Machine-Learning Approaches for Predicting the Need of Oxygen Therapy in Early-Stage COVID-19 in Japan: Multicenter Retrospective Observational Study.

Background: Early prediction of oxygen therapy in patients with coronavirus disease 2019 (COVID-19) is vital for triage. Several machine-learning prognostic models for COVID-19 are currently available. However, external validation of these models has rarely been performed. Therefore, most reported predictive performance is optimistic and has a high risk of bias. This study aimed to develop and validate a model that predicts oxygen therapy needs in the early stages of COVID-19 using a sizable multicenter dataset. Methods: This multicenter retrospective study included consecutive COVID-19 hospitalized patients confirmed by a reverse transcription chain reaction in 11 medical institutions in Fukui, Japan. We developed and validated seven machine-learning models (e.g., penalized logistic regression model) using routinely collected data (e.g., demographics, simple blood test). The primary outcome was the need for oxygen therapy (≥1 L/min or SpO2 ≤ 94%) during hospitalization. C-statistics, calibration slope, and association measures (e.g., sensitivity) evaluated the performance of the model using the test set (randomly selected 20% of data for internal validation). Among these seven models, the machine-learning model that showed the best performance was re-evaluated using an external dataset. We compared the model performances using the A-DROP criteria (modified version of CURB-65) as a conventional method. Results: Of the 396 patients with COVID-19 for the model development, 102 patients (26%) required oxygen therapy during hospitalization. For internal validation, machine-learning models, except for the k-point nearest neighbor, had a higher discrimination ability than the A-DORP criteria (P < 0.01). The XGboost had the highest c-statistic in the internal validation (0.92 vs. 0.69 in A-DROP criteria; P < 0.001). For the external validation with 728 temporal independent datasets (106 patients [15%] required oxygen therapy), the XG boost model had a higher c-statistic (0.88 vs. 0.69 in A-DROP criteria; P < 0.001). Conclusions: Machine-learning models demonstrated a more significant performance in predicting the need for oxygen therapy in the early stages of COVID-19.

Machine Learning Approaches for Predicting Difficult Airway and First-Pass Success in the Emergency Department: Multicenter Prospective Observational Study.

BACKGROUND: There is still room for improvement in the modified LEMON (look, evaluate, Mallampati, obstruction, neck mobility) criteria for difficult airway prediction and no prediction tool for first-pass success in the emergency department (ED). OBJECTIVE: We applied modern machine learning approaches to predict difficult airways and first-pass success. METHODS: In a multicenter prospective study that enrolled consecutive patients who underwent tracheal intubation in 13 EDs, we developed 7 machine learning models (eg, random forest model) using routinely collected data (eg, demographics, initial airway assessment). The outcomes were difficult airway and first-pass success. Model performance was evaluated using c-statistics, calibration slopes, and association measures (eg, sensitivity) in the test set (randomly selected 20% of the data). Their performance was compared with the modified LEMON criteria for difficult airway success and a logistic regression model for first-pass success. RESULTS: Of 10,741 patients who underwent intubation, 543 patients (5.1%) had a difficult airway, and 7690 patients (71.6%) had first-pass success. In predicting a difficult airway, machine learning models-except for k-point nearest neighbor and multilayer perceptron-had higher discrimination ability than the modified LEMON criteria (all, P≤.001). For example, the ensemble method had the highest c-statistic (0.74 vs 0.62 with the modified LEMON criteria; P<.001). Machine learning models-except k-point nearest neighbor and random forest models-had higher discrimination ability for first-pass success. In particular, the ensemble model had the highest c-statistic (0.81 vs 0.76 with the reference regression; P<.001). CONCLUSIONS: Machine learning models demonstrated greater ability for predicting difficult airway and first-pass success in the ED.

Calibration-Free Cuffless Blood Pressure Estimation Based on a Population With a Diverse Range of Age and Blood Pressure.

This study presents a new blood pressure (BP) estimation algorithm utilizing machine learning (ML). A cuffless device that can measure BP without calibration would be precious for portability, continuous measurement, and comfortability, but unfortunately, it does not currently exist. Conventional BP measurement with a cuff is standard, but this method has various problems like inaccurate BP measurement, poor portability, and painful cuff pressure. To overcome these disadvantages, many researchers have developed cuffless BP estimation devices. However, these devices are not clinically applicable because they require advanced preparation before use, such as calibration, do not follow international standards (81060-1:2007), or have been designed using insufficient data sets. The present study was conducted to combat these issues. We recruited 127 participants and obtained 878 raw datasets. According to international standards, our diverse data set included participants from different age groups with a wide variety of blood pressures. We utilized ML to formulate a BP estimation method that did not require calibration. The present study also conformed to the method required by international standards while calculating the level of error in BP estimation. Two essential methods were applied in this study: (a) grouping the participants into five subsets based on the relationship between the pulse transit time and systolic BP by a support vector machine ensemble with bagging (b) applying the information from the wavelet transformation of the pulse wave and the electrocardiogram to the linear regression BP estimation model for each group. For systolic BP, the standard deviation of error for the proposed BP estimation results with cross-validation was 7.74 mmHg, which was an improvement from 17.05 mmHg, as estimated by the conventional pulse-transit-time-based methods. For diastolic BP, the standard deviation of error was 6.42 mmHg for the proposed BP estimation, which was an improvement from 14.05mmHg. The purpose of the present study was to demonstrate and evaluate the performance of the newly developed BP estimation ML method that meets the international standard for non-invasive sphygmomanometers in a population with a diverse range of age and BP.

Estimation of respiratory signal from thoracic impedance cardiography in low electrical current.

A new method to estimate respiratory signal from thoracic impedance is proposed. To realize battery powered, wearable respiratory monitoring devices, low current impedance measurement techniques are desired. However, under low current conditions, conventional methods to separate cardiac and respiratory signals do not work well as the cardiac signal is much larger than the respiratory signal. In the proposed method, respiratory signal is estimated by calculating an envelope curve from the detected T waves of cardiac component. The results of the experiments show that the accuracy of proposed method is greater than conventional method.

Early event-related brain potentials that reflect interest for content information in the media.

This study investigated the relationship between event-related brain potentials (ERPs) to abridged content information in the media and the subsequent decisions to view the full content. Student volunteers participated in a task that simulated information selection on the basis of the content information. Screenshots of television clips and headlines of news articles on the Web were used as content information for the image condition and the headline condition, respectively. Following presentation of a stimulus containing content information, participants decided whether or not they would view the full content by pressing a select or a reject button. When the select button was pressed, participants were presented with a television clip or a news article. When the reject button was pressed, participants continued on to the next trial, without viewing further. In comparison with rejected stimuli, selected stimuli elicited a larger negative component, with a peak latency of ∼250 ms. The increase in the negative component was independent of the type of visual stimulus. These results suggest that interest toward content information is reflected in early-stage event-related brain potential responses.

Estimating uncomfortable loudness levels using evoked potentials to auditory stimuli for hearing aid fitting.

Determining the loudest sound level that a person can comfortably tolerate (uncomfortable loudness level: UCL) imposes a strain on people suffering from hearing loss. In the present study, we propose a method of estimating UCL based on auditory evoked potentials (AEPs). Adults with normal hearing (18 men aged 25-56 years) participated in the study. Three tone bursts (S1, S2 and S3; a triplet) of the same frequency (either 1k, 2k or 4k Hz) were presented to the right or left ear with an interstimulus interval of 300 ms. The sound intensity decreased gradually by 5 dB HL from 80 dB (S1) to 70 dB HL (S3). The interval between triplets was 450 ± 50 ms. The frequency of a given triplet differed from the frequency of the preceding triplet. An electroencephalogram was recorded from three scalp electrode sites (Cz, C3, and C4) with the right mastoid reference. The 900-ms period after the onset of the triplet was transformed to a wavelet coefficient and averaged separately by stimulated ear and tone frequency. The UCLs were estimated by linear discriminant analysis on the basis of trained data of the other participants' subjective UCLs and the wavelet coefficients. The mean estimation error was 4.9 ± 5.0 dB. This result suggests that the UCLs could be estimated successfully on the basis of AEPs to triplets of auditory tones.

Identification of event-related potentials elicited by conceptual mismatch between expectations and self-chosen TV images.

When a voluntary action is followed by an unexpected stimulus, a late positive potential (LPP) with a posterior scalp distribution is elicited in a latency range of 500-700 ms. In the present study, we examined what type of mismatch between expectations and action outcomes was reflected by the LPP. Twelve student volunteers participated in a task simulating choice of TV programs. After choosing one of three options displayed as a cue stimulus, they viewed a second stimulus (still TV image). To manipulate the type of expectation, three kinds of cue conditions were used: thumbnail image condition (three small TV images), category label condition (three words), and no cue condition (three question marks). Over trials, the second stimulus either matched (p = .80) or mismatched (p = .20) the chosen option. As compared to matched TV images, mismatched TV images elicited a larger LPP (500-700 ms) in the thumbnail image and category label conditions. In addition, a larger centroparietal P3 (400-450 ms) was elicited to mismatched TV images in the thumbnail image condition alone. LPP reflects a conceptual mismatch between a category-based expectation and an ensuing action outcome, whereas P3 reflects a perceptual mismatch between an image-based expectation and an action outcome.

Event-related potentials elicited by unexpected visual stimuli after voluntary actions.

Event-related potentials from visual stimuli that were presented after voluntary actions were recorded to examine how people expect their action effects. Participants pressed a button in response to a cue stimulus (L or R) either in the fixed condition where participants always pressed a center button or in the choice condition where they selectively pressed the corresponding left or right button. Immediately after the button press, a second stimulus (left or right) was presented visually to inform that their action was registered. When the second stimulus did not match the cue stimulus (p=.20), a late positive potential (LPP) with a posterior scalp distribution occurred in a latency range of 500-700 ms. The amplitude of this mismatch-related LPP was larger in the choice condition than in the fixed condition. The results suggest that the cognitive mismatch between the expected and actual action effects is reflected in the LPP, and the selection of a specific action strengthens the expectation of its action effect.

Predicting the effectiveness of population replacement strategy using mathematical modeling.

Charles Taylor and John Marshall explain the utility of mathematical modeling for evaluating the effectiveness of population replacement strategy. Insight is given into how computational models can provide information on the population dynamics of mosquitoes and the spread of transposable elements through A. gambiae subspecies. The ethical considerations of releasing genetically modified mosquitoes into the wild are discussed.