Detection of dementia on voice recordings using deep learning: a Framingham Heart Study

By kharp September 2nd, 2021 in Publications

(Source: BMC Alzheimer's Research and Therapy)

New publication from Chonghua Xue, Bioinformatics Analyst and Dr. Vijaya Kolachalama, Assistant Professor of Medicine in the Section of Computational Biomedicine. See below for a brief summary and click the link to read the whole article.

Background

Identification of reliable, affordable, and easy-to-use strategies for detection of dementia is sorely needed. Digital technologies, such as individual voice recordings, offer an attractive modality to assess cognition but methods that could automatically analyze such data are not readily available.

Methods and findings

We used 1264 voice recordings of neuropsychological examinations administered to participants from the Framingham Heart Study (FHS), a community-based longitudinal observational study. The recordings were 73 min in duration, on average, and contained at least two speakers (participant and examiner). Of the total voice recordings, 483 were of participants with normal cognition (NC), 451 recordings were of participants with mild cognitive impairment (MCI), and 330 were of participants with dementia (DE). We developed two deep learning models (a two-level long short-term memory (LSTM) network and a convolutional neural network (CNN)), which used the audio recordings to classify if the recording included a participant with only NC or only DE and to differentiate between recordings corresponding to those that had DE from those who did not have DE (i.e., NDE (NC+MCI)). Based on 5-fold cross-validation, the LSTM model achieved a mean (±std) area under the receiver operating characteristic curve (AUC) of 0.740 ± 0.017, mean balanced accuracy of 0.647 ± 0.027, and mean weighted F1 score of 0.596 ± 0.047 in classifying cases with DE from those with NC. The CNN model achieved a mean AUC of 0.805 ± 0.027, mean balanced accuracy of 0.743 ± 0.015, and mean weighted F1 score of 0.742 ± 0.033 in classifying cases with DE from those with NC. For the task related to the classification of participants with DE from NDE, the LSTM model achieved a mean AUC of 0.734 ± 0.014, mean balanced accuracy of 0.675 ± 0.013, and mean weighted F1 score of 0.671 ± 0.015. The CNN model achieved a mean AUC of 0.746 ± 0.021, mean balanced accuracy of 0.652 ± 0.020, and mean weighted F1 score of 0.635 ± 0.031 in classifying cases with DE from those who were NDE.

Conclusion

This proof-of-concept study demonstrates that automated deep learning-driven processing of audio recordings of neuropsychological testing performed on individuals recruited within a community cohort setting can facilitate dementia screening.

Click here to read the whole paper.

Multi-resolution characterization of molecular taxonomies in bulk and single-cell transcriptomics data

By kharp July 15th, 2021 in Publications

(Source: Oxford Academic)

New publication from Dr. Stefano Monti, Associate Professor of Medicine in the Section of Computational Biomedicine. See below for a brief summary and click the link to read the whole article.

As high-throughput genomics assays become more efficient and cost effective, their utilization has become standard in large-scale biomedical projects. These studies are often explorative, in that relationships between samples are not explicitly defined a priori, but rather emerge from data-driven discovery and annotation of molecular subtypes, thereby informing hypotheses and independent evaluation. Here, we present K2Taxonomer, a novel unsupervised recursive partitioning algorithm and associated R package that utilize ensemble learning to identify robust subgroups in a ‘taxonomy-like’ structure. K2Taxonomer was devised to accommodate different data paradigms, and is suitable for the analysis of both bulk and single-cell transcriptomics, and other ‘-omics’, data. For each of these data types, we demonstrate the power of K2Taxonomer to discover known relationships in both simulated and human tissue data. We conclude with a practical application on breast cancer tumor infiltrating lymphocyte (TIL) single-cell profiles, in which we identified co-expression of translational machinery genes as a dominant transcriptional program shared by T cells subtypes, associated with better prognosis in breast cancer tissue bulk expression data.

Click here to read more.

Deep learning-driven quantification of interstitial fibrosis in digitized kidney biopsies

By kharp May 27th, 2021 in Publications

(Source: The American Journal of Pathology)

New publication from Dr. Vijaya Kolachalama, Assistant Professor of Medicine in the Section of Computational Biomedicine. See below for a brief summary and click the link to read the whole article.

Interstitial fibrosis and tubular atrophy (IFTA) on a renal biopsy are strong indicators of disease chronicity and prognosis. Techniques that are typically used for IFTA grading remain manual, leading to variability among pathologists. Accurate IFTA estimation using computational techniques can reduce this variability and provide quantitative assessment. Using trichrome-stained whole slide images (WSIs) processed from human renal biopsies, we developed a deep learning framework that captured finer pathological structures at high resolution and overall context at the WSI-level to predict IFTA grade. WSIs (n=67) were obtained from The Ohio State University Wexner Medical Center (OSUWMC). Five nephropathologists independently reviewed them and provided fibrosis scores that were converted to IFTA grades: <=10% (None or minimal), 11-25% (Mild), 26-50% (Moderate), and >50% (Severe). The model was developed by associating the WSIs with the IFTA grade determined by majority voting (reference estimate). Model performance was evaluated on WSIs (n=28) obtained from the Kidney Precision Medicine Project (KPMP). There was good agreement on the IFTA grading between the pathologists and the reference estimate (Kappa=0.622±0.071). The accuracy of the DL model was 71.8±5.3% on OSUWMC and 65.0±4.2% on KPMP datasets, respectively. Our approach to analyzing microscopic- and WSI-level changes in renal biopsies attempts to mimic the pathologist and provides a regional and contextual estimation of IFTA. Such methods can assist clinicopathologic diagnosis.

Click here to read the full article.