Novel in silico screening system for plant defense activators using deep learning-based prediction of reactive oxygen species accumulation.

BACKGROUND: Plant defense activators offer advantages over pesticides by avoiding the emergence of drug-resistant pathogens. However, only a limited number of compounds have been reported. Reactive oxygen species (ROS) act as not only antimicrobial agents but also signaling molecules that trigger immune responses. They also affect various cellular processes, highlighting the potential ROS modulators as plant defense activators. Establishing a high-throughput screening system for ROS modulators holds great promise for identifying lead chemical compounds with novel modes of action (MoAs). RESULTS: We established a novel in silico screening system for plant defense activators using deep learning-based predictions of ROS accumulation combined with the chemical properties of the compounds as explanatory variables. Our screening strategy comprised four phases: (1) development of a ROS inference system based on a deep neural network that combines ROS production data in plant cells and multidimensional chemical features of chemical compounds; (2) in silico extensive-scale screening of seven million commercially available compounds using the ROS inference model; (3) secondary screening by visualization of the chemical space of compounds using the generative topographic mapping; and (4) confirmation and validation of the identified compounds as potential ROS modulators within plant cells. We further characterized the effects of selected chemical compounds on plant cells using molecular biology methods, including pathogenic signal-triggered enzymatic ROS induction and programmed cell death as immune responses. Our results indicate that deep learning-based screening systems can rapidly and effectively identify potential immune signal-inducible ROS modulators with distinct chemical characteristics compared with the actual ROS measurement system in plant cells. CONCLUSIONS: We developed a model system capable of inferring a diverse range of ROS activity control agents that activate immune responses through the assimilation of chemical features of candidate pesticide compounds. By employing this system in the prescreening phase of actual ROS measurement in plant cells, we anticipate enhanced efficiency and reduced pesticide discovery costs. The in-silico screening methods for identifying plant ROS modulators hold the potential to facilitate the development of diverse plant defense activators with novel MoAs.

Development of Machine Learning Model for Selecting the 1st Coil in the Treatment of Cerebral Aneurysms by Coil Embolization.

To achieve good treatment outcomes in coil embolization for cerebral aneurysms, it is important to select an appropriate 1st coil for each aneurysm since it serves as a frame to support the subsequent coils to be deployed. However, its selection as appropriate size and length from a wide variety of lineups is not easy, especially for inexperienced neurosurgeons. We developed a machine learning model (MLM) to predict the optimal size and length of the 1st coil by learning information on patients and aneurysms that were previously treated with coil embolization successfully. The accuracy rates of the MLM for the test data were 86.3% and 83.4% in the prediction of size and length, respectively. In addition, the accuracy rates for the 30 cases showed good prediction by the MLM when compared with two different skilled neurosurgeons. Although the accuracy rate of the well-experienced neurosurgeon is similar to MLM, the inexperienced neurosurgeon showed a worse rate and can benefit from the method.Clinical Relevance- The developed MLM has the potential to assist in the selection of the 1st coil for aneurysms. A technically and cost efficient supply chain in the treatment of aneurysms may also be achieved by MLM application.

Development of a Machine Learning Model to Predict Cardiac Arrest during Transport of Trauma Patients.

BACKGROUND: Trauma is a serious medical and economic burden worldwide, and patients with traumatic injuries have a poor survival rate after cardiac arrest. The authors developed a prediction model specific to prehospital trauma care and used machine learning techniques to increase its accuracy. METHODS: This retrospective observational study analyzed data from patients with blunt trauma injuries due to traffic accidents and falls from January 1, 2018, to December 31, 2019. The data were collected from the National Emergency Medical Services Information System, which stores emergency medical service activity records nationwide in the United States. A random forest algorithm was used to develop a machine learning model. RESULTS: The prediction model had an area under the curve of 0.95 and a negative predictive value of 0.99. The feature importance of the predictive model was highest for the AVPU (Alert, Verbal, Pain, Unresponsive) scale, followed by oxygen saturation (SpO2). Among patients who were progressing to cardiac arrest, the cutoff value was 89% for SpO2 in nonalert patients. CONCLUSIONS: The machine learning model was highly accurate in identifying patients who did not develop cardiac arrest.

Machine learning for predicting successful extubation in patients receiving mechanical ventilation.

Ventilator liberation is one of the most critical decisions in the intensive care unit; however, prediction of extubation failure is difficult, and the proportion thereof remains high. Machine learning can potentially provide a breakthrough in the prediction of extubation success. A total of seven studies on the prediction of extubation success using machine learning have been published. These machine learning models were developed using data from electronic health records, 8-78 features, and algorithms such as artificial neural network, LightGBM, and XGBoost. Sensitivity ranged from 0.64 to 0.96, specificity ranged from 0.73 to 0.85, and area under the receiver operating characteristic curve ranged from 0.70 to 0.98. The features deemed most important included duration of mechanical ventilation, PaO2, blood urea nitrogen, heart rate, and Glasgow Coma Scale score. Although the studies had limitations, prediction of extubation success by machine learning has the potential to be a powerful tool. Further studies are needed to assess whether machine learning prediction reduces the incidence of extubation failure or prolongs the duration of ventilator use, thereby increasing tracheostomy and ventilator-related complications and mortality.

Machine Learning Prediction for Supplemental Oxygen Requirement in Patients with COVID-19.

BACKGROUND: The coronavirus disease (COVID-19) poses an urgent threat to global public health and is characterized by rapid disease progression even in mild cases. In this study, we investigated whether machine learning can be used to predict which patients will have a deteriorated condition and require oxygenation in asymptomatic or mild cases of COVID-19. METHODS: This single-center, retrospective, observational study included COVID-19 patients admitted to the hospital from February 1, 2020, to May 31, 2020, and who were either asymptomatic or presented with mild symptoms and did not require oxygen support on admission. Data on patient characteristics and vital signs were collected upon admission. We used seven machine learning algorithms, assessed their capability to predict exacerbation, and analyzed important influencing features using the best algorithm. RESULTS: In total, 210 patients were included in the study. Among them, 43 (19%) required oxygen therapy. Of all the models, the logistic regression model had the highest accuracy and precision. Logistic regression analysis showed that the model had an accuracy of 0.900, precision of 0.893, and recall of 0.605. The most important parameter for predictive capability was SpO2, followed by age, respiratory rate, and systolic blood pressure. CONCLUSION: In this study, we developed a machine learning model that can be used as a triage tool by clinicians to detect high-risk patients and disease progression earlier. Prospective validation studies are needed to verify the application of the tool in clinical practice.

CADM1 and SPC25 Gene Mutations in Lung Cancer Patients With Idiopathic Pulmonary Fibrosis.

INTRODUCTION: To investigate the genomic profiles of patients with lung cancer with idiopathic pulmonary fibrosis (IPF-LC), mechanism of carcinogenesis, and potential therapeutic targets. METHODS: We analyzed 29 matched, surgically resected, cancerous and noncancerous lung tissues (19 IPF-LC and 10 non-IPF-LC) by whole-exome sequencing and bioinformatics analysis and established a medical-engineering collaboration with the Department of Engineering of the Tokyo University of Science. RESULTS: In IPF-LC, CADM1 and SPC25 were mutated at a frequency of 47% (9 of 19) and 53% (10 of 19), respectively. Approximately one-third of the IPF-LC cases (7 of 19; 36%) had both mutations. Pathway analysis revealed that these two genes are involved in transforming growth factor-ß1 signaling. CADM1 and SPC25 gene mutations decreased the expression of CADM1 and increased that of SPC25 revealing transforming growth factor-ß1-induced epithelial-to-mesenchymal transition and cell proliferation in lung cancer cells. Furthermore, treatment with paclitaxel and DNMT1 inhibitor suppressed SPC25 expression. CONCLUSIONS: CADM1 and SPC25 gene mutations may be novel diagnostic markers and therapeutic targets for IPF-LC.

Machine Learning for Prediction of Successful Extubation of Mechanical Ventilated Patients in an Intensive Care Unit: A Retrospective Observational Study.

BACKGROUND: Ventilator weaning protocols are commonly implemented for patients receiving mechanical ventilation. However, despite such protocols, the rate of extubation failure remains high. This study analyzed the usefulness and accuracy of machine learning in predicting extubation success. METHODS: We retrospectively evaluated data from patients who underwent intubation for respiratory failure and received mechanical ventilation in an intensive care unit (ICU). Information on 57 features, including patient demographics, vital signs, laboratory data, and ventilator data, were extracted. Extubation failure was defined as re-intubation within 72 hours of extubation. For supervised learning, data were labeled as intubation-required or not. We used three learning algorithms (Random Forest, XGBoost, and LightGBM) to predict successful extubation. We also analyzed important features and evaluated the area under curve (AUC) and prediction metrics. RESULTS: Overall, 13 of the 117 included patients required re-intubation. LightGBM had the highest AUC (0.950), followed by XGBoost (0.946) and Random Forest (0.930). The accuracy, precision, and recall performance were 0.897, 0.910, and 0.909 for Random Forest; 0.910, 0.912, and 0.931 for XGBoost; and 0.927, 0.915, and 0.960 for LightGBM, respectively. The most important feature was duration of mechanical ventilation, followed by fraction of inspired oxygen, positive end-expiratory pressure, maximum and mean airway pressures, and Glasgow Coma Scale. CONCLUSIONS: Machine learning predicted successful extubation of ICU patients on mechanical ventilation. LightGBM had the best overall performance. Duration of mechanical ventilation was the most important feature in all models.

Indicators of Acute Kidney Injury as Biomarkers to Differentiate Heatstroke from Coronavirus Disease 2019: A Retrospective Multicenter Analysis.

BACKGROUND: Coronavirus disease 2019 (COVID-19) and heat-related illness are systemic febrile diseases. These illnesses must be differentiated during a COVID-19 pandemic in summer. However, no studies have compared and distinguished heat-related illness and COVID-19. We compared data from patients with early heat-related illness and those with COVID-19. METHODS: This retrospective observational study included 90 patients with early heat-related illness selected from the Heatstroke STUDY 2017-2019 (nationwide registries of heat-related illness in Japan) and 86 patients with laboratory-confirmed COVID-19 who had fever or fatigue and were admitted to one of two hospitals in Tokyo, Japan. RESULTS: Among vital signs, systolic blood pressure (119 vs. 125 mm Hg, p = 0.02), oxygen saturation (98% vs. 97%, p < 0.001), and body temperature (36.6°C vs. 37.6°C, p<0.001) showed significant between-group differences in the heatstroke and COVID-19 groups, respectively. The numerous intergroup differences in laboratory findings included disparities in white blood cell count (10.8 × 103/µL vs. 5.2 × 103/µL, p<0.001), creatinine (2.2 vs. 0.85 mg/dL, p<0.001), and C-reactive protein (0.2 vs. 2.8 mg/dL, p<0.001), although a logistic regression model achieved an area under the curve (AUC) of 0.966 using these three factors. A Random Forest machine learning model achieved an accuracy, precision, recall, and AUC of 0.908, 0.976, 0.842, and 0.978, respectively. Creatinine was the most important feature of this model. CONCLUSIONS: Acute kidney injury was associated with heat-related illness, which could be essential in distinguishing or evaluating patients with fever in the summer during a COVID-19 pandemic.