Dataset Information

Predicting natural language descriptions of mono-molecular odorants.

ABSTRACT: There has been recent progress in predicting whether common verbal descriptors such as "fishy", "floral" or "fruity" apply to the smell of odorous molecules. However, accurate predictions have been achieved only for a small number of descriptors. Here, we show that applying natural-language semantic representations on a small set of general olfactory perceptual descriptors allows for the accurate inference of perceptual ratings for mono-molecular odorants over a large and potentially arbitrary set of descriptors. This is noteworthy given that the prevailing view is that humans' capacity to identify or characterize odors by name is poor. We successfully apply our semantics-based approach to predict perceptual ratings with an accuracy higher than 0.5 for up to 70 olfactory perceptual descriptors, a ten-fold increase in the number of descriptors from previous attempts. These results imply that the semantic distance between descriptors defines the equivalent of an odorwheel.

SUBMITTER: Gutierrez ED

PROVIDER: S-EPMC6255800 | biostudies-literature | 2018 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting natural language descriptions of mono-molecular odorants.

Gutiérrez E Darío ED Dhurandhar Amit A Keller Andreas A Meyer Pablo P Cecchi Guillermo A GA

Nature communications 20181126 1

There has been recent progress in predicting whether common verbal descriptors such as "fishy", "floral" or "fruity" apply to the smell of odorous molecules. However, accurate predictions have been achieved only for a small number of descriptors. Here, we show that applying natural-language semantic representations on a small set of general olfactory perceptual descriptors allows for the accurate inference of perceptual ratings for mono-molecular odorants over a large and potentially arbitrary s ...[more]

PMID: 30478272

Similar Datasets

Project description:BackgroundIf individual differences are relevant and prominent features of personality, then they are expected to be encoded in natural language, thus manifesting themselves in single words. Recently, the quantification of text data using advanced natural language processing techniques offers innovative opportunities to map people's own words and narratives to their responses to self-reports. Here, we demonstrate the usefulness of self-descriptions in natural language and what we tentatively call Quantitative Semantic Test Theory (QuSTT) to validate two short inventories that measure character traits.MethodIn Study 1, participants (N 1 = 997) responded to the Short Character Inventory, which measures self-directedness, cooperativeness, and self-transcendence. In Study 2, participants (N 2 = 2373) responded to Short Dark Triad, which measures Machiavellianism, narcissism, and psychopathy. In both studies, respondents were asked to generate 10 self-descriptive words. We used the Latent Semantic Algorithm to quantify the meaning of each trait using the participants' self-descriptive words. We then used these semantic representations to predict the self-reported scores. In a second set of analyses, we used word-frequency analyses to map the self-descriptive words to each of the participants' trait scores (i.e., one-dimensional analysis) and character profiles (i.e., three-dimensional analysis).ResultsThe semantic representation of each character trait was related to each corresponding self-reported score. However, participants' self-transcendence and Machiavellianism scores demonstrated similar relationships to all three semantic representations of the character traits in their respective personality model. The one-dimensional analyses showed that, for example, "loving" was indicative of both high cooperativeness and self-transcendence, while "compassionate," "kind," and "caring" was unique for individuals high in cooperativeness. The words "kind" and "caring" indicated low levels of Machiavellianism and psychopathy, whereas "shy" or "introvert" indicated low narcissism. We also found specific keywords that unify or that make the individuals in some profiles unique.ConclusionDespite being short, both inventories capture individuals' identity as expected. Nevertheless, our method also points out some shortcomings and overlaps between traits measured with these inventories. We suggest that self-descriptive words can be quantified to validate measures of psychological constructs (e.g., prevalence in self-descriptions or QuSTT) and that this method may complement traditional methods for testing the validity of psychological measures.

Project description:The ability to predict psychiatric readmission would facilitate the development of interventions to reduce this risk, a major driver of psychiatric health-care costs. The symptoms or characteristics of illness course necessary to develop reliable predictors are not available in coded billing data, but may be present in narrative electronic health record (EHR) discharge summaries. We identified a cohort of individuals admitted to a psychiatric inpatient unit between 1994 and 2012 with a principal diagnosis of major depressive disorder, and extracted inpatient psychiatric discharge narrative notes. Using these data, we trained a 75-topic Latent Dirichlet Allocation (LDA) model, a form of natural language processing, which identifies groups of words associated with topics discussed in a document collection. The cohort was randomly split to derive a training (70%) and testing (30%) data set, and we trained separate support vector machine models for baseline clinical features alone, baseline features plus common individual words and the above plus topics identified from the 75-topic LDA model. Of 4687 patients with inpatient discharge summaries, 470 were readmitted within 30 days. The 75-topic LDA model included topics linked to psychiatric symptoms (suicide, severe depression, anxiety, trauma, eating/weight and panic) and major depressive disorder comorbidities (infection, postpartum, brain tumor, diarrhea and pulmonary disease). By including LDA topics, prediction of readmission, as measured by area under receiver-operating characteristic curves in the testing data set, was improved from baseline (area under the curve 0.618) to baseline+1000 words (0.682) to baseline+75 topics (0.784). Inclusion of topics derived from narrative notes allows more accurate discrimination of individuals at high risk for psychiatric readmission in this cohort. Topic modeling and related approaches offer the potential to improve prediction using EHRs, if generalizability can be established in other clinical cohorts.

Project description:BackgroundPatient-reported outcomes (PRO) allow clinicians to measure health-related quality of life (HRQOL) and understand patients' treatment priorities, but obtaining PRO requires surveys which are not part of routine care. We aimed to develop a preliminary natural language processing (NLP) pipeline to extract HRQOL trajectory based on deep learning models using patient language.Materials and methodsOur data consisted of transcribed interviews of 100 patients undergoing surgical intervention for low-risk thyroid cancer, paired with HRQOL assessments completed during the same visits. Our outcome measure was HRQOL trajectory measured by the SF-12 physical and mental component scores (PCS and MCS), and average THYCA-QoL score.We constructed an NLP pipeline based on BERT, a modern deep language model that captures context semantics, to predict HRQOL trajectory as measured by the above endpoints. We compared this to baseline models using logistic regression and support vector machines trained on bag-of-words representations of transcripts obtained using Linguistic Inquiry and Word Count (LIWC). Finally, given the modest dataset size, we implemented two data augmentation methods to improve performance: first by generating synthetic samples via GPT-2, and second by changing the representation of available data via sequence-by-sequence pairing, which is a novel approach.ResultsA BERT-based deep learning model, with GPT-2 synthetic sample augmentation, demonstrated an area-under-curve of 76.3% in the classification of HRQOL accuracy as measured by PCS, compared to the baseline logistic regression and bag-of-words model, which had an AUC of 59.9%. The sequence-by-sequence pairing method for augmentation had an AUC of 71.2% when used with the BERT model.ConclusionsNLP methods show promise in extracting PRO from unstructured narrative data, and in the future may aid in assessing and forecasting patients' HRQOL in response to medical treatments. Our experiments with optimization methods suggest larger amounts of novel data would further improve performance of the classification model.

Project description:BackgroundMachine learning (ML) achieves better predictions of postoperative mortality than previous prediction tools. Free-text descriptions of the preoperative diagnosis and the planned procedure are available preoperatively. Because reading these descriptions helps anesthesiologists evaluate the risk of the surgery, we hypothesized that deep learning (DL) models with unstructured text could improve postoperative mortality prediction. However, it is challenging to extract meaningful concept embeddings from this unstructured clinical text.ObjectiveThis study aims to develop a fusion DL model containing structured and unstructured features to predict the in-hospital 30-day postoperative mortality before surgery. ML models for predicting postoperative mortality using preoperative data with or without free clinical text were assessed.MethodsWe retrospectively collected preoperative anesthesia assessments, surgical information, and discharge summaries of patients undergoing general and neuraxial anesthesia from electronic health records (EHRs) from 2016 to 2020. We first compared the deep neural network (DNN) with other models using the same input features to demonstrate effectiveness. Then, we combined the DNN model with bidirectional encoder representations from transformers (BERT) to extract information from clinical texts. The effects of adding text information on the model performance were compared using the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC). Statistical significance was evaluated using P<.05.ResultsThe final cohort contained 121,313 patients who underwent surgeries. A total of 1562 (1.29%) patients died within 30 days of surgery. Our BERT-DNN model achieved the highest AUROC (0.964, 95% CI 0.961-0.967) and AUPRC (0.336, 95% CI 0.276-0.402). The AUROC of the BERT-DNN was significantly higher compared to logistic regression (AUROC=0.952, 95% CI 0.949-0.955) and the American Society of Anesthesiologist Physical Status (ASAPS AUROC=0.892, 95% CI 0.887-0.896) but not significantly higher compared to the DNN (AUROC=0.959, 95% CI 0.956-0.962) and the random forest (AUROC=0.961, 95% CI 0.958-0.964). The AUPRC of the BERT-DNN was significantly higher compared to the DNN (AUPRC=0.319, 95% CI 0.260-0.384), the random forest (AUPRC=0.296, 95% CI 0.239-0.360), logistic regression (AUPRC=0.276, 95% CI 0.220-0.339), and the ASAPS (AUPRC=0.149, 95% CI 0.107-0.203).ConclusionsOur BERT-DNN model has an AUPRC significantly higher compared to previously proposed models using no text and an AUROC significantly higher compared to logistic regression and the ASAPS. This technique helps identify patients with higher risk from the surgical description text in EHRs.

Dataset Information

Predicting natural language descriptions of mono-molecular odorants.

Publications

Predicting natural language descriptions of mono-molecular odorants.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets