scholarly journals Predicting Working Memory in Healthy Older Adults Using Real-Life Language and Social Context Information: A Machine Learning Approach (Preprint)

JMIR Aging ◽  
10.2196/28333 ◽  
2021 ◽  
Author(s):  
Andrea Ferrario ◽  
Minxia Luo ◽  
Angelina J. Polsinelli ◽  
Suzanne A. Moseley ◽  
Matthias R. Mehl ◽  
...  
Keyword(s):  
Machine Learning ◽  
Older Adults ◽  
Working Memory ◽  
Social Context ◽  
Real Life ◽  
Context Information ◽  
Learning Approach ◽  
Healthy Older Adults ◽  
Machine Learning Approach

Predicting Working Memory in Healthy Older Adults Using Real-Life Language and Social Context Information: A Machine Learning Approach (Preprint)

2021 ◽  
Author(s):  
Andrea Ferrario ◽  
Minxia Luo ◽  
Angelina J. Polsinelli ◽  
Suzanne A. Moseley ◽  
Matthias R. Mehl ◽  
...  
Keyword(s):  
Machine Learning ◽  
Older Adults ◽  
Working Memory ◽  
Social Context ◽  
Cognitive Decline ◽  
Language Use ◽  
Real Life ◽  
Context Information ◽  
Healthy Older Adults ◽  
Behavioral Indicators

BACKGROUND Language use and social interactions have demonstrated a close relationship with cognitive measures. It is important to improve the understanding of language use and behavioral indicators from social context to study the early prediction of cognitive decline among healthy populations of older adults. OBJECTIVE This study aims at predicting an important cognitive ability, working memory, of n=98 healthy older adults participating in a four days-long naturalistic observation study. We used linguistic measures, part-of-speech (POS) tags and social context information extracted from 7450 real-life audio recordings of their everyday conversations. METHODS The methods in this study comprise 1) the generation of linguistic measures (representing idea density, vocabulary richness, and grammatical complexity) and POS-tags with natural language processing (NLP) from the transcripts of real-life conversations, and 2) the training of machine learning models to predict working memory using linguistic measures, POS-tags and social context information. We measured working memory using the 1) “Keep Track” test, 2) “Consonant Updating” test, and 3) a composite score of “Keep Track” and “Consonant Updating.” We trained machine learning models using random forests (RF), implementing repeated cross-validation with different numbers of folds and repeats and recursive feature elimination to avoid overfitting. RESULTS For all three prediction routines, models comprising linguistic measures, POS-tags and social coded information improved the baseline performance on the validation folds and on the whole dataset. The best model for the “Keep Track” prediction routine comprises linguistic measures, POS-tags and social context variables, with R^2=0.75. The best models for “Consonant Updating” and the composite working memory score comprise POS-tags and linguistic measures, with R^2=0.40 and R^2=0.45 respectively. The performance of the best models of all three prediction routines is in line with (or it improves) the one of benchmarks in the literature on the modeling of cognitive abilities with behavioral indicators. CONCLUSIONS The results suggest that machine learning and NLP may support the prediction of working memory using, in particular, linguistic measures and social context information extracted from the everyday conversations of healthy older adults. Our findings may support the design of an early warning system to be used in longitudinal studies that collects cognitive ability scores and records real-life conversations unobtrusively. This system may support the timely detection of early cognitive decline. In particular, the use of a privacy-sensitive passive monitoring technology would allow designing a program of interventions to enable strategies and treatments to decrease or avoid early cognitive decline.

scholarly journals A Median-Based Machine-Learning Approach for Predicting Random Sampling Bernoulli Distribution Parameter

2019 ◽  
Vol 06 (01) ◽  
pp. 17-28 ◽  
Author(s):  
Hoang Pham ◽  
David H. Pham
Keyword(s):  
Machine Learning ◽  
Population Distribution ◽  
Real Life ◽  
Population Data ◽  
Correction Method ◽  
Machine Learning Techniques ◽  
Learning Approach ◽  
Large Sample Size ◽  
Bernoulli Distribution ◽  
Machine Learning Approach

In real-life applications, we often do not have population data but we can collect several samples from a large sample size of data. In this paper, we propose a median-based machine-learning approach and algorithm to predict the parameter of the Bernoulli distribution. We illustrate the proposed median approach by generating various sample datasets from Bernoulli population distribution to validate the accuracy of the proposed approach. We also analyze the effectiveness of the median methods using machine-learning techniques including correction method and logistic regression. Our results show that the median-based measure outperforms the mean measure in the applications of machine learning using sampling distribution approaches.

scholarly journals Assessing the Heterogeneity of Complaints Related to Tinnitus and Hyperacusis from an Unsupervised Machine Learning Approach: An Exploratory Study

2020 ◽  
Vol 25 (4) ◽  
pp. 174-189 ◽  
Author(s):  
Guillaume  Palacios ◽  
Arnaud Noreña ◽  
Alain Londero
Keyword(s):  
Machine Learning ◽  
Statistical Analysis ◽  
Language Processing ◽  
Exploratory Study ◽  
Latent Dirichlet Allocation ◽  
Suicide Attempts ◽  
Real Life ◽  
Supervised Machine Learning ◽  
Learning Approach ◽  
Machine Learning Approach

Introduction: Subjective tinnitus (ST) and hyperacusis (HA) are common auditory symptoms that may become incapacitating in a subgroup of patients who thereby seek medical advice. Both conditions can result from many different mechanisms, and as a consequence, patients may report a vast repertoire of associated symptoms and comorbidities that can reduce dramatically the quality of life and even lead to suicide attempts in the most severe cases. The present exploratory study is aimed at investigating patients’ symptoms and complaints using an in-depth statistical analysis of patients’ natural narratives in a real-life environment in which, thanks to the anonymization of contributions and the peer-to-peer interaction, it is supposed that the wording used is totally free of any self-limitation and self-censorship. Methods: We applied a purely statistical, non-supervised machine learning approach to the analysis of patients’ verbatim exchanged on an Internet forum. After automated data extraction, the dataset has been preprocessed in order to make it suitable for statistical analysis. We used a variant of the Latent Dirichlet Allocation (LDA) algorithm to reveal clusters of symptoms and complaints of HA patients (topics). The probability of distribution of words within a topic uniquely characterizes it. The convergence of the log-likelihood of the LDA-model has been reached after 2,000 iterations. Several statistical parameters have been tested for topic modeling and word relevance factor within each topic. Results: Despite a rather small dataset, this exploratory study demonstrates that patients’ free speeches available on the Internet constitute a valuable material for machine learning and statistical analysis aimed at categorizing ST/HA complaints. The LDA model with K = 15 topics seems to be the most relevant in terms of relative weights and correlations with the capability to individualizing subgroups of patients displaying specific characteristics. The study of the relevance factor may be useful to unveil weak but important signals that are present in patients’ narratives. Discussion/Conclusion: We claim that the LDA non-supervised approach would permit to gain knowledge on the patterns of ST- and HA-related complaints and on patients’ centered domains of interest. The merits and limitations of the LDA algorithms are compared with other natural language processing methods and with more conventional methods of qualitative analysis of patients’ output. Future directions and research topics emerging from this innovative algorithmic analysis are proposed.

Predicting persistent depressive symptoms in older adults: A machine learning approach to personalised mental healthcare

2019 ◽  
Vol 246 ◽  
pp. 857-860 ◽  
Author(s):  
Christopher M. Hatton ◽  
Lewis W. Paton ◽  
Dean McMillan ◽  
James Cussens ◽  
Simon Gilbody ◽  
...  
Keyword(s):  
Machine Learning ◽  
Older Adults ◽  
Depressive Symptoms ◽  
Mental Healthcare ◽  
Learning Approach ◽  
Machine Learning Approach

scholarly journals Connectomic Underpinnings of Working Memory Deficits in Schizophrenia: Evidence From a replication fMRI study

2020 ◽  
Vol 46 (4) ◽  
pp. 916-926 ◽  
Author(s):  
Jie Yang ◽  
Weidan Pu ◽  
Guowei Wu ◽  
Eric Chen ◽  
Edwin Lee ◽  
...  
Keyword(s):  
Machine Learning ◽  
Working Memory ◽  
Negative Symptoms ◽  
Clinical Symptoms ◽  
Linear Regression Analysis ◽  
Symptom Burden ◽  
Learning Approach ◽  
Brain Connectome ◽  
Graph Properties ◽  
Machine Learning Approach

Abstract Background Working memory (WM) deficit is a key feature of schizophrenia that relates to a generalized neural inefficiency of extensive brain areas. To date, it remains unknown how these distributed regions are systemically organized at the connectome level and how the disruption of such organization brings about the WM impairment seen in schizophrenia. Methods We used graph theory to examine the neural efficiency of the functional connectome in different granularity in 155 patients with schizophrenia and 96 healthy controls during a WM task. These analyses were repeated in another independent dataset (81 patients and 54 controls). Linear regression analysis was used to test associations of altered graph properties, clinical symptoms, and WM accuracy in patients. A machine-learning approach was adopted to study the ability of multivariate connectome features from one dataset to discriminate patients from controls in the second dataset. Results Small-worldness of the whole-brain connectome was significantly increased in schizophrenia during the WM task; this increase is related to better (though subpar) WM accuracy in patients with more severe negative symptom burden. There was a shift in the degree distribution to a more homogeneous form in patients. The machine-learning approach classified a new set of patients from controls with 84.3% true-positivity rate for schizophrenia and 71.6% overall accuracy. Conclusions We demonstrate a putative mechanistic link between connectome topology, hub redistribution, and impaired n-back performance in schizophrenia. The task-dependent modulation of the connectome relates to, but remains inefficient in, improving the performance above par in the presence of severe negative symptoms.

Personalised Accelerometer Cut-point Prediction for Older Adults’ Movement Behaviours using a Machine Learning approach.

2021 ◽  
pp. 106165
Author(s):  
Nonso Nnamoko ◽  
Luis Adrián Cabrera-Diego ◽  
Daniel Campbell ◽  
George Sanders ◽  
Stuart J. Fairclough ◽  
...  
Keyword(s):  
Machine Learning ◽  
Older Adults ◽  
Learning Approach ◽  
Cut Point ◽  
Machine Learning Approach
Sign in / Sign up

Export Citation Format

Share Document