Reinforcement learning assisted oxygen therapy for COVID-19 patients under intensive care

Background Patients with severe Coronavirus disease 19 (COVID-19) typically require supplemental oxygen as an essential treatment. We developed a machine learning algorithm, based on deep Reinforcement Learning (RL), for continuous management of oxygen flow rate for critically ill patients under intensive care, which can identify the optimal personalized oxygen flow rate with strong potentials to reduce mortality rate relative to the current clinical practice. Methods We modeled the oxygen flow trajectory of COVID-19 patients and their health outcomes as a Markov decision process. Based on individual patient characteristics and health status, an optimal oxygen control policy is learned by using deep deterministic policy gradient (DDPG) and real-time recommends the oxygen flow rate to reduce the mortality rate. We assessed the performance of proposed methods through cross validation by using a retrospective cohort of 1372 critically ill patients with COVID-19 from New York University Langone Health ambulatory care with electronic health records from April 2020 to January 2021. Results The mean mortality rate under the RL algorithm is lower than the standard of care by 2.57% (95% CI: 2.08–3.06) reduction (P < 0.001) from 7.94% under the standard of care to 5.37% under our proposed algorithm. The averaged recommended oxygen flow rate is 1.28 L/min (95% CI: 1.14–1.42) lower than the rate delivered to patients. Thus, the RL algorithm could potentially lead to better intensive care treatment that can reduce the mortality rate, while saving the oxygen scarce resources. It can reduce the oxygen shortage issue and improve public health during the COVID-19 pandemic. Conclusions A personalized reinforcement learning oxygen flow control algorithm for COVID-19 patients under intensive care showed a substantial reduction in 7-day mortality rate as compared to the standard of care. In the overall cross validation cohort independent of the training data, mortality was lowest in patients for whom intensivists’ actual flow rate matched the RL decisions.

Effect of Rotten Butter Shock Load on Anaerobic Digestion of Chicken Manure

Anaerobic digestion is a popular method for improving fertilizing properties, but there is no report on the effect of shock load with butter on anaerobic digestion of chicken manure. Therefore, this study aimed to investigate the anaerobic digestion of chicken manure with butter addition. The volatile suspended solid (VSS) was set at 20g VSS/L with different butter additions from 0 to 60 g VSS/L and different oxygen flow rate (OFR) from 0 to 2.5 mL/h. The results showed that ammonia ranged from 0.072 g/L to 0.082 g/L, while the volatile acids ranged from 425 mg/L to 325 mg/L. The volatile organic acid was significantly influenced by a change in OFR compared to ammonia, while a correlation between hydrogen and hydrogen sulfide was observed. The results showed that the highest hydrogen and methane production was obtained at butter addition of 30 g VSS/L with OFR 1.4 mL/h with volumes of 78 mL and 25 L respectively. In addition, hydrogen sulfide emissions induced rapid growth with increase in butter concentration.

ANALYSIS OF BIOGAS COMPONENT PRODUCTION DURING ANAEROBIC DIGESTION OF SOUR CABBAGE IN MICROAERATION CONDITIONS UNDER DIFFERENT pH CONDITIONS

In the article, were checked influences of microaeration, pH, and VSS (Volatile Suspended Solid) for sour cab-bage anaerobic digestion. Results fermentation of sour cabbage under the condition of small oxygen addition are presented in this research can be classified as dark fermentation or hydrogenotrophic anaerobic digestion. The investigations were carried out for two concentrations 5 g VSS /L and 10 g VSS /L of sour cabbage at pH 6.0. The oxygen flow rates (OFR) for 5 g VSS /L were in the range of 0.53 to 3.3 mL/h for obtaining 2% to 8% of oxygen. In cases of low pH and microaeration, ethylene production was observed at a level below 0.05% in biogas. The highest volume of hydrogen for 5 g VSS/L was obtained for flow rate 0.58 O2 mL/h, giving hydrogen concentration in biogas in the range of 0 to 20%. For VSS 5 g/L and oxygen flow rate 0.58 mL/h; 0.021 L of hydrogen is produced per gram of VSS. In this case, VSS 10 g/L and oxygen flow rate 1.4 mL/h at pH 6.0, 0.03 L of hydrogen is generated per gram. Microaeration from 0.58 mL/h to 0.87 mL/h was propitious for hydrogen production at 5 g VSS/L of sour cabbage and 1.4 mL/h for 10 g/L. Another relevant factor is the volatile suspended solid factor of sour cabbage that caused optimal hydrogen production at VSS 89.32%.

Effect of Oxygen Flow Rate on Properties of Aluminum-Doped Indium-Saving Indium Tin Oxide (ITO) Thin Films Sputtered on Preheated Glass Substrates

Amorphous aluminum-doped indium tin oxide (ITO) thin films with a reduced indium oxide content of 50 mass% were manufactured by co-sputtering of ITO and Al2O3 targets in a mixed argon–oxygen atmosphere onto glass substrates preheated at 523 K. The oxygen gas flow rate and heat treatment temperature effects on the electrical, optical and structural properties of the films were studied. Thin films were characterized by means of a four-point probe, ultraviolet–visible-infrared (UV–Vis-IR) spectroscopy and X-ray diffraction. Transmittance of films and crystallization temperature increased as a result of doping of the ITO thin films by aluminum. The increase in oxygen flow rate led to an increase in transmittance and hindering of the crystallization of the aluminum-doped indium saving ITO thin films. It has been found that the film sputtered under optimal conditions showed a volume resistivity of 713 µΩcm, mobility of 30.8 cm2/V·s, carrier concentration of 2.9 × 1020 cm−3 and transmittance of over 90% in the visible range.

Impact of Oxygen Concentration Delivered via Nasal Cannula on Different Lung Conditions: A Bench Study

Background: Measuring the fraction of inspired oxygen (FiO2) is challenging in spontaneously breathing patients with impaired respiratory mechanics during low-flow nasal cannula. Our study investigates the FiO2 with varied tidal volume (VT) and respiratory rate (RR) among different lung mechanics and provides equations to estimate the FiO2. Methods: Two training and test lungs were used in this study, and the three lung mechanics (normal (R5/C60), restrictive (R20/C80), obstructive (R5/C40)) were designed. Spontaneous breathing with VT (300, 500, and 700 mL) and RR (10, 20, and 30 breaths/min) was simulated. The flow rate of the nasal cannula was set to 1, 3, and 5 L per minute (LPM), and the FiO2 was measured at the carina. Results: The lowest and highest FiO2 were evident during high (700 mL) and low VT (300 mL), respectively, among normal, restrictive, and obstructive lung models. As RR increases, this decreases the FiO2. However, we found that VT and oxygen flow rate are the principal factors influencing measured FiO2 by multiple linear regression analysis. Conclusions: Our data suggest that the actual FiO2 is never as high in spontaneously breathing patients as that estimated. VT and oxygen flow rate had a substantial impact on the FiO2.

Effect of Oxygen Flow Rate on Combustion Time and Temperature of Underground Coal Gasification

Underground Coal Gasification (UCG) is a process of converting coal in the ground into synthetic gas that has economic value. In the UCG process which will be carried out in the UCG prototype assisted by the presence of oxygen as a gasification agent, which this gasification agent will help the process of burning coal in the ground. The flow rate of oxygen in the process of UCG affecting the coal combustion temperature and effective flame from burning coal. The highest temperature at a flow rate of 5 l/min is 240oC, at an oxygen flow rate of 3 l/min the highest temperature is 143oC and at an oxygen flow rate of 2 l/min the highest temperature is 135oC and time effective flame at a flow rate of 5 l / min ie 80 minutes, effective burning time on the speed of the flow rate of 3 l / min ie for 120 minutes and time effective flame at a flow rate of 2 l / min ie for 165 minutes. This study proves that the greater the oxygen flow rate is used as the gasification agent at UCG process the lignite coal combustion temperatures will be high and effective flame coal combustion process will be more brief.