Clinical Utility of Machine Learning Methods Using Regression Models for Diagnosing Eosinophilic Chronic Rhinosinusitis.

Objective: Machine learning methods using regression models can predict actual values of histological eosinophil count from blood eosinophil levels. Therefore, these methods might be useful for diagnosing eosinophilic chronic rhinosinusitis, but their utility still remains unclear. We compared 2 statistical approaches, and investigated the utility of machine learning methods for diagnosing eosinophilic chronic rhinosinusitis. Study Design: Retrospective study. Setting: Medical center. Methods: Data, including eosinophilic levels, obtained from blood and sinonasal samples of 264 patients with chronic rhinosinusitis (257 with and 57 without nasal polyps) were analyzed. We determined factors affecting histopathological eosinophil count in regression models. We also investigated optimal cutoff values for blood eosinophil percentages/absolute eosinophil counts (AECs) through receiver operating characteristic curves and machine-learning methods based on regression models. A histopathological eosinophil count ≥10/high-power field was defined as eosinophilic chronic rhinosinusitis. Results: Blood eosinophil levels, nasal polyp presence, and comorbid asthma were factors affecting histopathological eosinophil count. Cutoffs between the 2 statistical approaches differed in the group with nasal polyps, but not in one without nasal polyps. Machine-learning methods identified blood eosinophil percentages ≥1% or AEC ≥100/µL as cut-offs for eosinophilic chronic rhinosinusitis with nasal polyps, while ≥6% or ≥400/µL for one without nasal polyps. Conclusion: Cut-offs of blood eosinophil levels obtained by machine-learning methods might be useful when suspecting eosinophilic chronic rhinosinusitis prior to biopsy because of their ability to adjust covariates, dealing with overfitting, and predicting actual values of histological eosinophil count.

Comorbidity of eosinophilic chronic rhinosinusitis in chronic eosinophilic pneumonia.

We aimed to elucidate details of comorbid chronic rhinosinusitis (CRS) in chronic eosinophilic pneumonia (CEP) under the collaboration between otolaryngologists and pulmonologists in a prospective study. The CEP diagnosis was performed by pulmonologists based on clinical symptoms, laboratory findings, and/or eosinophilia detected in bronchoalveolar lavage. All patients were referred to otolaryngologists before undergoing oral corticosteroid treatment for CEP. Ten CEP cases visited to otolaryngologists. All cases showed bilateral sinonasal inflammation in computed tomography (CT), indicating comorbid CRS. Nasal polyps (NPs) were observed in 50% of patients on endoscopy. Eighty percent of patients were diagnosed with eosinophilic CRS. In blood eosinophil levels and the mucosal eosinophil count, there were no significant differences between CRS without and with NPs. In Lund-Mackay CT total scores, among-individual variability was observed in CRS with NPs. The collaboration revealed blood/sinonasal eosinophilia and the variability in Lund-Mackay CT total scores as remarkable findings about the comorbid CRS.

Psychological states affecting initial pupil size changes after olfactory stimulation in healthy participants.

Odor perception affects physiological and psychological states. Pupillary light reflex (PLR) parameters can be affected by olfactory stimulation and psychological states, although it remains unclear whether the olfactory stimulation-induced psychological changes can associate with PLR parameter changes. This study aimed to investigate effects of olfactory stimulation-induced psychological changes on PLR parameter changes with repeated measurements. We collected data on six mood subscales of the profile of mood states, and on five PLR parameter measurements from 28 healthy participants. Participants underwent a 10-min olfactory stimulation on different days with six odorants available with the T&T olfactometer. As obtained data were clustered, we used linear mixed-effects models for statistical analyses. The olfactory stimulation using the no-odor liquid did not affect mood states and the initial pupil size (INIT). The sweat odorant worsened all mood subscales including fatigue-inertia (Fatigue)/Vigor-Activity (Vigor), and decreased INIT compared to the no-odor liquid. When comparing INIT responses related to changes in mood subscales between the no-odor liquid and the sweat odorant, worsened states of Fatigue/Vigor were associated with decreased INIT in the sweat odorant. Fatigue/Vigor can be used as mental fatigue indicators. Thus, mental fatigue can be associated with decreased INIT in the olfactory stimulation.

Recommendation of using both initial pupil size and constriction latency in pupillary light reflex as objective indicators reflecting subacute pain-related mental fatigue.

A previous study examining clinical subacute pain models under different methodological conditions showed that pain-induced mental fatigue can be associated with decreased initial pupil size (INIT)/shortened constriction latency (LAT) in the pupillary light reflex (PLR). We aimed to investigate the potential of INIT/LAT as objective indicators reflecting mental fatigue under the same methodological conditions. We recruited 118 patients planning to undergo three types of representative otolaryngological head and neck surgery procedures. We used the numerical rating scale (NRS) to assess subjective pain intensity and two mental fatigue-related mood categories of the Profile of Mood States, as well as INIT and LAT measurements (1) in the afternoon one day before surgery (pre1-surgery), (2) in the morning of the day of surgery (pre2-surgery), and (3) in the morning of the day following surgery (post-surgery). We assessed time point-dependent changes using one- or two-way analysis of variance, as well as responses of PLR parameters to mental fatigue using linear mixed-effects models (LMMs). As a result, NRS scores, the two mood categories, as well as LAT and INIT, showed significant time point-dependent changes. In post-hoc analyses, only INIT showed significant changes between the two pre-surgery time points. Thus, INIT values fluctuated even under pain-free conditions due to differences in the time of the day. LMMs demonstrated decreased INIT/shortened LAT related to mental fatigue. All surgical groups showed similar associations between mental fatigue and INIT/LAT findings. As each parameter has advantages and disadvantages, it is recommended to use both INIT and LAT as the indicators.

Decreased initial pupil size and shortened constriction latency due to negative mood states and mental fatigue in clinical subacute pain models.

Previous clinical studies on pupillary light reflex parameters showed shortened constriction latency (LAT) and decreased initial pupil size (INIT) due to increased numeric rating scale (NRS) scores, reflecting subjective pain intensity, in subacute pain models. As noxious stimulation causes pupil dilation, decreased INIT (pupil constriction) was an unexpected finding. Pain-related negative moods and mental fatigue might have caused this finding. We aimed to investigate how psychological states affect LAT/INIT in two subacute pain models. For psychological assessment, we used the Profile of Mood States (POMS) and calculated the total mood disturbance (TMD) score using six mood categories. We collected data on NRS scores, POMS-related scores, LAT, and INIT through a longitudinal study. Using linear mixed-effects models, we evaluated the association of TMD scores with NRS scores, LAT, and INIT. Furthermore, we performed subanalyses targeting two mood categories that represent mental fatigue: Fatigue-Inertia (Fatigue) and Vigor-Activity (Vigor). We investigated whether obtained results can be identical in both models. In total, 141 patients were enrolled. Increased NRS scores were associated with increased TMD/Fatigue scores and decreased Vigor scores, being associated with shortened LAT/decreased INIT in both models. Score changes in NRS, TMD, Fatigue, and Vigor indicated that increased subjective pain intensity can be associated with negative mood states, especially mental fatigue. This study revealed that negative moods and mental fatigue induced by acute pain can be associated with shortened LAT/decreased INIT in both models, indicating clinical potential of LAT/INIT as objective indicators reflecting the psychological states for pain assessment.

Clinical potential of pupillary light reflex and heart rate variability parameters as objective indicators of tonsillectomy-induced pain.

Objective.Establishing objective indicators of subjective pain intensity is important in pain assessment. Pupillary light reflex (PLR) and heart rate variability (HRV) indicate autonomic nervous system (ANS) activity and may serve as pain indicators because pain can affect ANS activity. In this prospective longitudinal study, we aimed to investigate the potential of PLR/HRV parameters as objective indicators of subjective pain intensity after tonsillectomy.Approach.Sixty-seven patients undergoing tonsillectomy were enrolled. Subjective pain intensity based on a numeric rating scale (NRS) and eight PLR/HRV parameters were assessed at five time points. We investigated the changes in the NRS values over time. We estimated regression coefficients reflecting parameter changes per unit change in the NRS score using linear mixed-effects models.Main Results.The mean NRS score was 0 at two pre-surgery time points, 5 on postoperative days (PODs) 1 and 2, and 0 at postoperative week 3. Two parameters (initial pupil size [INIT] and constriction latency [LAT]) showed significant changes on POD1 and POD2 in comparison to baseline data measured at the pre-surgery time point. Among these parameters, only LAT showed no significant changes between POD1 and POD2. Significant regression coefficients with the narrowest 95% confidence intervals were observed for INIT and LAT. Increased NRS scores were associated with decreased INIT and shortened LAT.Significance.LAT was a robust indicator of subjective pain intensity. Our patients showed decreased INIT with increased NRS scores, indicating the predominance of the parasympathetic, not sympathetic, tone in pupils. Further studies are required to investigate factors causing this predominance.

Rapid progressive destruction of the cochleae in an infant due to pneumococcal meningitis.

The widespread adoption of pneumococcal conjugate vaccines has reduced the incidence of Streptococcus pneumoniae infections, but has also led to the emergence of infections due to non-vaccine serotypes. A 15-month-old girl was referred to our hospital with suspected meningitis. S. pneumoniae was isolated from her cerebrospinal fluid. She was initially treated with a combination of cefotaxime and vancomycin, followed by ampicillin and vancomycin. After 7 days, the patient's condition improved and she was transferred to the general ward; however, her mother noted signs of hearing difficulties. On the 16th day of admission, we performed an auditory brainstem response test, which suggested severe bilateral hearing impairment. This was confirmed using an auditory steady-state response test after consulting with otolaryngologists. Magnetic resonance imaging revealed fibrosis of both cochleae with labyrinthitis. The patient underwent emergency cochlear implantation at a different hospital. The S. pneumoniae isolate was later identified to be serotype 10A with a PBP2x mutation, which is not covered by the conjugate vaccine and has reduced cephalosporin susceptibility. This case was characterized by highly rapid cochlear destruction, and an earlier otolaryngologist consultation may have provided a more well-organized surgery plan. Pediatricians are urged to promptly consult with otolaryngologists for patients with similar indications.

Clinical potential of pupillary light reflex parameters as objective indicators reflecting chronic rhinosinusitis-specific quality of life: a 12-month prospective longitudinal study.

Pupillary light reflex (PLR) and heart rate variability (HRV) parameters can be objective indicators of chronic rhinosinusitis (CRS) status from the viewpoint of autonomic nervous system activity. This study aimed to establish objective indicators for CRS using the 22-item Sino-Nasal Outcome Test (SNOT-22) and PLR/HRV parameters. Sixty-seven patients were prospectively and longitudinally followed up after surgical treatment. We investigated changes in SNOT-22 scores, representing CRS-specific quality of life (QOL). We prepared two models: linear regression model adjusting clinical factors as predictor variables (model 1) and linear mixed-effects model adjusting clinical factors and among-individual variability (model 2). We compared Akaike's information criterion (AIC) values and regression coefficients. The model with lower AIC values was defined as the better-fit model. Model 2 showed lower AIC values in all parameters (better-fit model). Three parameters showed opposite results between the two models. The better-fit models showed significances in the five PLR parameters but not in any HRV parameters. Among these PLR parameters, constriction latency can be the most robust indicator because of the narrowest 95% confidence intervals. Adjusting the among-individual variability while investigating clinical potential of PLR/HRV parameters to reflect CRS-specific QOL can improve the model fit, thereby reaching robust conclusions from obtained data.