A machine-learned analysis suggests non-redundant diagnostic information in olfactory subtests

Association between cognition and olfaction-specific parameters in patients with chronic rhinosinusitis

BACKGROUND

Patients with chronic rhinosinusitis (CRS) have reported significantly cognitive and olfactory dysfunction. This study aimed to explore the relationship between cognitive function and olfaction-specific parameters in patients with CRS.

METHODS

A cross-sectional survey method was used to investigate 98 participants, including 75 patients with CRS and 23 healthy controls. Cognitive function and psychophysical olfactory tests were performed. Olfactory cleft endoscopy scale and olfactory cleft computed tomography (CT) scores were obtained. Multivariate logistic regression was used to analyze the risk factors of Mild Cognitive Impairment (MCI) in patients with CRS.

RESULTS

There are significant differences in age, Montreal Cognitive Assessment (MoCA) scores, number of MCI, Lund-Mackay olfactory cleft (LM-OC) score, and blood eosinophil count between CRS with and without olfactory dysfunction groups (all P < 0.05). Total MoCA scores were positively correlated with thresholds-discrimination-identification (TDI) score (r = 0.541, P < 0.001), olfactory threshold (OT) (r = 0.440, P < 0.001), olfactory discrimination (OD) (r = 0.541, P < 0.001), and olfactory identification (OI) (r = 0.382, P = 0.001) scores. Furthermore, total MoCA scores were negatively correlated with LM-OC scores (r =  - 0.351, P = 0.002). After adjusting for patient demographics, only the OD score was an independent risk factor for MCI among patients with CRS (odds ratio = 0.792; P = 0.039). The OD scores less than 11.5 were the best predictor of MCI in patients with CRS.

CONCLUSION

Olfaction-specific clinical parameters were highly correlated with cognitive function in patients with CRS and the OD score was an independent risk factor for MCI in patients with CRS.

Proof-of-concept: SCENTinel 1.1 rapidly discriminates COVID-19-related olfactory disorders

It is estimated that 20%-67% of those with COVID-19 develop olfactory disorders, depending on the SARS-CoV-2 variant. However, there is an absence of quick, population-wide olfactory tests to screen for olfactory disorders. The purpose of this study was to provide a proof-of-concept that SCENTinel 1.1, a rapid, inexpensive, population-wide olfactory test, can discriminate between anosmia (total smell loss), hyposmia (reduced sense of smell), parosmia (distorted odor perception), and phantosmia (odor sensation without a source). Participants were mailed a SCENTinel 1.1 test, which measures odor detection, intensity, identification, and pleasantness, using one of 4 possible odors. Those who completed the test (N = 287) were divided into groups based on their self-reported olfactory function: quantitative olfactory disorder only (anosmia or hyposmia, N = 135), qualitative olfactory disorder only (parosmia and/or phantosmia; N = 86), and normosmia (normal sense of smell; N = 66). SCENTinel 1.1 accurately discriminates quantitative olfactory disorders, qualitative olfactory disorders, and normosmia groups. When olfactory disorders were assessed individually, SCENTinel 1.1 discriminates between hyposmia, parosmia, and anosmia. Participants with parosmia rated common odors less pleasant than those without parosmia. We provide proof-of-concept that SCENTinel 1.1, a rapid smell test, can discriminate quantitative and qualitative olfactory disorders, and is the only direct test to rapidly discriminate parosmia.

Proof-of-concept: SCENTinel 1.1 rapidly discriminates COVID-19 related olfactory disorders

It is estimated that 20-67% of those with COVID-19 develop olfactory disorders, depending on the SARS-CoV-2 variant. However, there is an absence of quick, population-wide olfactory tests to screen for olfactory disorders. The purpose of this study was to provide a proof-of-concept that SCENTinel 1.1, a rapid, inexpensive, population-wide olfactory test, can discriminate between anosmia (total smell loss), hyposmia (reduced sense of smell), parosmia (distorted odor perception), and phantosmia (odor sensation without a source). Participants were mailed a SCENTinel 1.1 test, which measures odor detection, intensity, identification, and pleasantness, using one of four possible odors. Those who completed the test (N = 381) were divided into groups based on their self-reported olfactory function: quantitative olfactory disorder (anosmia or hyposmia, N = 135), qualitative olfactory disorder (parosmia and/or phantosmia; N = 86), and normosmia (normal sense of smell; N = 66). SCENTinel 1.1 accurately discriminates quantitative olfactory disorders, qualitative olfactory disorders, and normosmia groups. When olfactory disorders were assessed individually, SCENTinel 1.1 discriminates between hyposmia, parosmia and anosmia. Participants with parosmia rated common odors less pleasant than those without parosmia. We provide proof-of-concept that SCENTinel 1.1, a rapid smell test, can discriminate quantitative and qualitative olfactory disorders, and is the only direct test to rapidly discriminate parosmia.

Sorting of Odor Dilutions Is a Meaningful Addition to Assessments of Olfactory Function as Suggested by Machine-Learning-Based Analyses

Background: The categorization of individuals as normosmic, hyposmic, or anosmic from test results of odor threshold, discrimination, and identification may provide a limited view of the sense of smell. The purpose of this study was to expand the clinical diagnostic repertoire by including additional tests. Methods: A random cohort of n = 135 individuals (83 women and 52 men, aged 21 to 94 years) was tested for odor threshold, discrimination, and identification, plus a distance test, in which the odor of peanut butter is perceived, a sorting task of odor dilutions for phenylethyl alcohol and eugenol, a discrimination test for odorant enantiomers, a lateralization test with eucalyptol, a threshold assessment after 10 min of exposure to phenylethyl alcohol, and a questionnaire on the importance of olfaction. Unsupervised methods were used to detect structure in the olfaction-related data, followed by supervised feature selection methods from statistics and machine learning to identify relevant variables. Results: The structure in the olfaction-related data divided the cohort into two distinct clusters with n = 80 and 55 subjects. Odor threshold, discrimination, and identification did not play a relevant role for cluster assignment, which, on the other hand, depended on performance in the two odor dilution sorting tasks, from which cluster assignment was possible with a median 100-fold cross-validated balanced accuracy of 77–88%. Conclusions: The addition of an odor sorting task with the two proposed odor dilutions to the odor test battery expands the phenotype of olfaction and fits seamlessly into the sensory focus of standard test batteries.

Machine-Learning Points at Endoscopic, Quality of Life, and Olfactory Parameters as Outcome Criteria for Endoscopic Paranasal Sinus Surgery in Chronic Rhinosinusitis

Chronic rhinosinusitis (CRS) is often treated by functional endoscopic paranasal sinus surgery, which improves endoscopic parameters and quality of life, while olfactory function was suggested as a further criterion of treatment success. In a prospective cohort study, 37 parameters from four categories were recorded from 60 men and 98 women before and four months after endoscopic sinus surgery, including endoscopic measures of nasal anatomy/pathology, assessments of olfactory function, quality of life, and socio-demographic or concomitant conditions. Parameters containing relevant information about changes associated with surgery were examined using unsupervised and supervised methods, including machine-learning techniques for feature selection. The analyzed cohort included 52 men and 38 women. Changes in the endoscopic Lildholdt score allowed separation of baseline from postoperative data with a cross-validated accuracy of 85%. Further relevant information included primary nasal symptoms from SNOT-20 assessments, and self-assessments of olfactory function. Overall improvement in these relevant parameters was observed in 95% of patients. A ranked list of criteria was developed as a proposal to assess the outcome of functional endoscopic sinus surgery in CRS patients with nasal polyposis. Three different facets were captured, including the Lildholdt score as an endoscopic measure and, in addition, disease-specific quality of life and subjectively perceived olfactory function.

Clinical Implications of Psychophysical Olfactory Testing: Assessment, Diagnosis, and Treatment Outcome

Purpose of Review

Olfactory dysfunction dramatically impairs quality of life with a prevalence of 20% in the general adult population. Psychophysical olfactory testing has been widely used to evaluate the ability to smell due to its validated utility and feasibility in clinic. This review summarizes the current literature regarding psychophysical olfactory testing and the clinical relevance of the olfactory testing with different components. Furthermore, the review highlights the diagnosis and treatment value of olfactory subtests in patients with olfactory dysfunction.

Recent Findings

With the accumulation of studies of psychophysical olfactory testing in olfactory disorders, the clinical relevance of olfactory testing with different components is expanding. Different olfactory domains present with distinct olfactory processing and cortical activity. Psychophysical assessment of olfaction with three domains reveals different levels of olfactory processing and might assist with analyzing the pathophysiologic mechanism of the various olfactory disorders. Furthermore, olfactory thresholds provided the largest amount of non-redundant information to the olfactory diagnosis. Sinonasal olfactory dysfunction and non-sinonasal-related olfactory dysfunction are emerging classifications of smell disorders with certain characteristics of olfactory impairment and different responses to the therapy including steroids, sinus surgery, and olfactory training.

Summary

These recent advancements should promote the understanding of psychophysical olfactory testing, the association between individual subcomponents and neurophysiological processes, and pave the way for precision assessment and treatment of the olfactory dysfunction.

Evaluation of Diagnostic Tests

As technology advances, diagnostic tests continue to improve and each year, we are presented with new alternatives to standard procedures. Given the plethora of diagnostic alternatives, diagnostic tests must be evaluated to determine their place in the diagnostic armamentarium. The first step involves determining the accuracy of the test, including the sensitivity and specificity, positive and negative predictive values, likelihood ratios for positive and negative tests, and receiver operating characteristic (ROC) curves. The role of the test in a diagnostic pathway has then to be determined, following which the effect on patient outcome should be examined.

Association of subjective olfactory dysfunction and 12-item odor identification testing in ambulatory COVID-19 patients

BACKGROUND

Acute loss of smell and taste are well-recognized symptoms of coronavirus disease 2019 (COVID-19), yet the correlation between self-reported and psychophysical olfactory function remains unclear. Understanding the reliability of self-reported smell loss in ambulatory cases can assess the utility of this screening measure.

METHODS

A prospective, longitudinal study evaluating patient-reported and measured olfactory function using the validated 12-item Brief Smell Identification Test (BSIT) was conducted on adult outpatients with COVID-19. Patient-reported olfaction scores using a visual analog scale (VAS) were obtained at baseline, time of COVID-19 testing, and time of BSIT completion. Linear associations between VAS and BSIT were evaluated using Spearman's correlation coefficient and the sensitivity, specificity, and accuracy of VAS scores were calculated. Logistic regression identified characteristics associated with accurate assessment of olfactory function.

RESULTS

A total of 81 polymerase chain reaction (PCR)-confirmed COVID-19 positive subjects, of whom 54 self-reported smell loss, were prospectively recruited ≤5 days from diagnosis date between May 8, 2020, and July 8, 2020. Self-reported smell loss had good discriminative ability in identifying abnormal BSIT (area under receiver operating curve [AUC] 0.82, 95% confidence interval [CI], 0.71 to 0.92). A VAS <5 demonstrated sensitivity of 0.62 and specificity of 0.94 for predicting hyposmia (BSIT ≤8) with accuracy of 82.7%, whereas a VAS <9 had highest sensitivity at 0.86. Moderate bivariate linear associations were found between VAS and BSIT scores (rs = 0.59, p < 0.001).

CONCLUSION

Self-reported olfactory loss associated with COVID-19 has a strong ability to predict abnormal olfactory function though the 2 measures are moderately correlated. Subjective olfactory assessment is useful in screening olfactory dysfunction at early disease time points when psychophysical testing cannot be conducted.

Machine-learned analysis of the association of next-generation sequencing-based genotypes with persistent pain after breast cancer surgery

Cancer and its surgical treatment are among the most important triggering events for persistent pain, but additional factors need to be present for the clinical manifestation, such as variants in pain-relevant genes. In a cohort of 140 women undergoing breast cancer surgery, assigned based on a 3-year follow-up to either a persistent or nonpersistent pain phenotype, next-generation sequencing was performed for 77 genes selected for known functional involvement in persistent pain. Applying machine-learning and item categorization techniques, 21 variants in 13 different genes were found to be relevant to the assignment of a patient to either the persistent pain or the nonpersistent pain phenotype group. In descending order of importance for correct group assignment, the relevant genes comprised DRD1, FAAH, GCH1, GPR132, OPRM1, DRD3, RELN, GABRA5, NF1, COMT, TRPA1, ABHD6, and DRD4, of which one in the DRD4 gene was a novel discovery. Particularly relevant variants were found in the DRD1 and GPR132 genes, or in a cis-eCTL position of the OPRM1 gene. Supervised machine-learning-based classifiers, trained with 2/3 of the data, identified the correct pain phenotype group in the remaining 1/3 of the patients at accuracies and areas under the receiver operator characteristic curves of 65% to 72%. When using conservative classical statistical approaches, none of the variants passed α-corrected testing. The present data analysis approach, using machine learning and training artificial intelligences, provided biologically plausible results and outperformed classical approaches to genotype-phenotype association.

Machine-learning-derived rules set excludes risk of Parkinson's disease in patients with olfactory or gustatory symptoms with high accuracy

BACKGROUND

Chemosensory loss is a symptom of Parkinson's disease starting already at preclinical stages. Their appearance without an identifiable etiology therefore indicates a possible early symptom of Parkinson's disease. Supervised machine-learning was used to identify parameters that predict Parkinson's disease among patients having sought medical advice for chemosensory symptoms.

METHODS

Olfactory, gustatory and demographic parameters were analyzed in 247 patients who had reported for chemosensory symptoms. Unsupervised machine-learning, implanted as so-called fast and frugal decision trees, was applied to map these parameters to a diagnosis of Parkinson's disease queried for in median 9 years after the first interview.

RESULTS

A symbolic hierarchical decision rule-based classifier was created that comprised d = 5 parameters, including scores in tests of odor discrimination, odor identification and olfactory thresholds, the age at which the chemosensory loss has been noticed, and a familial history of Parkinson's disease. The rule set provided a cross-validated negative predictive performance of Parkinson's disease of 94.1%; however, its balanced accuracy to predict the disease was only 58.9% while robustly above guessing.

CONCLUSIONS

Applying machine-learning techniques, a classifier was developed that took the shape of a set of six hierarchical rules with binary decisions about olfaction-related features or a familial burden of Parkinson's disease. Its main clinical strength lies in the exclusion of the possibility of developing Parkinson's disease in a patient with olfactory or gustatory loss.

Clinical Usefulness of Self-Rated Olfactory Performance—A Data Science-Based Assessment of 6000 Patients

In clinical practice, with its time constraints, a frequent conclusion is that asking about the ability to smell may suffice to detect olfactory problems. To address this question systematically, 6049 subjects were asked about how well they can perceive odors, with 5 possible responses. Participants presented at a University Department of Otorhinolaryngology, where olfactory testing was part of the routine investigation performed in patients receiving surgery at the clinic (for various reasons). According to an odor identification test, 1227 subjects had functional anosmia and 3113 were labeled with normosmia. Measures of laboratory test performance were used to assess the success of self-estimates to capture the olfactory diagnosis. Ratings of the olfactory function as absent or impaired provided the diagnosis of anosmia at a balanced accuracy of 79%, whereas ratings of good or excellent indicated normosmia at a balanced accuracy of 64.6%. The number of incorrect judgments of anosmia increased with age, whereas false negative self-estimates of normosmia became rarer with increasing age. The subject’s sex was irrelevant in this context. Thus, when asking the question “How well can you smell odors?” and querying standardized responses, fairly accurate information can be obtained about whether or not the subject can smell. However, this has to be completed with the almost 30% (355 subjects) of anosmic patients who judged their ability to smell as at least “average.” Thus, olfactory testing using reliable and validated tests appears indispensable.