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

PURPOSE: This prospective study was conducted to determine the incidence and related characteristics of respiratory medical device-related pressure ulcers (MDRPU) in children admitted to a pediatric intensive care unit (PICU). METHODS: The participants were 184 children who were admitted to the PICU of P University Hospital from April 2016 to January 2017. Data were collected on the occurrence of respiratory MDRPU and characteristics regarding the application of respiratory medical devices. RESULTS: Respiratory MDRPU occurred in 11.9% of participants (58.3%: stage I ulcers, 37.5%: mucosal ulcers). The devices associated with respiratory MDRPU were endotracheal tubes (54.2%), high-flow nasal cannulas (37.5%), and oximetry probes (8.3%). Respiratory MDRPU associated with an endotracheal tube were significant differences according to the site and strength of fixation, the use of a bite block and adhesive tape, skin dryness, and edema. In high-flow nasal cannulas, significant differences were found according to the site of fixation, immobility after fixation, and skin dryness. CONCLUSION: The occurrence of respiratory MDRPU is significantly affected by the method and strength of fixation, as well as skin dryness and edema. Therefore, appropriate consideration of these factors in nursing care can help prevent respiratory MDRPU.
Adhesives ; Catheters ; Child ; Critical Care ; Edema ; Humans ; Incidence ; Intensive Care Units ; Methods ; Nursing Care ; Oximetry ; Pressure Ulcer ; Prospective Studies ; Skin ; Surgical Tape ; Ulcer

From the perspective of portable monitoring devices,we use an analog front-end AFE4490 design a module of Non-invasive blood oxygen measurement, used to collect human pulse wave signal and peak (valley) value detection and then use the principles of non-invasive oximetry calculated oxygen saturation (SPO2). This design of noninvasive oximetry module has the characteristics of small size, low power consumption, and the results of test show that the measurement of oxygen saturation are correct.
Heart Rate ; Humans ; Oximetry ; instrumentation ; methods ; Oxygen ; blood

Based on the imaging photoplethysmography (iPPG) and blind source separation (BSS) theory the author put forward a method for non-contact heartbeat frequency estimation. Using the recorded video images of the human face in the ambient light with Webcam, we detected the human face through software, separated the detected facial image into three channels RGB components. And then preprocesses i.e. normalization, whitening, etc. were carried out to a certain number of RGB data. After the independent component analysis (ICA)'theory and joint approximate diagonalization of eigenmatrices (JADE) algorithm were applied, we estimated the frequency of heart rate through spectrum analysis. Taking advantage of the consistency of Bland-Altman theory analysis and the commercial Pulse Oximetry Sensor test results, the root mean square error of the algorithm result was calculated as 2. 06 beat/min. It indicated that the algorithm could realize the non-contact measurement of heart rate and lay the foundation for the re- mote and non-contact measurement of multi-parameter physiological measurements.
Algorithms ; Face ; Heart Rate ; Humans ; Monitoring, Physiologic ; methods ; Oximetry ; Photoplethysmography ; Software ; Video Recording

A method which combines empirical mode decomposition with wavelet transform is employed to remove breathing baseline draft from pulse wave signal. First of all, this method decomposes pulse wave signal into several intrinsic mode functions and judges the intrinsic mode function which contains the information of breathing baseline draft. And then wavelet transform is used to decompose these intrinsic mode functions, and the detail coefficients representing breathing baseline draft are set into zero. At last, the signal is rebuilt. This can realize removing breathing baseline draft. A self-developed measurement device was used to obtain the pulse wave signal for validating, and AC-DC modulation ratio value was adopted to evaluate the effect. The results showed that this method could effectively remove breathing baseline draft from pulse wave signal.
Algorithms ; Oximetry ; instrumentation ; methods ; Respiration

OBJECTIVELife-threatening critical congenital heart disease (cCHD) is often not detected in the neonatal period. Unrecognized cCHD results in high morbidity and mortality rates. As a non-invasive, convenient, quick and accurate measuring method, pulse oximetry is considered to be a promising strategy to screen for cCHD in neonates. This article is a review on the neonatal pulse oximetry screening for cCHD.

DATA SOURCESArticles on neonatal pulse oximetry screening for cCHD were accessed from PubMed, using keywords including congenital heart defects, neonatal screening and oximetry.

STUDY SELECTIONOriginal articles and critical reviews selected were relevant to the review's theme.

RESULTSThe factors in the course of implementation, including threshold for positive pulse-oximetry screening results, the pulse oximeters used, timing of the screening, and the measuring position, influence the accuracy of the screening. It is recommended that the screening is completed on the second day of life, before hospital discharge. Motion-tolerant pulse oximeters, which can also be applied to measure the saturation in low-perfusion conditions, should be used. The probe should be put on both the right hand and on one foot. Thresholds of < 95% in either limb or a difference of > 3% between the limbs as a positive result may be appropriate. It should be emphasized that pulse-oximetry screening cannot be used as the only way to detect cCHD, clinical examination is also important in this situation. Cost-benefit analysis in the United Kingdom revealed it was plausible to use pulse oximetry as an adjunct to clinical examination. However, it is still controversial as to whether pulse oximetry can be used as a routine screening method for cCHD in neonates.

CONCLUSIONSNeonatal pulse oximetry screening improves detection of cCHD. Further studies should be carried out before it becomes one of the routine newborn screening programs.

Cost-Benefit Analysis ; Heart Defects, Congenital ; diagnosis ; Humans ; Infant, Newborn ; Neonatal Screening ; Oximetry ; methods

This paper proposes a multifunctional fitness monitor based on FFT and photoelectric sensor, which uses pulse-type and non-invasive detection method to complete the analysis of the human blood oxygen saturation and heart rate. The system collects the absorption of red and infrared light absorbed by fingertip, then by programmable gain amplifier and the Fast Fourier analysis, it extracts the amplitude, frequency of the AC signal. PIC24FJ128GA010 is used to complete the collection, automatic gain judgment and signal processing. Finally, the result is calibrated by pulse blood oxygen emulator. Furthermore, it realizes the pedometer function based on three axles acceleration sensors MMA7260, which enhances fitness monitor's usability and allows people to obtain dynamic physiological signs when exercising.
Equipment Design ; Fourier Analysis ; Humans ; Monitoring, Physiologic ; instrumentation ; Oximetry ; instrumentation ; methods

INTRODUCTIONPulse oximetry (SpO2) measures oxygen saturation but not alveolar ventilation. Its failure to detect alveolar hypoventilation during sedated endoscopy under oxygen supplementation has been reported. The aim of this study was to measure the masking effect of oxygen supplementation in SpO2 when alveolar hypoventilation develops during sedated endoscopy.

METHODSA total of 70 patients undergoing sedated diagnostic colonoscopy were randomly divided into two groups - oxygen supplementation group (n = 35) and room air breathing group (n = 35). SpO2 and end-tidal carbon dioxide (etCO2) were measured by non-intubated capnography during the procedure for all the patients.

RESULTSThe rise of etCO2 caused by alveolar hypoventilation was comparable in the two groups after sedation. SpO2 was significantly higher in the oxygen supplementation group than in the room air breathing group (98.6% ± 1.4% vs. 93.1% ± 2.9%; p < 0.001) at peak etCO2, and oxygen supplementation caused SpO2 to be overestimated by greater than 5% when compared with room air. SpO2 at peak etCO2 was reduced from the baseline before sedation for the oxygen supplementation and room air breathing groups by 0.5% ± 1.1% and 4.1% ± 3.1%, respectively (p < 0.001).

CONCLUSIONSpO2 alone is not adequate for monitoring alveolar ventilation during sedated endoscopy under oxygen supplementation due to possible delays in detecting alveolar hypoventilation in patients. Even if SpO2 decreases by only 1% during the procedure and its level remains near 100%, physicians should consider the onset of severe alveolar hypoventilation, which requires immediate intervention.

Adult ; Aged ; Carbon Dioxide ; analysis ; Colonoscopy ; Conscious Sedation ; Endoscopy ; Female ; Humans ; Hypoventilation ; diagnosis ; Male ; Middle Aged ; Monitoring, Intraoperative ; methods ; Oximetry ; methods ; Oxygen ; administration & dosage ; Respiration, Artificial

By studying of the pathology of human sleep and respiration disorder diseases, the method of sleep and respiration measurement, the evaluation index, a kind of micro sleep monitor and evaluation system was designed. Based on the methods of spectrum absorption and force changing, using high performance pulse oxygen saturation monitoring technology and respiration monitoring technology, developing a low-cost, high usability sleep monitor system which is convenience for family using. It can measure the signal of human oxygen saturation and chest respiration, can improve the quality of signal and reliable from arithmetic and sensor installing.
Humans ; Monitoring, Physiologic ; instrumentation ; methods ; Oximetry ; instrumentation ; methods ; Respiration ; Sleep ; physiology ; Software Design

The present paper was aimed to study the security of burning during the continuous monitoring of transesophageal arterial oxygen saturation. 20 rabbits were randomly divided into two groups: control group and high-frequency electrotome group. All rabbits were implanted with the oxygen saturation detection probes into the lower esophageal after anesthesia. The probes were made up with two light-emitting diode (LED) and then connected with oxygen saturation sensor to monitoring for 2h and 6h, respectively. We then intercepted two luminous points as esophageal specimens and dist the esophageal tissue detection device headend 1cm gastric side esophageal specimens (self-contr01) after monitoring, and carried out pathological examination. The pathological results of the LED-1, LED-2 esophageal biopsy and self-control section were mucous integrity, submucosal mildedema, hyperemia, a small number of lymphocytes and mononuclear cell infiltration. All the score of the esophageal tissue histologic was 2. The results showed that montioring the SteO2 not more than 6h was safe with montiored using a matching of oxygen saturation sensor and monitoring esophageal arterial oxygen saturation.
Animals ; Esophagus ; pathology ; Female ; Male ; Mucous Membrane ; pathology ; Oximetry ; adverse effects ; methods ; Rabbits ; Safety