Health data science最新文献

Background: In charge of dispatching the ambulances, Emergency Medical Services (EMS) call center specialists often have difficulty deciding the acuity of a case given the information they can gather within a limited time. Although there are protocols to guide their decision-making, observed performance can still lack sensitivity and specificity. Machine learning models have been known to capture complex relationships that are subtle, and well-trained data models can yield accurate predictions in a split of a second.

Methods: In this study, we proposed a proof-of-concept approach to construct a machine learning model to better predict the acuity of emergency cases. We used more than 360,000 structured emergency call center records of cases received by the national emergency call center in Singapore from 2018 to 2020. Features were created using call records, and multiple machine learning models were trained.

Results: A Random Forest model achieved the best performance, reducing the over-triage rate by an absolute margin of 15% compared to the call center specialists while maintaining a similar level of under-triage rate.

Conclusions: The model has the potential to be deployed as a decision support tool for dispatchers alongside current protocols to optimize ambulance dispatch triage and the utilization of emergency ambulance resources.

Importance: Digestive system neoplasms (DSNs) are the leading cause of cancer-related mortality with a 5-year survival rate of less than 20%. Subjective evaluation of medical images including endoscopic images, whole slide images, computed tomography images, and magnetic resonance images plays a vital role in the clinical practice of DSNs, but with limited performance and increased workload of radiologists or pathologists. The application of artificial intelligence (AI) in medical image analysis holds promise to augment the visual interpretation of medical images, which could not only automate the complicated evaluation process but also convert medical images into quantitative imaging features that associated with tumor heterogeneity.

Highlights: We briefly introduce the methodology of AI for medical image analysis and then review its clinical applications including clinical auxiliary diagnosis, assessment of treatment response, and prognosis prediction on 4 typical DSNs including esophageal cancer, gastric cancer, colorectal cancer, and hepatocellular carcinoma.

Conclusion: AI technology has great potential in supporting the clinical diagnosis and treatment decision-making of DSNs. Several technical issues should be overcome before its application into clinical practice of DSNs.

Background: Due to the high burden of chronic pain, and the detrimental public health consequences of its treatment with opioids, there is a high-priority need to identify effective alternative therapies. Social media is a potentially valuable resource for knowledge about self-reported therapies by chronic pain sufferers.

Methods: We attempted to (a) verify the presence of large-scale chronic pain-related chatter on Twitter, (b) develop natural language processing and machine learning methods for automatically detecting self-disclosures, (c) collect longitudinal data posted by them, and (d) semiautomatically analyze the types of chronic pain-related information reported by them. We collected data using chronic pain-related hashtags and keywords and manually annotated 4,998 posts to indicate if they were self-reports of chronic pain experiences. We trained and evaluated several state-of-the-art supervised text classification models and deployed the best-performing classifier. We collected all publicly available posts from detected cohort members and conducted manual and natural language processing-driven descriptive analyses.

Results: Interannotator agreement for the binary annotation was 0.82 (Cohen's kappa). The RoBERTa model performed best (F₁ score: 0.84; 95% confidence interval: 0.80 to 0.89), and we used this model to classify all collected unlabeled posts. We discovered 22,795 self-reported chronic pain sufferers and collected over 3 million of their past posts. Further analyses revealed information about, but not limited to, alternative treatments, patient sentiments about treatments, side effects, and self-management strategies.

Conclusion: Our social media based approach will result in an automatically growing large cohort over time, and the data can be leveraged to identify effective opioid-alternative therapies for diverse chronic pain types.

Background. COVID-19 prevention and control measures might affect influenza epidemic in China since the nonpharmaceutical interventions (NPIs) and behavioral changes contain transmission of both SARS-CoV-2 and influenza virus. We aimed to explore the impact of COVID-19 prevention and control measures on influenza using data from the National Influenza Surveillance Network.Methods. The percentage of influenza-like illness (ILI%) in southern and northern China from 2010 to 2022 was collected from the National Influenza Surveillance Network. Weekly ILI% observed value from 2010 to 2019 was used to calculate estimated annual percentage change (EAPC) of ILI% with 95% confidence intervals (CIs). Time series analysis was applied to estimate weekly ILI% predicted values in 2020/2021 and 2021/2022 season. Impact index was used to explore the impact of COVID-19 prevention and control on influenza during nonpharmaceutical intervention and vaccination stages.Results. China influenza activity was affected by the COVID-19 pandemic and different prevention and control measures during 2020-2022. In 2020/2021 season, weekly ILI% observed value in both southern and northern China was at a low epidemic level, and there was no obvious epidemic peak in winter and spring. In 2021/2022 season, weekly ILI% observed value in southern and northern China showed a small peak in summer and epidemic peak in winter and spring. The weekly ILI% observed value was generally lower than the predicted value in southern and northern China during 2020-2022. The median of impact index of weekly ILI% was 15.11% in north and 22.37% in south in 2020/2021 season and decreased significantly to 2.20% in north and 3.89% in south in 2021/2022 season.Conclusion. In summary, there was a significant decrease in reported ILI in China during the 2020-2022 COVID-19 pandemic, particularly in winter and spring. Reduction of influenza virus infection might relate to everyday Chinese public health COVID-19 interventions. The confirmation of this relationship depends on future studies.

Background. Lung cancer remains the leading cause of death because of cancer globally in the past years. To inspire researchers with new targets and path-breaking directions for lung cancer research, this study is aimed at exploring the research trends and emerging hotspots in the lung cancer surgery literature in the recent decade.Methods. This cross-sectional study combined bibliometric and network analysis techniques to undertake a quantitative analysis of lung cancer surgery literature. Dimensions database was searched using keywords in a 10-year period (2012-2021). Publications were characterized by publication year, research countries, field citation ratio, cooperation status, research area, and emerging hotspots.Results. Overall, global scholarly outputs of lung cancer surgery had almost doubled during the recent decade, with China, Japan, and the United States leading the way, while Denmark and Belgium predominated in terms of scientific influence. Network analysis showed that international cooperation accounted for a relatively small portion in lung cancer surgery research, and the United States, China, and Europe were the prominent centers of international cooperation network. In the recent decade, research of lung cancer surgery majored in prevention, biomedical imaging, rehabilitation, and genetics, and the emerging research hotspots transformed into immunotherapy. Research on immunotherapy showed a considerable increase in scientific influence in the latest year.Conclusions. The study findings are expected to provide researchers and policymakers with interesting insights into the changing trends of lung cancer surgery research and further generate evidence to support decision-making in improving prognosis for patients with lung cancer.