BACKGROUND: To characterize acoustic features of an infant's cry and use machine learning to provide an objective measurement of behavioral state in a cry-translator. To apply the cry-translation algorithm to colic hypothesizing that these cries sound painful. METHODS: Assessment of 1000 cries in a mobile app (ChatterBaby TM). Training a cry-translation algorithm by evaluating >6000 acoustic features to predict whether infant cry was due to a pain (vaccinations, ear-piercings), fussy, or hunger states. Using the algorithm to predict the behavioral state of infants with reported colic. RESULTS: The cry-translation algorithm was 90.7% accurate for identifying pain cries, and achieved 71.5% accuracy in discriminating cries from fussiness, hunger, or pain. The ChatterBaby cry-translation algorithm overwhelmingly predicted that colic cries were most likely from pain, compared to fussy and hungry states. Colic cries had average pain ratings of 73%, significantly greater than the pain measurements found in fussiness and hunger (p < 0.001, 2-sample t test). Colic cries outranked pain cries by measures of acoustic intensity, including energy, length of voiced periods, and fundamental frequency/pitch, while fussy and hungry cries showed reduced intensity measures compared to pain and colic. CONCLUSIONS: Acoustic features of cries are consistent across a diverse infant population and can be utilized as objective markers of pain, hunger, and fussiness. The ChatterBaby algorithm detected significant acoustic similarities between colic and painful cries, suggesting that they may share a neuronal pathway.
Recent evidence suggests the aging process is accelerated by HIV. Degradation of white matter (WM) has been independently associated with HIV and healthy aging. Thus, WM may be vulnerable to joint effects of HIV and aging. Diffusion‐weighted imaging (DWI) was conducted with HIV‐seropositive (n = 72) and HIV‐seronegative (n = 34) adults. DWI data underwent tractography, which was parcellated into 18 WM tracts of interest (TOIs). Functional Analysis of Diffusion Tensor Tract Statistics (FADTTS) regression was conducted assessing the joint effect of advanced age and HIV on fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD) along TOI fibers. In addition to main effects of age and HIV on WM microstructure, the interactive effect of age and HIV was significantly related to lower FA and higher MD, AD, and RD across all TOIs. The location of findings was consistent with the clinical presentation of HIV‐associated neurocognitive disorders. While older age is related to poorer WM microstructure, its detrimental effect on WM is stronger among HIV+ relative to HIV− individuals. Loss of WM integrity in the context of advancing age may place HIV+ individuals at increased risk for brain and cognitive compromise.
Background: This study sought to validate the clinical utility of multimodal magnetic resonance imaging (MRI) techniques in the assessment of neurodegenerative disorders. We intended to demonstrate that advanced neuroimaging techniques commonly used in research can effectively be employed in clinical practice to accurately differentiate heathy aging and dementia subtypes.Methods: Twenty patients with dementia of the Alzheimer's type (DAT) and 18 patients with Parkinson's disease dementia (PDD) were identified using gold-standard techniques. Twenty-three healthy, age and sex matched control participants were also recruited. All participants underwent multimodal MRI including T1 structural, diffusion tensor imaging (DTI), arterial spin labeling (ASL), and magnetic resonance spectroscopy (MRS). MRI modalities were evaluated by trained neuroimaging readers and were separately assessed using cross-validated, iterative discriminant function analyses with subsequent feature reduction techniques. In this way, each modality was evaluated for its ability to differentiate patients with dementia from healthy controls as well as to differentiate dementia subtypes.Results: Following individual and group feature reduction, each of the multimodal MRI metrics except MRS successfully differentiated healthy aging from dementia and also demonstrated distinct dementia subtypes. Using the following ten metrics, excellent separation (95.5% accuracy, 92.3% sensitivity; 100.0% specificity) was achieved between healthy aging and neurodegenerative conditions: volume of the left frontal pole, left occipital pole, right posterior superior temporal gyrus, left posterior cingulate gyrus, right planum temporale; perfusion of the left hippocampus and left occipital lobe; fractional anisotropy (FA) of the forceps major and bilateral anterior thalamic radiation. Using volume of the left frontal pole, right posterior superior temporal gyrus, left posterior cingulate gyrus, perfusion of the left hippocampus and left occipital lobe; FA of the forceps major and bilateral anterior thalamic radiation, neurodegenerative subtypes were accurately differentiated as well (87.8% accuracy, 95.2% sensitivity; 85.0% specificity). Conclusions: Regional volumetrics, DTI metrics, and ASL successfully differentiated dementia patients from controls with sufficient sensitivity to differentiate dementia subtypes. Similarly, feature reduction results suggest that advanced analyses can meaningfully identify brain regions with the most positive predictive value and discriminant validity. Together, these advanced neuroimaging techniques can contribute significantly to 2 Kuhn et al. Multimodal MRI in the clinic
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.