No abstract

Background Modern clinical care in intensive care units is full of rich data, and machine learning has great potential to support clinical decision-making. The development of intelligent machine learning–based clinical decision support systems is facing great opportunities and challenges. Clinical decision support systems may directly help clinicians accurately diagnose, predict outcomes, identify risk events, or decide treatments at the point of care. Objective We aimed to review the research and application of machine learning–enabled clinical decision support studies in intensive care units to help clinicians, researchers, developers, and policy makers better understand the advantages and limitations of machine learning–supported diagnosis, outcome prediction, risk event identification, and intensive care unit point-of-care recommendations. Methods We searched papers published in the PubMed database between January 1980 and October 2020. We defined selection criteria to identify papers that focused on machine learning–enabled clinical decision support studies in intensive care units and reviewed the following aspects: research topics, study cohorts, machine learning models, analysis variables, and evaluation metrics. Results A total of 643 papers were collected, and using our selection criteria, 97 studies were found. Studies were categorized into 4 topics—monitoring, detection, and diagnosis (13/97, 13.4%), early identification of clinical events (32/97, 33.0%), outcome prediction and prognosis assessment (46/97, 47.6%), and treatment decision (6/97, 6.2%). Of the 97 papers, 82 (84.5%) studies used data from adult patients, 9 (9.3%) studies used data from pediatric patients, and 6 (6.2%) studies used data from neonates. We found that 65 (67.0%) studies used data from a single center, and 32 (33.0%) studies used a multicenter data set; 88 (90.7%) studies used supervised learning, 3 (3.1%) studies used unsupervised learning, and 6 (6.2%) studies used reinforcement learning. Clinical variable categories, starting with the most frequently used, were demographic (n=74), laboratory values (n=59), vital signs (n=55), scores (n=48), ventilation parameters (n=43), comorbidities (n=27), medications (n=18), outcome (n=14), fluid balance (n=13), nonmedicine therapy (n=10), symptoms (n=7), and medical history (n=4). The most frequently adopted evaluation metrics for clinical data modeling studies included area under the receiver operating characteristic curve (n=61), sensitivity (n=51), specificity (n=41), accuracy (n=29), and positive predictive value (n=23). Conclusions Early identification of clinical and outcome prediction and prognosis assessment contributed to approximately 80% of studies included in this review. Using new algorithms to solve intensive care unit clinical problems by developing reinforcement learning, active learning, and time-series analysis methods for clinical decision support will be greater development prospects in the future.

Background: To analyze the clinical characteristics of the re-positive discharged COVID-19 patients and find markers to distinguish them.Methods：The demographic features, clinical symptoms, laboratory results, comorbidities, co-infections, treatments, illness severities and chest CT scan results of 267 patients were collected during 1st January and 15th February 2020. COVID-19 was diagnosed by RT-PCR. The subsequent clinical symptoms and nucleic acid test results was obtained during the 14 days post-hospitalization quarantine.Results: 30 out of 267 COVID-19 patients were detected re-positive during the post-hospitalization quarantine. Re-positive patients couldn’t be distinguished by demographic features, clinical symptoms, laboratory results, comorbidities, co-infections, treatments, chest CT scan results or subsequent clinical symptoms. However, the re-positive rate were found illness severity correlated, along with APACHE II and CURB-65.Conclusion: Common clinical characteristics arn’t able to distinguish re-positive patients. However, severe and critical cases with high APACHE II and CURB-65 scores are more likely to turn re-positive after discharge.Authors Shengyang He, Wenwu Sun, Kefu Zhou contributed equally to this work.

BACKGROUND Modern clinical care in intensive care units is full of rich data, and machine learning has great potential to support clinical decision-making. The development of intelligent machine learning–based clinical decision support systems is facing great opportunities and challenges. Clinical decision support systems may directly help clinicians accurately diagnose, predict outcomes, identify risk events, or decide treatments at the point of care. OBJECTIVE We aimed to review the research and application of machine learning–enabled clinical decision support studies in intensive care units to help clinicians, researchers, developers, and policy makers better understand the advantages and limitations of machine learning–supported diagnosis, outcome prediction, risk event identification, and intensive care unit point-of-care recommendations. METHODS We searched papers published in the PubMed database between January 1980 and October 2020. We defined selection criteria to identify papers that focused on machine learning–enabled clinical decision support studies in intensive care units and reviewed the following aspects: research topics, study cohorts, machine learning models, analysis variables, and evaluation metrics. RESULTS A total of 643 papers were collected, and using our selection criteria, 97 studies were found. Studies were categorized into 4 topics—monitoring, detection, and diagnosis (13/97, 13.4%), early identification of clinical events (32/97, 33.0%), outcome prediction and prognosis assessment (46/97, 47.6%), and treatment decision (6/97, 6.2%). Of the 97 papers, 82 (84.5%) studies used data from adult patients, 9 (9.3%) studies used data from pediatric patients, and 6 (6.2%) studies used data from neonates. We found that 65 (67.0%) studies used data from a single center, and 32 (33.0%) studies used a multicenter data set; 88 (90.7%) studies used supervised learning, 3 (3.1%) studies used unsupervised learning, and 6 (6.2%) studies used reinforcement learning. Clinical variable categories, starting with the most frequently used, were demographic (n=74), laboratory values (n=59), vital signs (n=55), scores (n=48), ventilation parameters (n=43), comorbidities (n=27), medications (n=18), outcome (n=14), fluid balance (n=13), nonmedicine therapy (n=10), symptoms (n=7), and medical history (n=4). The most frequently adopted evaluation metrics for clinical data modeling studies included area under the receiver operating characteristic curve (n=61), sensitivity (n=51), specificity (n=41), accuracy (n=29), and positive predictive value (n=23). CONCLUSIONS Early identification of clinical and outcome prediction and prognosis assessment contributed to approximately 80% of studies included in this review. Using new algorithms to solve intensive care unit clinical problems by developing reinforcement learning, active learning, and time-series analysis methods for clinical decision support will be greater development prospects in the future.

Recent epidemiologic studies show that increased dietary β‐cryptoxanthin (BCX) intake, rather than β‐carotene used in earlier human trials, is associated with reduced risk of lung cancer. However, BCX efficacy on lung carcinogenesis has not been reported. Here, we report the protective effects of different doses of BCX against lung carcinogenesis at the initiation and promotion stages in AJ mouse models. In the tobacco carcinogen NNK‐initiated lung carcinogenesis model, we found a 52–63% reduction of lung tumor multiplicity in mice pre‐treated with BCX at 0.2 and 2 mg kg BW‐1 d‐1, as compared to the NNK group, P<0.01. In the NNK‐initiated and nicotine‐promoted lung cancer model, we found that nicotine not only induced emphysema, a risk for lung cancer, but also increased greatly lung tumor multiplicity of the NNK‐treated mice. Notably, BCX at 2 and 4 mg kg BW‐1 d‐1 prevented nicotine‐induced emphysema and decreased tumor multiplicity by 86–91%, P<0.01. BCX protection was associated with suppressions of lung AKT activation, IL‐6 and early growth response‐1 mRNA. Unlike β‐carotene reported in prior animal studies, BCX induced retinoic acid receptor‐β mRNA. By HPLC analysis, liver BCX, not retinol, increased in the BCX supplemented mice. Our data suggest that BCX is a unique chemopreventive agent for lung cancer prevention, which is likely to be independent of its provitamin A activity.Grant Funding Source : NIH R01CA104932