INTRODUCTION: Obstructive sleep apnoea (OSA) is a serious but underdiagnosed condition. Demand for the gold standard diagnostic polysomnogram (PSG) far exceeds its availability. More efficient diagnostic methods are needed, even in tertiary settings. Machine learning (ML) models have strengths in disease prediction and early diagnosis. We explored the use of ML with oximetry, demographic and anthropometric data to diagnose OSA. METHODS: A total of 2,996 patients were included for modelling and divided into test and training sets. Seven commonly used supervised learning algorithms were trained with the data. Sensitivity (recall), specificity, positive predictive value (PPV) (precision), negative predictive value, area under the receiver operating characteristic curve (AUC) and F1 measure were reported for each model. RESULTS: In the best performing four-class model (neural network model predicting no, mild, moderate or severe OSA), a prediction of moderate and/or severe disease had a combined PPV of 94%; one out of 335 patients had no OSA and 19 had mild OSA. In the best performing two-class model (logistic regression model predicting no-mild vs. moderate-severe OSA), the PPV for moderate-severe OSA was 92%; two out of 350 patients had no OSA and 26 had mild OSA. CONCLUSION Our study showed that the prediction of moderate-severe OSA in a tertiary setting with an ML approach is a viable option to facilitate early identification of OSA. Prospective studies with home-based oximeters and analysis of other oximetry variables are the next steps towards formal implementation.
Humans ; Oximetry/methods* ; Sleep Apnea, Obstructive/diagnosis* ; Male ; Female ; Middle Aged ; Machine Learning ; Polysomnography ; Adult ; Anthropometry ; ROC Curve ; Aged ; Algorithms ; Predictive Value of Tests ; Sensitivity and Specificity ; Neural Networks, Computer ; Demography

Objective:To explore whether a portable monitor device（PMD） can be used to evaluate the efficacy of supraglottoplasty（SGP） in neonates with severe laryngomalacia（LM）. Methods:A retrospective analysis of 11 neonates diagnosed as severe LM treated in our hospital from January 2020 to November 2023 was performed. All neonates underwent SGP under general anesthesia and overnight PMD monitoring before and after surgery.The changes of sleep monitoring parameters before and after surgery were compared, SPSS 18.0 statistical software was applied and Wilcoxon symbolic-rank l test was used. P<0.05 showed statistical difference. Results:One week after surgery, the obstructive apnea-hypopnea index（OAHI）, obstructive apnea index（OAI）, oxygen desaturationindex（ODI） of 11 children were lower than those before operation, and the minimum pulse oximetry saturation（SpO2） was higher than that before operation, P<0.05, the difference was statistically significant, and there was no significant difference in sleep apnea hypopnea index（AHI） compared with that before operation. One month after surgery, AHI, OAHI, OAI and ODI were lower than those before operation, and the minimum SpO2 and mean SpO2 were higher than those before operation, P<0.05, the difference was statistically significant. Conclusion:Some parameters of PMD examination can be used to evaluate the efficacy of SGP in neonatal severe LM, which is an important auxiliary means for the evaluation of neonatal LM.
Humans ; Retrospective Studies ; Laryngomalacia/surgery* ; Infant, Newborn ; Male ; Female ; Postoperative Period ; Sleep Apnea, Obstructive/surgery* ; Oximetry ; Polysomnography ; Glottis/surgery* ; Infant ; Treatment Outcome

Humans ; COVID-19/epidemiology* ; Singapore/epidemiology* ; Oximetry ; Hypoxia

Humans ; COVID-19/epidemiology* ; Singapore/epidemiology* ; Oximetry ; Hypoxia

Humans ; COVID-19/epidemiology* ; Singapore/epidemiology* ; Oximetry ; Hypoxia

OBJECTIVES: Obstructive sleep apnea hypopnea syndrome (OSAHS) is a common disease that seriously affects health. Continuous positive airway pressure (CPAP) therapy is the preferred treatment for moderate-to-severe OSAHS patients. However, poor adherence to CPAP is a major obstacle in the treatment of OSAHS. Information-motivation-behavioral (IMB) skills, as a kind of mature technology to change the behavior, has been used in various health areas to improve treatment adherence. This study aims to explore the effects of the IMB skills intervention on CPAP adherence in OSAHS patients. METHODS: Patients who were primary diagnosed with moderate-to-severe OSAHS were randomly divided into the IMB group (n=62) and the control group (n=58). The patients in the IMB group received CPAP therapy and the IMB skills intervention for 4 weeks. The patients in the control group received CPAP therapy and a usual health care provided by a registered nurse. We collected the baseline data of the general information, including age, sex, body mass index (BMI), the Epworth Sleepiness Scale (ESS) score, the Hospital Anxiety and Depression Scale (HADS) score, and indicators about disease severity [apnea-hypopnea index (AHI), percentage of time with arterial oxygen saturation SaO₂<90% (T90), average SaO₂, lowest SaO₂, arousal index]. After CPAP titration, we collected CPAP therapy-relevant parameters (optimal pressure, maximum leakage, average leakage, 95% leakage, and residual AHI), score of satisfaction and acceptance of CPAP therapy, and score of willingness to continue CPAP therapy. After 4 weeks treatment, we collected the ESS score, HADS score, CPAP therapy-relevant parameters, effective CPAP therapy time per night, CPAP therapy days within 4 weeks, CPAP adherence rate, score of satisfaction and acceptance of CPAP therapy, and score of willingness to continue CPAP therapy. Visual analog scale (VAS) of 0-5 was used to evaluate the satisfaction and acceptance of IMB intervention measures in the IMB group. RESULTS: There were no significant differences in the baseline level of demographic parameters, ESS score, HADS score, disease severity, and CPAP therapy related parameters between the IMB group and the control group (all P>0.05). There were no significant differences in score of willingness to continue CPAP therapy, as well as score of satisfaction and acceptance of CPAP therapy after CPAP titration between the IMB group and the control group (both P>0.05). After 4 weeks treatment, the ESS score, HADS score, maximum leakage, average leakage, and 95% leakage of the IMB group were significantly decreased, while the score of satisfaction and acceptance of CPAP therapy and willingness to continue CPAP therapy of the IMB group were significantly increased (all P<0.05); while the above indexes in the control group were not different before and after 4 weeks treatment (all P<0.05). Compared with the control group, the ESS score, HADS score, maximum leakage, average leakage, and 95% leakage of the IMB group after 4 weeks treatment were significantly lower (all P<0.05); the effective CPAP therapy time, CPAP therapy days within 4 weeks, score of satisfaction and acceptance of CPAP therapy, score of willingness to continue CPAP therapy of the IMB group were significantly higher (all P<0.05). The rate of CPAP therapy adherence in 4 weeks of the IMB group was significantly higher than that of the control group (90.3% vs 62.1%, P<0.05). The VAS of overall satisfaction with IMB skills intervention measures was 4.46±0.35. CONCLUSIONS IMB skills intervention measures can effectively improve the adherence of CPAP therapy in OSAHS patients, and is suitable for clinical promotion.
Continuous Positive Airway Pressure ; Humans ; Motivation ; Oximetry ; Patient Compliance ; Sleep Apnea, Obstructive/diagnosis* ; Syndrome

Oxygen reserve index (ORI) is a novel dimensionless index used for noninvasive, real-time, and continuous monitoring of oxygenation, and ORI value ranges from 0 to 1, which reflects the range of 100-200 mmHg for arterial partial pressure of oxygen. ORI combined with pulse oximetry may help to accurately adjust the concentration of inspired oxygen and prevent hyperoxemia and hypoxemia. ORI is suitable for various clinical situations, and the medical staff should master this novel parameter and use it properly to assess the oxygenation of patients. In addition, several limitations of ORI should be noticed during clinical application.
Humans ; Oxygen ; Blood Gas Analysis ; Oxygen Inhalation Therapy ; Oximetry ; Hypoxia/therapy*

INTRODUCTION: Balanced general anesthesia technique is a popular choice for induction because it can minimize potential side effects from individual drugs when otherwise used alone. However, hypotension is still a common occurrence during induction. Perfusion Index (PI) has been used as a measure of systemic vascular resistance and has shown to predict hypotension after regional anesthesia and propofol induction. This study aimed to determine whether baseline PI can predict hypotension following balanced general anesthesia induction and determine a cut-off value where hypotension is expected to occur. METHODS: Thirty-five ASA I/II adults for elective surgery under general anesthesia were enrolled. Heart rate, blood pressure and PI were measured every minute from baseline to 5 minutes following induction and 10 minutes after endotracheal intubation. Hypotension was defined as fall in systolic BP (SBP) by >30% of baseline and/or mean arterial pressure (MAP) to <60 mmHg. Severe hypotension (MAP of <55 mm Hg) was treated. RESULTS: No hypotension was observed in the first 5 minutes. Within 10 minutes, hypotension occurred in 8.6% by SBP criterion and 2.6% by MAP criterion. Within 15 minutes, hypotension was seen in 5.7% by SBP and MAP criterion, respectively. PI showed very low (r < 0.2) to low (r = 0.2 to 0.39), negative to positive and insignificant correlation (p > 0.05) with hypotension whether using SBP or MAP criterion and whether observed at 10 or 15 minutes of anesthesia induction. The Area under the ROC curve is 0.397, 95% CI [0 .126, 0.667], p = 0.431. CONCLUSION This study lends inconclusive evidence on the usefulness of Innovo Deluxe Fingertip Pulse Oximeter with Plethysmograph and Perfusion Index to predict intraoperative hypotension following balanced general anesthesia induction for this sample of patients. However, there was a positive, moderate (r=0.538, 0.501 and 0.469) and significant (p<0.05) correlation between perfusion index and SBP, Diastolic BP and MAP, respectively.
oximetry ; hypotension ; Anesthesia, General ; arterial pressure ; blood pressure ; Perfusion index

During the COVID-19 epidemic, our national guidelines have suggested that surgical patients should wear a mask to decrease the potential transmission of COVID-19 in the operating room, as long as the condition allows. However, so far, there is no study to discuss the influence of wearing a mask on the ventilation and blood oxygenation status in patients of spontaneous breathing with supplementary oxygen through an anesthetic facemask. This is a before-after study in the same patient, and 10 healthy volunteers were recruited, by testing the arterial blood gas parameters at key time points before and after oxygen inhalation to evaluate the effects of two different supplementary oxygen methods ('disposable medical mask + anesthetic facemask' and 'anesthetic facemask only') on the oxygenation of subjects. Our data demonstrated whether wearing a disposable medical mask or not could effectively increase the oxygen supply of the subjects compared with the basic value before oxygen inhalation; however, compared with the group without mask, the arterial oxygen partial (PaO
COVID-19 ; Healthy Volunteers ; Humans ; Masks ; Oximetry ; Oxygen/blood*

OBJECTIVE: To explore the predictive values of the combination of preoperative data, including medical history and physical examination, and results of sleep oximetry performed early after the surgery (one week) in predicting the treatment outcomes of uvulopalatopharyngoplasty (UPPP) in adult patients with obstructive sleep apnea hypopnea syndrome (OSAHS). METHODS: All the patients who were diagnosed with OSAHS, underwent UPPP treatment and had complete follow-up data in our institution between Jan 2013 and May 2016 were enrolled in our study. The pre-operative data of these patients, including age, physical examination, and polysomnography (PSG) data, were all exactly collected for analysis. All these patients had received the evaluation of subjective efficacy scale and the sleep oximetry test in early post-operative days (within one week). The long-term efficacy evaluations including PSG and subjective efficacy scale were all finished at least three months after the surgery. RESULTS: In the research 61 patients were finally studied, including 25 responders (41.0%) and 36 non-responders (59.0%). Regression analysis revealed that the pre-operative Friedman stage and early post-operative oxygen desaturation index of ≥4% (ODI4) were found to be independently predictive parameters for the UPPP treatment outcomes (P<0.05). The ROC curve analysis was used to estimate the predictive values of ODI4 to the treatment outcomes, and it was calculated with an area under the curve of 0.822. Using the ODI4 of 15 as the cutoff value, the sensitivity and specificity of that calculated were up to 0.778 and 0.760 respectively. The response rate among the patients with an early post-operative ODI4 of <15 was 70.4%, which was significantly higher than that of the patients with an early post-operative ODI4 of ≥15, whose response rate was 17.6% (P<0.05). The similar results could also be obtained in the patients with pre-operative Friedman stage II (87.5% vs.25.0%) and Friedman stage III (33.3% vs. 6.7%). CONCLUSION The combination of early post UPPP operation oximetry parameters, especially ODI4, and pre-operative Friedman stage could be used in better evaluating the potential surgical outcomes of UPPP.
Adult ; Humans ; Oximetry ; Palate ; Pharynx ; Polysomnography ; Treatment Outcome