Pulse Oximeter Research Articles

The role of oxygen in the development and treatment of bronchopulmonary dysplasia

Oxygen (O2) is crucial for both the development and treatment of one of the most important consequences of prematurity: bronchopulmonary dysplasia (BPD). In fetal life, the hypoxic environment is important for alveolar development and maturation. After birth, O2 becomes a double-edged sword. While O2 is needed to prevent hypoxia, it also causes oxidative stress leading to a plethora of morbidities, including retinopathy and BPD. The advent of continuous O2 monitoring with pulse oximeters has allowed clinicians to recognize the narrow therapeutic margins of oxygenation for the preterm infant, but more knowledge is needed to understand what these ranges are at different stages of the preterm infant's life, including at birth, in the neonatal intensive care unit and after hospital discharge. Future research, especially in innovative technologies such as automated O2 control and remote oximetry, will improve the understanding and treatment of the O2 needs of infants with BPD.

Patient and clinician perceptions of the pulse oximeter in a remote monitoring setting for COVID-19: Qualitative study.

As a response to the COVID-19 pandemic, the Royal Prince Alfred Hospital in New South Wales, Australia, launched the rpavirtual program, the first full-scale virtual hospital in Australia, to remotely monitor and follow-up stable COVID-19 patients. As part of the intervention, a pulse oximeter wearable device was delivered to patients to monitor their oxygen saturation levels, a critical indicator of COVID-19 patient deterioration. Understanding users' perceptions towards the device is fundamental to assessing its usability and acceptability and contributing to the effectiveness of the intervention, but no research to date has explored the user experience of the pulse oximeter for remote monitoring in this setting. To explore the utilization, performance, and acceptability of the pulse oximeter by clinicians and patients in rpavirtual during COVID-19. Semi-structured interviews and usability testing were conducted. Stable COVID-19 adult patients (≥18 years old) who used the pulse oximeter and were monitored by rpavirtual and rpavirtual clinicians monitoring these patients were interviewed. Clinicians could be nurses, doctors or staff part of the team who assisted patients with the use of the pulse oximeter. Usability testing was conducted with patients who had the pulse oximeter when they were contacted. Interviews were coded using the Theoretical Framework of Acceptability. Usability testing was conducted using a think-aloud protocol. Data was collected until saturation was reached. Twenty-one patients (average age: 51 years) and 15 clinicians (average age: 41 years) completed the interview. Eight patients (average age: 51 years) completed the usability testing. All participants liked the device and thought it was easy to use. They also had a good understanding of how to use the device and the device's purpose. Patient age and device-use related characteristics (e.g., the warmth of hands, hand steadiness) were identified by users as factors negatively impacting the accurate use of the pulse oximeter. Patients and clinicians had very positive perceptions of the pulse oximeter for COVID-19 remote monitoring, indicating high acceptability and usability of the device. However, factors that may impact the accuracy of the device should be considered when delivering interventions using the pulse oximeter for remote monitoring. Targeted instructions about the use of the device may be necessary for specific populations (e.g. elderly, patients unfamiliar with technology). Further research should focus on the integration of the pulse oximeter data into electronic medical records for real-time and secure patient monitoring.

Bacterial Contamination on Reusable Pulse Oximeter Sensors in Intensive Care Units and Its Manual Disinfection by Alcohol and Sodium Hypochlorite

: Nosocomial infections may result from intensive care unit pulse oximeters. The descriptive study examined pulse oximeter sensor microbiological contamination and the efficacy of manual disinfection with alcohol and sodium hypochlorite in five hospital intensive care units. Sixty-eight reusable pulse oximeter sensors were swabbed, cultured, and evaluated after decontamination. In private and public hospitals, 12 (35.2%) and 13 (37.2%) pulse oximeters tested positive for bacteria. Alcohol 70% reduced the microbial load and more than 10% sodium hypochlorite. The study found that purposeful cleaning and disinfection reduce microorganisms. Alcohol was more efficacious than sodium hypochlorite. Critical care facilities should regularly clean reusable pulse oximeter sensors.

Emergency preparedness capacity of a university hospital in Ghana: a cross-sectional study.

The health and safety of people are often endangered during emergencies and disasters. Efficient emergency management systems ensure that mitigation, preparedness, response, and recovery actions exist to preserve the health, safety, and welfare of the public. Failure to carry out appropriate responses can have adverse consequences for both emergency responders and casualties; hence, the need for emergency preparedness. This study sought to assess the state of emergency preparedness capacity of the Kwame Nkrumah University of Science and Technology hospital in Ghana. A facility-based cross-sectional study was conducted between December 2018 and February 2019 using three guidelines developed respectively by the World Health Organization, the Ministry of Health-Ghana, and the Ghana Health Service. The hospital's emergency preparedness was assessed regarding the emergency policies, plan, protocol, equipment, and medications. Overall, the hospital's emergency preparedness level was weak (57.36%). Findings revealed that the hospital had inadequate emergency equipment, and supplies for emergency care delivery, especially during upsurge. It also did not have an emergency planning committee. There were noticeable deficiencies in some emergency resources such as chest tubes, basic airway supplies, and many emergency drugs. Other vital emergency tools such as pulse oximeter, thermometer, and emergency medications were inadequate. The hospital had a strong emergency plan and policies on assessment (77.8% and 78%) respectively. The Kwame Nkrumah University of Science and Technology hospital is not prepared sufficiently for an emergency surge, and this poses a major health challenge. Emergency items must be made available, and the organization and planning of emergency service provisions must be improved to avoid preventable deaths during an emergency surge.

Oxygen Saturation and Heart Rate Monitoring System by Mobile

COVID-19 changed the way people live, causing a high mortality rate and making the entire health system in the world difficult due to the lack of equipment and infrastructure, causing many people to be treated from home, constantly measuring their saturation level and heart rate with the help of a pulse oximeter, since the virus directly affects the respiratory system, it has been added that people with lung or cardiovascular problems also have to perform the constant measurement of both vital signs to visualize that they are in a normal range, otherwise, they would have to attend a medical center, so it is important to monitor both vital signs. In view of this problem, in this article a monitoring system of oxygen saturation and heart rate was carried out by mobile application, in such a way that both vital signs can be constantly monitored and an alert can be given to the health center with the coordinates of the person when the system detects a measurement outside the normal range, with this, it would help people who may need medical attention immediately, being able to save their lives. Through the development of the monitoring system, it was possible to observe the operation of the mobile application with an efficiency of 99.15% in monitoring the level of oxygen saturation and 98.78% in monitoring the heart rate, taking 4 seconds to send the alert to the health center to assist the patient.

Effectiveness of nesting and pronation on oxygen saturation in babies with respiratory distress syndrome

Background: The infant mortality rate in Indonesia is still relatively high at 15 per 1000 live births. Cause of Infant death can occur due to intrapartum complications, one of which is a respiratory system disorder in the form of Respiratory Distress Syndrome (RDS). The nesting and prone positions intervention can be made to optimize the oxygenation status of babies with RDS. However, it is necessary to see the effectiveness of both positions in increasing oxygen saturation.Objective: This study aims to determine differences in oxygen saturation in infants with RDS who are given nesting and pronation.Methods: This is a quasi-experimental with a two-group pretest-posttest design. The total sample of 36 respondents was divided into the nesting and pronation group positions with the consecutive sampling technique. Oxygen saturation levels were measured using a pulse oximeter before and after the intervention for 15 minutes in one day. The analytical test is a paired t-test and an independent t-test.Results: The statistical test results for the pretest-posttest difference in oxygen saturation (p<0.05) in the pronation group increased by 3.6% compared to the nesting group by 0.3%, which means that the prone position is better at increasing oxygen saturation.Conclusion: Pronation is more effective in increasing oxygen saturation than nesting in infants with RDS. So, pronation can be used as a nursing intervention in infants with RDS.

Design and Demonstration of Arduino based Low Cost Pulse Oximeter

One of the main reasons for the pushback of the pandemic in India was the awareness that developed in people during the crisis. The adapting mindset of the Indian populace helped turn the tides. The Pulse Oximeter proved to be an important tool that helped in identifying the affected, to get timely healthcare. A very simple information was shared among people that the BPM (heart rate in beats per minute) should be around 60 - 100 (resting) for an average adult and the SpO2, i.e., oxygen saturation must be above 95% for all age groups. Just this was able to counter an entire wave of the Pandemic with the help of early detections, timely isolations, immediate health care and much more. However, access to this was not available to everyone due to the high prices of these devices. This project aims to build a simple monitor module with an Arduino Nano board which can determine the Blood Oxygen level and Heart rate of a person by using the MAX30102 sensor.

Correlation between dental crown’s color and pulse oximetry interpretation in teeth submitted to bleaching procedures

To evaluate the correlation between the dental crown’s color and the pulse oximeter result in healthy teeth before and after 30 days of the end bleaching procedures. Material and methods: The dental crown’s color of 70 healthy maxillary central incisors were evaluated using a spectrophotometer and the oxygen saturation level of the pulp was recorded using a pulse oximeter. The bleaching was performed using the combined technique, with 35% hydrogen peroxide bleaching gel, in the office stage, and 10% carbamide peroxide, in the at-home, for 16 days. The variables symmetry was verified by the Kolmogorov Smirnov test, and the quantitative variables described by mean and standard deviation. The correlation between quantitative variables was established using Pearson’s correlation coefficient. The significance level considered was 5%. Results: A significant change was observed between values recorded by the pulse oximeter before (85.0% ± 4.1) and after (86.4% ± 2.3) 30 days of the end. Thirty days after the end of the bleaching procedures, the dental crowns were lighter with the difference between L*s equal to 1.4, more greenish with a difference between a*s equal to 1.3, and more bluish with a difference between b*s equal to -7.2. There was no correlation between the values of coordinates L*, a* and b* and the results recorded by the pulse oximeter in the initial period, respectively, or 30 days after the bleaching procedures, respectively. Conclusion: Changes in pulse oximeter recordings did not correlate with the change in the dental crown’s color promoted by bleaching procedures.

Duration of parturition in ewes and its consequences on behavioural traits in mother-lamb bond: Doctoral thesis abstract

Lamb mortality within the first 72 hours of life greatly affects sheep breeding, especially in extensive rearing, resulting in important economic losses and involving animal welfare. Prolonged fetal expulsion phase can influence maternal behaviour, and the extended period of hypoxia during birth can also affect the behaviour of the neonate. Limited information exists regarding the necessary duration of the fetal expulsion phase for these changes in maternal behaviour to occur or for the resulting hypoxia from prolonged delivery to either be reversed or cause sequelae that affect lamb viability. Behavioural disturbances of both the mother and the neonate prevent establishing a proper mother-lamb bond. This thesis aims to investigate the required time for the duration of the fetal expulsion phase to have consequences on both maternal and offspring behaviour. For early detection of foetal hypoxia, the effectiveness of a non-invasive and easy-to-use tool, a pulse oximeter, was evaluated and compared with venous blood gas analysis. The prolonged duration of parturition affected the behaviour of both dams and lambs, disrupting the mother-lamb bond and leading to a higher percentage of abandonment. A linear correlation between the duration of delivery and poor maternal behaviour was observed in primiparous ewes, but not in multiparous ones. The pulse oximeter successfully detected lambs with low oxygenation at birth, which would allow to establish therapeutic or management measures to improve survival. Reducing the duration of the foetal expulsion phase through programmed parturition assistance improved maternal behaviour and lamb vigour in primiparous ewes, enabling the establishment of an appropriate mother-lamb bond and potentially enhancing neonatal survival.

222 Pediatric Pulse Oximetry to Monitor the Post-Operative Integrity of Free Flaps

Abstract Introduction The post-operative monitoring of free-flaps can be a challenge, particularly for junior staff on-call and in patients with darker or mottled skin. We present a case employing paediatric pulse oximetry to monitor a free flap where clinical assessment was challenging, illustrating its value as an adjunct to existing techniques such as doppler. Case A 23-year-old patient underwent tenolysis to his anterior right leg compartment due to a painful, tethered scar following injury. He subsequently had a superficial circumflex iliac perforator (SCIP) flap anastomosed end-to-side to his posterior tibial artery. The operation was technically challenging, but the flap had a strong doppler and remained clinically well until day 4 post-op, where it became mottled but remained warm and soft. Clinical assessment was equivocal, and a paediatric pulse oximeter was taped to the flap, consistently showing saturations >95%, providing reassurance out-of-hours and facilitating the decision to delay haematoma evacuation for the following day. The flap survived and the patient did well. Conclusions The use of paediatric pulse oximetry to assess free flaps is a useful technique for clinically ambiguous cases where re-exploration could compromise survival. It is cheap, widely accessible and can be easily employed by junior clinicians and nurses who may be relatively inexperienced in their assessment of flaps’ clinical condition.

Validation of mobile health technology (mhealth tech) for cardiovascular risk detection

BackgroundWireless health monitoring device is handy, reduces measurement time and aids in screening and monitoring especially in resource limited settings and remote areas leading to early diagnosis and treatment. Objective of this study was to validate mobile health technology (mhealth tech) in cardiovascular risk detection and to assess Cardiovascular Disease (CVD) risk based on WHO's International Society of Hypertension (ISH) risk score among the study population. MethodologyA Cross-sectional study was carried out in 172 participants. Vital parameters were measured by wireless health monitoring device and traditional methods. Pulse rate and respiratory rate were calculated manually. SPO2, temperature and blood pressure were measured by pulse oximeter, thermometer and sphygmomanometer respectively. ROC curve and Independent T-test were done. ResultsMean difference in time spent measuring vitals manually by traditional method and by wireless health monitoring device was 239.65 (P=<0.001, 95% CI = 232.91 to 246.38). Area under the Receiver Operating Characteristic (ROC) curve for accuracy in diagnosing tachycardia, tachypnoea, hypoxia, hyperthermia, systolic and diastolic hypertension was 0.866 (95% CI (0.745–0.988); p=<0.001), 0.866 (95% CI (0.686–1); p=<0.001), 0.872 (95% CI (0.617–1); p = 0.011), 0.931 (95% CI (0.797–1); p=<0.001), 0.907 (95% CI (0.782–1); p=<0.001), and 0.854 (95% CI (0.651–1); p = 0.002) respectively. ConclusionWireless health monitoring devices can be used as a screening and monitoring tool. It is convenient, user-friendly and quickly measures vitals, hence can be used in centres with minimal manpower, health camps and mass screening.

The adaptive features of cardiohemodynamic and gas exchange readjustment under test load in young northern natives of different generations

The research aimed to study the restructuring of hemodynamics, gas exchange, and heart rate variability parameters in response to the stress test with breathing in confined space in different generations of young Caucasoid natives permanently residing in Russia’s Magadan region. Material and methods. Two hundred 18–21 year old male migrants and those born to them in 1–3 generations, all Caucasians by origin, participated in the Magadan city survey. During the resting and confined space rebreathing sessions we registered subjective heart rate, blood pressure, oxygen and carbon dioxide level. The heart rate variability was recorded by the Varicard complex coupled with the Iskim-6 software. The exhaled gas level was determined by the Karbonik analyzer. The blood oxygen saturation was measured by a pulse oximeter. An electronic tonometer was used for the blood pressure control. Results and discussion. Both resting and rebreathing tests revealed lower HRV rates in the group of migrants (zero generation): not only did they exhibit a decrease in the activity of the autonomic regulation contour – they also reported an imbalance in the sympathetic and parasympathetic regulation of cardiac hemodynamics. However, the 3rd generation subjects showed an optimal and stable balance between the links of autonomic regulation, both at rest and during functional exercise with rebreathing, which is reflected in the parameters of arterial pressure and gas exchange. Interestingly, the most informative indicators of adaptation are not the absolute values of the studied indicators but the difference between their background and testing values, which to a greater extent hold information on the body functional reserves of those born in the North in different generations constantly living in the extreme conditions of the North. It was found that the increase in parasympathetic activity and its influence on the cardiac rhythm both at rest and in response to a breathing test was most pronounced in the group of natives of the 3rd generation, which reflects a deeper degree of their adaptation to the northern conditions. Apparently, this is a manifestation of the general strategy of functional restructuring of the body’s regulatory systems aimed at the formation of optimal compensatory-adaptive restructuring of gas homeostasis during an increased period of residence in the North.

Evaluation of the Erbium-doped Yttrium Aluminum Garnet Laser and the Conventional Method on Pain Perception and Anxiety Level in Children during Caries Removal: A Randomized Split-mouth Study.

To assess and compare children's anxiety level and pain perception during cavity preparation using an erbium-doped yttrium aluminum garnet (Er:YAG) laser vs traditional rotational treatment. A randomized, controlled, split-mouth clinical trial was carried out in 35 healthy children with 70 carious primary molars. Teeth were divided equally into two groups according to the method of treatment. A bur was used to prepare the cavity in one quadrant, while an Er:YAG laser was used to prepare the cavity in the other quadrant. Anxiety was assessed using Venham's dental anxiety scale and a fingertip pulse oximeter. The pain was assessed using the Wong-Baker Face Pain Rating Scale, and the number of local anesthesia (LA) needed during both procedures was also considered. The mean age was 9.4 ± 1.29. Males accounted for 51.4% of the participants. There were no statistically significant variations in pulse rate at the baseline between Er:YAG laser and the conventional treatments. The mean pulse rate was higher during the conventional intervention than during the laser intervention; this difference was statistically significant vs the baseline pulse rate. The mean pulse rate with the conventional method was significantly higher during and after cavity formation than with the laser method. The Er:YAG laser and the conventional groups showed statistically significant differences in the Venham's and Wong-Baker scores. The scores of both scales were much higher in the conventional group. The number of participants who requested LA during the conventional technique was significantly higher than during the laser procedure. Using Er:YAG lasers to remove caries produces minimal pain and anxiety and reduces the requirement for LA. During cavity preparation, the Er:YAG laser helps children stay calm. Abdrabuh RE, El Meligy OAES, Felemban OM, et al. Evaluation of the Erbium-doped Yttrium Aluminum Garnet Laser and the Conventional Method on Pain Perception and Anxiety Level in Children during Caries Removal: A Randomized Split-mouth Study. Int J Clin Pediatr Dent 2023;16(S-1):S39-S44.

Knowledge of pulse oximetry among emergency and critical care nurses.

The pulse oximeter is a simple, cost-effective and reliable device for estimating arterial blood oxygen saturation. Nurses are required to be knowledgeable in pulse oximeter use. Little is known about nurses' knowledge of pulse oximetry in the Middle East region. To assess nurses' knowledge of pulse oximetry among emergency and critical care nurses and to explore predictors of nurses' knowledge of pulse oximetry. This is the second part of data analysis that was first presented in the 'proficiency in ECG' study conducted in Jordan. The original data used for both parts of analysis included a questionnaire with two tests; a knowledge of pulse oximeter test and an ECG proficiency test. Participants were asked to take, alone without receiving assistance, both tests. In this study, the second part of analysis, the focus is on the pulse oximeter test. The test consisted of 21 items that emphasize knowledge of basic physiological principles as well as device limitations; whether technical or interpretation. The test administration procedure also included asking participants to provide socio-demographic variables. In the original data collected in both parts of analysis, nurses working in the emergency department, cardiac care units or intensive care units from nine different hospitals (1 governmental, 6 private and 2 educational) and holding a bachelor degree or higher were asked to participate. The total number of participating nurses was 210; out of 247 approached (response rate, 85%). The mean score in the nurses' knowledge of pulse oximetry test was 12.33 out of 21, corresponding to 58.7%. The clinical area currently working in predicted the knowledge of pulse oximetry test score after controlling for all other variables. Emergency department and intensive care unit nurses scored higher than cardiac care unit nurses by 1.86 and 1.63 points respectively (58.2% and 60% respectively). Nurses consistently report inadequate education and training concerning pulse oximeter use and interpretation. A revision to hospital in-service education seminars and undergraduate nurses' curriculum to assure adequate preparation is needed. Knowledge of pulse oximetry among emergency and critical care nurses is modest. This is a challenge worldwide. Predictors of nurses' knowledge of pulse oximetery are the clinical area currently working in (ICU and ED nurses are more knowledgeable than CCU nurses), proficiency in electrocardiography and taking an advanced cardiac life support course.

Predicting acute pulmonary embolism in COVID-19.

Acute pulmonary embolism (PE) is a life-threatening condition in patients with Coronavirus disease-2019 (COVID-19). Computed tomography pulmonary angiography is the preferred test to confirm the diagnosis. However, computed tomography pulmonary angiography is expensive and is not available in every clinic. This study aimed to determine whether clinical findings, symptoms, and parameters that are cost-effective and available in many clinics such as C-reactive protein (CRP) lymphocyte ratio (CLR), and ferritin CRP ratio (FCR) can be used in the diagnosis of PE in patients with COVID-19. Out of the reviewed files, 127 patients were diagnosed with PE, whereas 105 patients had no PE. At the first admission, laboratory parameters, complaints, respiratory rate, and percent oxygen saturation in the blood (SpO2) with a pulse oximeter were recorded for each patient. Eosinophil levels remained lower, whereas ferritin lymphocyte ratio and CLR were higher in the PE group. Patients with more elevated ferritin, CRP, and CLR had an increased mortality risk. Shortness of breath and tiredness was more common in the PE group. A decrease in eosinophil levels, whereas an increase in CLR, D-dimer, and CRP may predict PE. Elevated CLR is highly predictive of PE and is associated with increased mortality risk. COVID-19 patients with a CLR level above 81 should be investigated for PE.

Clinical Outcomes Associated With Overestimation of Oxygen Saturation by Pulse Oximetry in Patients Hospitalized With COVID-19

Many pulse oximeters have been shown to overestimate oxygen saturation in persons of color, and this phenomenon has potential clinical implications. The relationship between overestimation of oxygen saturation with timing of COVID-19 medication delivery and clinical outcomes remains unknown. To investigate the association between overestimation of oxygen saturation by pulse oximetry and delay in administration of COVID-19 therapy, hospital length of stay, risk of hospital readmission, and in-hospital mortality. This cohort study included patients hospitalized for COVID-19 at 186 acute care facilities in the US with at least 1 functional arterial oxygen saturation (SaO2) measurement between March 2020 and October 2021. A subset of patients were admitted after July 1, 2020, without immediate need for COVID-19 therapy based on pulse oximeter saturation (SpO2 levels of 94% or higher without supplemental oxygen). Self-reported race and ethnicity, difference between concurrent SaO2 and pulse oximeter saturation (SpO2) within 10 minutes, and initially unrecognized need for COVID-19 therapy (first SaO2 reading below 94% despite SpO2 levels of 94% or above). The association of race and ethnicity with degree of pulse oximeter measurement error (SpO2 - SaO2) and odds of unrecognized need for COVID-19 therapy were determined using linear mixed-effects models. Associations of initially unrecognized need for treatment with time to receipt of therapy (remdesivir or dexamethasone), in-hospital mortality, 30-day hospital readmission, and length of stay were evaluated using mixed-effects models. All models accounted for demographics, clinical characteristics, and hospital site. Effect modification by race and ethnicity was evaluated using interaction terms. Among 24 504 patients with concurrent SpO2 and SaO2 measurements (mean [SD] age, 63.9 [15.8] years; 10 263 female [41.9%]; 3922 Black [16.0%], 7895 Hispanic [32.2%], 2554 Asian, Native American or Alaskan Native, Hawaiian or Pacific Islander, or another race or ethnicity [10.4%], and 10 133 White [41.4%]), pulse oximetry overestimated SaO2 for Black (adjusted mean difference, 0.93 [95% CI, 0.74-1.12] percentage points), Hispanic (0.49 [95% CI, 0.34-0.63] percentage points), and other (0.53 [95% CI, 0.35-0.72] percentage points) patients compared with White patients. In a subset of 8635 patients with a concurrent SpO2 - SaO2 pair without immediate need for COVID-19 therapy, Black patients were significantly more likely to have pulse oximetry values that masked an indication for COVID-19 therapy compared with White patients (adjusted odds ratio [aOR], 1.65; 95% CI, 1.33-2.03). Patients with an unrecognized need for COVID-19 therapy were 10% less likely to receive COVID-19 therapy (adjusted hazard ratio, 0.90; 95% CI, 0.83-0.97) and higher odds of readmission (aOR, 2.41; 95% CI, 1.39-4.18) regardless of race (P for interaction = .45 and P = .14, respectively). There was no association of unrecognized need for COVID-19 therapy with in-hospital mortality (aOR, 0.84; 95% CI, 0.71-1.01) or length of stay (mean difference, -1.4 days; 95% CI, -3.1 to 0.2 days). In this cohort study, overestimation of oxygen saturation by pulse oximetry led to delayed delivery of COVID-19 therapy and higher probability of readmission regardless of race. Black patients were more likely to have unrecognized need for therapy with potential implications for population-level health disparities.

Intermittent pulse oximeter as a measurement of newborn oxygen: a cross-sectional study

Introduction: Intermittent monitoring using fingertip pulse oximeters is increasingly being used in guiding oxygen therapy and screening congenital heart defects in newborns. However, there are no evidence-based guidelines for using fingertip pulse oximeters for intermittent monitoring of newborns in low-resource settings. This research assesses the validity of the fingertip pulse oximeter to measure oxygen saturation in newborns against the continuous monitoring pulse oximeter as a standard method. Method: A prospective study was conducted in the NICU and Neonatal Intermediate Unit of Dr. Soetomo Academic Hospital Surabaya. Newborns aged below 28 days using a respiratory device were included. Oxygen saturation measurements using a continuous monitoring pulse oximeter and intermittent pulse oximeter were done on the right hand and both feet. Paired t-test and Bland-Altman plot was performed to assess the validity. Results: Eighty-five neonates were included. There is an agreement between Intermittent and continuous pulse oximeters in the normoxic group with a limit of agreement -1.29 (CI 95% -1.62 to -0.95) to 1.29 (CI 95% 0.95 to 1.62) and hypoxic group with a limit of agreement -3.36 (CI 95% -4.29 to -2.44) to 3.00 (CI 95% 2.08 to 3.92). Intermittent pulse oximeter measurement requires a longer time for maximum results compared to continuous pulse oximeter (p=0.001). Conclusions: The intermittent pulse oximeter is available to be used alternately with a continuous pulse oximeter. However, it has limitations in hypoxemia settings, hence the application in real-time clinical practice needs further study.

Repeatability of Pulse Oximetry Measurements in Children During Triage in 2 Ugandan Hospitals.

In low- and middle-income countries, health workers use pulse oximeters for intermittent spot measurements of oxygen saturation (SpO2). However, the accuracy and reliability of pulse oximeters for spot measurements have not been determined. We evaluated the repeatability of spot measurements and the ideal observation time to guide recommendations during spot check measurements. Two 1-minute measurements were taken for the 3,903 subjects enrolled in the study conducted April 2020-January 2022 in Uganda, collecting 1 Hz SpO2 and signal quality index (SQI) data. The repeatability between the 2 measurements was assessed using an intraclass correlation coefficient (ICC), calculated using a median of all seconds of non-zero SpO2 values for each recording (any quality, Q1) and again with a quality filter only using seconds with SQI 90% or higher (good quality, Q2). The ICC was also recalculated for both conditions of Q1 and Q2 using the initial 5 seconds, then the initial 10 seconds, and continuing with 5-second increments up to the full 60 seconds. Lastly, the whole minute ICC was calculated with good quality (Q2), including only records where both measurements had a mean SQI of more than 70% (Q3). The repeatability ICC with condition Q1 was 0.591 (95% confidence interval [CI]=0.570, 0.611). Using only the first 5 seconds of each measurement reduced the repeatability to 0.200 (95% CI=0.169, 0.230). Filtering with Q2, the whole-minute ICC was 0.855 (95% CI=0.847, 0.864). The ICC did not improve beyond the first 35 seconds. For Q3, the repeatability rose to 0.908 (95% CI=0.901, 0.914). Training guidelines must emphasize the importance of signal quality and duration of measurement, targeting a minimum of 35 seconds of adequate-quality, stable data. In addition, the design of new devices should incorporate user prompts and force quality checks to encourage more accurate pulse oximetry measurements.

Interpretable machine learning for predicting 28-day all-cause in-hospital mortality for hypertensive ischemic or hemorrhagic stroke patients in the ICU: a multi-center retrospective cohort study with internal and external cross-validation.

Timely and accurate outcome prediction plays a critical role in guiding clinical decisions for hypertensive ischemic or hemorrhagic stroke patients admitted to the ICU. However, interpreting and translating the predictive models into clinical applications are as important as the prediction itself. This study aimed to develop an interpretable machine learning (IML) model that accurately predicts 28-day all-cause mortality in hypertensive ischemic or hemorrhagic stroke patients. A total of 4,274 hypertensive ischemic or hemorrhagic stroke patients admitted to the ICU in the USA from multicenter cohorts were included in this study to develop and validate the IML model. Five machine learning (ML) models were developed, including artificial neural network (ANN), gradient boosting machine (GBM), eXtreme Gradient Boosting (XGBoost), logistic regression (LR), and support vector machine (SVM), to predict mortality using the MIMIC-IV and eICU-CRD database in the USA. Feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. Model performance was evaluated based on the area under the curve (AUC), accuracy, positive predictive value (PPV), and negative predictive value (NPV). The ML model with the best predictive performance was selected for interpretability analysis. Finally, the SHapley Additive exPlanations (SHAP) method was employed to evaluate the risk of all-cause in-hospital mortality among hypertensive ischemic or hemorrhagic stroke patients admitted to the ICU. The XGBoost model demonstrated the best predictive performance, with the AUC values of 0.822, 0.739, and 0.700 in the training, test, and external cohorts, respectively. The analysis of feature importance revealed that age, ethnicity, white blood cell (WBC), hyperlipidemia, mean corpuscular volume (MCV), glucose, pulse oximeter oxygen saturation (SpO2), serum calcium, red blood cell distribution width (RDW), blood urea nitrogen (BUN), and bicarbonate were the 11 most important features. The SHAP plots were employed to interpret the XGBoost model. The XGBoost model accurately predicted 28-day all-cause in-hospital mortality among hypertensive ischemic or hemorrhagic stroke patients admitted to the ICU. The SHAP method can provide explicit explanations of personalized risk prediction, which can aid physicians in understanding the model.

Machine learning for the development of diagnostic models of decompensated heart failure or exacerbation of chronic obstructive pulmonary disease

Heart failure (HF) and chronic obstructive pulmonary disease (COPD) are two chronic diseases with the greatest adverse impact on the general population, and early detection of their decompensation is an important objective. However, very few diagnostic models have achieved adequate diagnostic performance. The aim of this trial was to develop diagnostic models of decompensated heart failure or COPD exacerbation with machine learning techniques based on physiological parameters. A total of 135 patients hospitalized for decompensated heart failure and/or COPD exacerbation were recruited. Each patient underwent three evaluations: one in the decompensated phase (during hospital admission) and two more consecutively in the compensated phase (at home, 30 days after discharge). In each evaluation, heart rate (HR) and oxygen saturation (Ox) were recorded continuously (with a pulse oximeter) during a period of walking for 6 min, followed by a recovery period of 4 min. To develop the diagnostic models, predictive characteristics related to HR and Ox were initially selected through classification algorithms. Potential predictors included age, sex and baseline disease (heart failure or COPD). Next, diagnostic classification models (compensated vs. decompensated phase) were developed through different machine learning techniques. The diagnostic performance of the developed models was evaluated according to sensitivity (S), specificity (E) and accuracy (A). Data from 22 patients with decompensated heart failure, 25 with COPD exacerbation and 13 with both decompensated pathologies were included in the analyses. Of the 96 characteristics of HR and Ox initially evaluated, 19 were selected. Age, sex and baseline disease did not provide greater discriminative power to the models. The techniques with S and E values above 80% were the logistic regression (S: 80.83%; E: 86.25%; A: 83.61%) and support vector machine (S: 81.67%; E: 85%; A: 82.78%) techniques. The diagnostic models developed achieved good diagnostic performance for decompensated HF or COPD exacerbation. To our knowledge, this study is the first to report diagnostic models of decompensation potentially applicable to both COPD and HF patients. However, these results are preliminary and warrant further investigation to be confirmed.