Predicting Alzheimer's Disease Progression Using a Versatile Sequence-Length-Adaptive Encoder-Decoder LSTM Architecture.

Detecting Alzheimer's disease (AD) accurately at an early stage is critical for planning and implementing disease-modifying treatments that can help prevent the progression to severe stages of the disease. In the existing literature, diagnostic test scores and clinical status have been provided for specific time points, and predicting the disease progression poses a significant challenge. However, few studies focus on longitudinal data to build deep-learning models for AD detection. These models are not stable to be relied upon in real medical settings due to a lack of adaptive training and testing. We aim to predict the individual's diagnostic status for the next six years in an adaptive manner where prediction performance improves with the number of patient visits. This study presents a Sequence-Length Adaptive Encoder-Decoder Long Short-Term Memory (SLA-ED LSTM) deep-learning model on longitudinal data obtained from the Alzheimer's Disease Neuroimaging Initiative archive. In the suggested approach, decoder LSTM dynamically adjusts to accommodate variations in training sequence length and inference length rather than being constrained to a fixed length. We evaluated the model performance for various sequence lengths and found that for inference length one, sequence length nine gives the highest average test accuracy and area under the receiver operating characteristic curves of 0.920 and 0.982, respectively. This insight suggests that data from nine visits effectively captures meaningful cognitive status changes and is adequate for accurate model training. We conducted a comparative analysis of the proposed model against state-of-the-art methods, revealing a significant improvement in disease progression prediction over the previous methods.

Contactless Monitoring Of Human Vitals: A Study With Simultaneous Measurements Using FMCW Radar And Thermal Camera.

This paper proposes contactless monitoring of Heart Rate (HR) and Breath Rate (BR) with simultaneous measurements using Frequency Modulated Continuous Wave (FMCW) radar and thermal camera. The radar collects the body movement signals which include Random Body Movements (RBMs). Non-negative Matrix Factorization (NMF) and Wavelet analysis were used on this signal to get the accurate values of HR and BR. Similarly, with thermal imaging, nostril and forehead regions are tracked to estimate the values of BR as well as HR. We conducted an experiment with 50 subjects to find similarities in the performance of radar and thermal camera while measuring HR and BR. Simultaneously, these two methods have been validated with pulse oximeter and visual camera. From the visual camera, we can get the abdominal movements on which the BR can be ascertained whereas pulse oximeter gives us the HR. Radar signals are degraded because of large RBMs whereas thermal signals get distorted because of sudden temperature changes in the surroundings, sweating, and occlusion. We used a Signal Quality Metric (SQM) to ascertain the measurement quality of the vital signs. This SQM-based approach can further be used for sensor fusion to build a robust contactless system to monitor vital signs.Clinical relevance- Contactless and accurate measurement of HR and BR is very essential for continuous and comfortable monitoring of vitals. In this paper, we combine both FMCW radar and thermal camera so that one can complement the other in adverse scenarios on the basis of signal quality.

A Novel Technique for Detecting Depressive Disorder: A Speech Database-Based Approach.

Depression is the second most diagnosed disease in the world and is predicted to be the highest by the year 2030. Depressive disorder impacts both on mentally and physically, thus diagnosing this disorder in early stage is essential. Automatic Depression Detection (ADD) system via speech can greatly facilitate early-stage depression diagnosis. Development of such systems demands a standard balanced database. In this work, we present a novel labeled audio distress interview database. To our knowledge, this is the first depression database in Bengali language that contains audio responses from depressed and non-depressed subjects. Alongside this, we present a set of hand-crafted acoustic features that effectively detect depression mood using speech signals. Finally, we justify the quality of our developed database and the efficacy of the feature set in predicting depression using a baseline machine learning (ML) model. We believe that the annotated database will be a valuable resource for use by treating clinicians.Clinical Relevance-This research reports a new speech database in Bengali language for depression detection. This database can be used in healthcare by developing an automatic prediction model for depression detection.

Accurate Prediction of Alzheimer's Disease Progression Trajectory via a Novel Encoder-Decoder LSTM Architecture.

With an increase in life expectancy, there has been an increase in the aged population globally, and around 10% of this population suffers from Alzheimer's disease. Alzheimer's hugely impacts the quality of life and well-being of older adults and their caregivers. Thus, it is an emerging challenge to improve the early diagnosis and prognosis of the disease. Detecting hidden patterns in complex multidimensional datasets using recent advancements in machine learning provides a tremendous opportunity to meet this crucial need. In this study, using multimodal features and an individual's clinical status on one or more time points, we aimed to predict the individual's cognitive test scores, changes in Magnetic Resonance Imaging features, and the individual's diagnostic status for the next three years. We presented a novel Encoder-Decoder Long Short-Term Memory deep-learning model architecture for implementing our prediction. We applied it to data from the Alzheimer's Disease Neuroimaging Initiative, comprising longitudinal data of 1737 participants and 12,741 instances. The proposed model was found to be competent, with a validation accuracy of 0.941, a multi-class area under the curve of 0.960, and a test accuracy of 0.88 in identifying the various stages of Alzheimer's disease progression in patients with an initially cognitively normal or mild cognitive impairment which is a significant improvement over previous methods.Clinical relevance- The proposed approach can help improve diagnostic understanding of Alzheimer's Disease progression and assist in the early detection of various stages of Alzheimer's Disease based on clinical heterogeneity.

Exploring 'Little-c' Creativity Through Eye-parameters.

Creativity can be divided into four factors, namely, mini c, little c, Pro C and Big C. Little c measures creativity required in doing daily activities which are essential for stable living. In this study little c is categorized into three levels of high, medium and low and its relationship with occulometric is studied to see if higher values obtained in the test also reflect in their eye movement patterns. Occulometric is studied using eye movement patterns such as fixations, saccades, and pupil diameter. Analysis by One way Anova shows differences in the three groups. It is found that high creativity group has higher number of fixations, low peak velocity, higher saccadic duration and larger mean pupil duration in comparison to its other counterparts. Clinical Relevance- Creativity is an important aspect of everyday living. Understanding this cognitive process through a bio-marker would help in validating a mental capability through eye parameters.

Multimodal prediction of trait emotional intelligence-Through affective changes measured using non-contact based physiological measures.

Inability to efficiently deal with emotionally laden situations, often leads to poor interpersonal interactions. This adversely affects the individual's psychological functioning. A higher trait emotional intelligence (EI) is not only associated with psychological wellbeing, educational attainment, and job-related success, but also with willingness to seek professional and non-professional help for personal-emotional problems, depression and suicidal ideation. Thus, it is important to identify low (EI) individuals who are more prone to mental health problems than their high EI counterparts, and give them the appropriate EI training, which will aid in preventing the onset of various mood related disorders. Since people may be unaware of their level of EI/emotional skills or may tend to fake responses in self-report questionnaires in high stake situations, a system that assesses EI using physiological measures can prove affective. We present a multimodal method for detecting the level of trait Emotional intelligence using non-contact based autonomic sensors. To our knowledge, this is the first work to predict emotional intelligence level from physiological/autonomic (cardiac and respiratory) response patterns to emotions. Trait EI of 50 users was measured using Schutte Self Report Emotional Intelligence Test (SSEIT) along with their cardiovascular and respiratory data, which was recorded using FMCW radar sensor both at baseline and while viewing affective movie clips. We first examine relationships between users' Trait EI scores and autonomic response and reactivity to the clips. Our analysis suggests a significant relationship between EI and autonomic response and reactivity. We finally attempt binary EI level detection using linear SVM. We also attempt to classify each sub factor of EI, namely-perception of emotion, managing own emotions, managing other's emotions, and utilization of emotions. The proposed method achieves an EI classification accuracy of 84%, while accuracies ranging from 58 to 76% is achieved for recognition of the sub factors. This is the first step towards identifying EI of an individual purely through physiological responses. Limitation and future directions are discussed.

Determinants of vaccine uptake in HIV-affected families from West Bengal.

Children living with Human Immunodeficiency virus (HIV; CLH) have special vaccine needs. Determinants of household-level uptake of vaccines need to be examined in high-risk families with CLH. We previously conducted a study on the impact of Haemophilus influenzae type b conjugate vaccine and pneumococcal conjugate vaccine (PCV-13) in 125 HIV-affected families and 47 HIV-unaffected families in West Bengal. We then interviewed 99 of these 172 families who had participated in the study to understand the household-level factors that determine vaccine uptake. Sixty-four of the 99 families had one or more CLH. Within these 64 families, 30% of CLH had missed vaccines under the universal immunization program (UIP), compared to only 6% of HIV-uninfected children (HUC) (p = .001). Maternal HIV positivity in a family increased risk of missing UIP vaccines nearly five times (4.82, p = .001). Almost all families accessed UIP vaccines at local primary vaccination centers, but 14% of families experienced stigma due to HIV and avoided getting one or more vaccine doses. In contrast, in our study, 100% of HIV-affected families actively sought PCV-13 and HibCV, despite having to travel. Factors that influenced uptake included awareness generation and activation by an outreach worker and availability of vaccines on pick-up days for anti-retroviral therapy. Eighty-six percent of families strongly recommended PCV-13 to other families. To conclude, while we found that CLH have barriers to getting vaccinations, a program designed to take into consideration the obstacles that HIV-affected families face showed a high rate of vaccine uptake.

Development of Objective Evidence in Rorschach Ink Blot Test: An Eye Tracking Study.

The Rorschach inkblot test (RIBT) is a standardized projective technique. It uses a subjective way of collecting and mapping responses of different regions like large (D) and small details (d). In this paper, eye tracking parameters like Initial Fixation Location, SF Ratio, Mean Fixation Duration and Mean Return are used to develop some objective measures which would be helpful in the assessment of the Rorschach responses. The study was conducted on 25 normal subjects who were administered RIBT cards I, II and X. The result shows an initial tendency to fixate in the central regions of the Rorschach cards. Computation of SF ratio helps in understanding most frequently fixated regions leading to popular response. Certain locations of each card have high attentional value where most shifts and fixations occur. The study supplements to the information obtained by the subjective scoring of RIBT and also indicates that specific eye tracking parameters could be an objective marker for personality assessment with RIBT.

A Multimodal System for Assessing Alertness Levels Due to Cognitive Loading.

This paper proposes a scheme for assessing the alertness levels of an individual using simultaneous acquisition of multimodal physiological signals and fusing the information into a single metric for quantification of alertness. The system takes electroencephalogram, high-speed image sequence, and speech data as inputs. Certain parameters are computed from each of these measures as indicators of alertness and a metric is proposed using a fusion of the parameters for indicating alertness level of an individual at an instant. The scheme has been validated experimentally using standard neuropsychological tests, such as the Visual Response Test (VRT), Auditory Response Test (ART), a Letter Counting (LC) task, and the Stroop Test. The tests are used both as cognitive tasks to induce mental fatigue as well as tools to gauge the present degree of alertness of the subject. Correlation between the measures has been studied and the experimental variables have been statistically analyzed using measures such as multivariate linear regression and analysis of variance. Correspondence of trends obtained from biomarkers and neuropsychological measures validate the usability of the proposed metric.