Further, the radiomic features of the active group significantly correlated with participants’ AD assessment scale-cognitive subscale (ADAS-Cog) change after treatment (false discovery rate corrected p < 0.05). Given that baseline radiomic features were able to accurately predict AD patients’ responses to rTMS treatment, these radiomic features warrant further investigation for personalizing AD therapeutic strategies. Graphical Abstract

Repetitive Transcranial Magnetic Stimulation (rTMS) has been applied as an investigational therapy for Alzheimer’s Disease (AD). The recent largest (N = 135) double-blind study with 6 months post-treatment follow-up investigating rTMS efficacy as a treatment for AD found about 72% of participants in each group of active and sham were positively responsive to rTMS (using Magstim AirFilm active and sham coils). Since the used sham coil produced about 25.3% of the peak active stimulus, it was hypothesized it could evoke a measurable response in AD patients. This study looks at the details of the above study’s sham responses to determine why and how such a response might occur and how cerebrovascular symptomatology may have impacted that response. In the above-mentioned study, 90 and 45 patients were randomly assigned to active and sham groups, respectively. Those with modified Hachinski Ischemic Scores (HIS) below and above 2 were labeled AD ₂ and ADcvd ₂ , respectively. Analysis of the primary outcome measure ADAS-Cog score change from baseline to post-treatment and follow-ups showed the ADcvd ₂ in the sham group had a significantly ( p = .034) greater improvement or less decline at post-treatment and follow-up sessions compared to the ADcvd ₂ in the active group. Additionally, the improvement of the ADcvd ₂ sham compared to those in the active group persisted longer. Also, there was a significant ( p = .036) improvement for AD ₂ individuals in the active compared to AD ₂ sham stimulation group at 2-months post-treatment. Overall, the sham rTMS stimulus did evoke a measurable response which was more effective for ADcvd ₂ in sham than ADcvd ₂ in active support of a vascular mechanism likely linked to the shallower sham stimulus penetration.

This study is a post-hoc examination of baseline MRI data from a clinical trial investigating the efficacy of repetitive transcranial magnetic stimulation (rTMS) as a treatment for patients with mild–moderate Alzheimer’s disease (AD). Herein, we investigated whether the analysis of baseline MRI data could predict the response of patients to rTMS treatment. Whole-brain T1-weighted MRI scans of 75 participants collected at baseline were analyzed. The analyses were run on the gray matter (GM) and white matter (WM) of the left and right dorsolateral prefrontal cortex (DLPFC), as that was the rTMS application site. The primary outcome measure was the Alzheimer’s disease assessment scale—cognitive subscale (ADAS-Cog). The response to treatment was determined based on ADAS-Cog scores and secondary outcome measures. The analysis of covariance showed that responders to active treatment had a significantly lower baseline GM volume in the right DLPFC and a higher GM asymmetry index in the DLPFC region compared to those in non-responders. Logistic regression with a repeated five-fold cross-validated analysis using the MRI-driven features of the initial 75 participants provided a mean accuracy of 0.69 and an area under the receiver operating characteristic curve of 0.74 for separating responders and non-responders. The results suggest that GM volume or asymmetry in the target area of active rTMS treatment (DLPFC region in this study) may be a weak predictor of rTMS treatment efficacy. These results need more data to draw more robust conclusions.

Alzheimer’s disease (AD) is the most common type of dementia, and AD individuals often present significant cerebrovascular disease (CVD) symptomology. AD with significant levels of CVD is frequently labeled mixed dementia (or sometimes AD-CVD), and the differentiation of these two neuropathologies (AD, AD-CVD) from each other is challenging, especially at early stages. In this study, we compared the gray matter (GM) and white matter (WM) volumes in AD (n = 83) and AD-CVD (n = 37) individuals compared with those of cognitively healthy controls (n = 85) using voxel-based morphometry (VBM) of their MRI scans. The control individuals, matched for age and sex with our two dementia groups, were taken from the ADNI. The VBM analysis showed widespread patterns of significantly lower GM and WM volume in both dementia groups compared to the control group ( P < .05, family-wise error corrected). While comparing with AD-CVD, the AD group mainly demonstrated a trend of lower volumes in the GM of the left putamen and right hippocampus and WM of the right thalamus (uncorrected P < .005 with cluster threshold, K = 10). The AD-CVD group relative to AD tended to present lower GM and WM volumes, mainly in the cerebellar lobules and right brainstem regions, respectively (uncorrected P < .005 with cluster threshold, K = 10). Although finding a discriminatory feature in structural MRI data between AD and AD-CVD neuropathologies is challenging, these results provide preliminary evidence that demands further investigation in a larger sample size.

Repetitive transcranial magnetic stimulation (rTMS) is used clinically to treat major depression and has more recently been applied as a potential treatment for Alzheimer’s disease (AD). Given that the rTMS treatment protocols for AD are similar to those used for depression, we investigated whether the AD participants’ cognition change after rTMS was, in part, due to a change in depressive level. Twenty-eight participants of an rTMS treatment study for AD participated in this study. We collected cognitive measures to partition them into 2 groups of subjects with marked or moderate responses (n = 13) and those with responses of small or none (n = 15). Besides, we recorded pre and post Electrovestibulography (EVestG) signals, and 2 EVestG features targeting depression were calculated from the averaged field potential curve (FP_ave) and low-frequency modulation of the recorded firing pattern (33-interval histogram [IH33]), respectively. We then compared these features in the above-mentioned cognitive-wise response groups. The FP_ave and IH33 depression-related features showed no substantial difference between pre- and post-treatment in either group in response to rTMS treatment. The change in these EVestG depression features of the AD participants was also poorly correlated with Alzheimer’s Disease Assessment Scale-Cognitive Subscale (ADAS-Cog) change with treatment. This study’s results demonstrate that cognitive improvement post rTMS is not predominantly a result of an improvement in depression.

With the increasing growth of technology, image security is hampering day to day. Now a watermarking technique which ensures security with less computational effort is the best solution. In this paper differential embedding and chirkov map based image watermarking in transformed domain is proposed. Here, Chirikov map is employed for scrambling the watermark providing security to the method. 2nd level DWT is applied to the host image and the middle band coefficients are chosen to maintain balance between imperceptibility and robustness. These coefficients are DCT transformed for energy compaction and zigzag scanning is performed to cluster the highly correlated coefficients. The concept of differential signaling is used to embed the watermark into the highly correlated coefficients of the host image. The use of different strength factor as secret key and control parameters in Chirikov map will ensure security. At the end section, NCC, MSE and PSNR is calculated as performance parameter to evaluate this method and comparison with the existing method is also discussed and our proposed method shows robustness and imperceptibility against a numbers of image processing attacks.