Burden of lung cancer attributed to particulate matter pollution in China: an epidemiological study from 1990 to 2019

OBJECTIVES

The aim of this study was to examine the disease burden of lung cancer attributable to particulate matter (PM2.5) pollution in China from 1990 to 2019.

STUDY DESIGN

Data from the Global Burden of Disease Study 2019 were used to estimate the disease burden of tracheal, bronchus and lung cancer attributed to PM2.5 over time in China.

METHODS

Joinpoint regression models were applied to disability-adjusted life years (DALYs) to assess the time trends and estimate the impact of PM2.5 on the overall disease burden of lung cancer. Furthermore, age-period-cohort models were conducted to assess the relationships between lung cancer DALYs attributed to PM2.5 exposure and age, calendar period and birth cohort trends in China from 1990 to 2019.

RESULTS

Lung cancer DALYs attributable to household air pollution from solid fuels decreased with an average annual percent change (AAPC) of 2.9 % per 100,000 population, while those attributable to ambient particular matter pollution (APE) increased (AAPC: -4.7 % per 100,000 population) over the past 30 years. The burden of lung cancer in terms of DALYs in males was higher than in females, and it demonstrated an age-dependent increase. The period and cohort effects also had significant impacts on the DALYs rates of lung cancer attributable to APE, indicating an overall increase in lung cancer DALYs for all age groups in each year.

CONCLUSIONS

This study highlights the need for effective strategies to reduce PM2.5 exposure in China, particularly from outdoor sources. Gender differences and age, period and cohort effects observed in the study provide valuable insights into long-term trends of lung cancer burden attributed to PM2.5.

Dynamic Associations Between Centers for Disease Control and Prevention Social Media Contents and Epidemic Measures During COVID-19: Infoveillance Study

BACKGROUND

Health agencies have been widely adopting social media to disseminate important information, educate the public on emerging health issues, and understand public opinions. The Centers for Disease Control and Prevention (CDC) widely used social media platforms during the COVID-19 pandemic to communicate with the public and mitigate the disease in the United States. It is crucial to understand the relationships between the CDC's social media communications and the actual epidemic metrics to improve public health agencies' communication strategies during health emergencies.

OBJECTIVE

This study aimed to identify key topics in tweets posted by the CDC during the pandemic, investigate the temporal dynamics between these key topics and the actual COVID-19 epidemic measures, and make recommendations for the CDC's digital health communication strategies for future health emergencies.

METHODS

Two types of data were collected: (1) a total of 17,524 COVID-19-related English tweets posted by the CDC between December 7, 2019, and January 15, 2022, and (2) COVID-19 epidemic measures in the United States from the public GitHub repository of Johns Hopkins University from January 2020 to July 2022. Latent Dirichlet allocation topic modeling was applied to identify key topics from all COVID-19-related tweets posted by the CDC, and the final topics were determined by domain experts. Various multivariate time series analysis techniques were applied between each of the identified key topics and actual COVID-19 epidemic measures to quantify the dynamic associations between these 2 types of time series data.

RESULTS

Four major topics from the CDC's COVID-19 tweets were identified: (1) information on the prevention of health outcomes of COVID-19; (2) pediatric intervention and family safety; (3) updates of the epidemic situation of COVID-19; and (4) research and community engagement to curb COVID-19. Multivariate analyses showed that there were significant variabilities of progression between the CDC's topics and the actual COVID-19 epidemic measures. Some CDC topics showed substantial associations with the COVID-19 measures over different time spans throughout the pandemic, expressing similar temporal dynamics between these 2 types of time series data.

CONCLUSIONS

Our study is the first to comprehensively investigate the dynamic associations between topics discussed by the CDC on Twitter and the COVID-19 epidemic measures in the United States. We identified 4 major topic themes via topic modeling and explored how each of these topics was associated with each major epidemic measure by performing various multivariate time series analyses. We recommend that it is critical for public health agencies, such as the CDC, to update and disseminate timely and accurate information to the public and align major topics with key epidemic measures over time. We suggest that social media can help public health agencies to inform the public on health emergencies and to mitigate them effectively.

[Pay attention to the infectious complications in the clinical application of biological agents]

Biological agents have been widely used in the treatment of many clinical diseases by targeting specific immune cells or cytokines. In the course of clinical use, biological agents can lead to secondary immune deficiency, which increases the risk of infection. At present, there are no evidence-based guidelines or management opinions on the differences of infections caused by various biological agents, how to identify infectious complications in the course of treatment with different biological agents at an early stage, and how to take effective and targeted prevention. This paper summarizes the infection complications and their characteristics that need to be paid attention to in the clinical introduction of biological agents, aiming to help clinicians make reasonable decisions for infection complications in the process of using biological agents, reduce the incidence of infection, and improve the success rate of diagnosis and treatment.

Health Information on Pre-Exposure Prophylaxis From Search Engines and Twitter: Readability Analysis

BACKGROUND

Pre-exposure prophylaxis (PrEP) is proven to prevent HIV infection. However, PrEP uptake to date has been limited and inequitable. Analyzing the readability of existing PrEP-related information is important to understand the potential impact of available PrEP information on PrEP uptake and identify opportunities to improve PrEP-related education and communication.

OBJECTIVE

We examined the readability of web-based PrEP information identified using search engines and on Twitter. We investigated the readability of web-based PrEP documents, stratified by how the PrEP document was obtained on the web, information source, document format and communication method, PrEP modality, and intended audience.

METHODS

Web-based PrEP information in English was systematically identified using search engines and the Twitter API. We manually verified and categorized results and described the method used to obtain information, information source, document format and communication method, PrEP modality, and intended audience. Documents were converted to plain text for the analysis and readability of the collected documents was assessed using 4 readability indices. We conducted pairwise comparisons of readability based on how the PrEP document was obtained on the web, information source, document format, communication method, PrEP modality, and intended audience, then adjusted for multiple comparisons.

RESULTS

A total of 463 documents were identified. Overall, the readability of web-based PrEP information was at a higher level (10.2-grade reading level) than what is recommended for health information provided to the general public (ninth-grade reading level, as suggested by the Department of Health and Human Services). Brochures (n=33, 7% of all identified resources) were the only type of PrEP materials that achieved the target of ninth-grade reading level.

CONCLUSIONS

Web-based PrEP information is often written at a complex level for potential and current PrEP users to understand. This may hinder PrEP uptake for some people who would benefit from it. The readability of PrEP-related information found on the web should be improved to align more closely with health communication guidelines for reading level to improve access to this important health information, facilitate informed decisions by those with a need for PrEP, and realize national prevention goals for PrEP uptake and reducing new HIV infections in the United States.

[Doublecortin-like kinase 1 activates Hippo pathway to promote migration, invasion and proliferation of pancreatic cancer cells]

Objective: To explore the mechanism of Doublecortin-like kinase 1 (DCLK1) in promoting cell migration, invasion and proliferation in pancreatic cancer. Methods: The correlation between DCLK1 and Hippo pathway was analyzed using TCGA and GTEx databases and confirmed by fluorescence staining of pancreatic cancer tissue microarrays. At the cellular level, immunofluorescence staining of cell crawls and western blot assays were performed to clarify whether DCLK1 regulates yes associated protein1 (YAP1), a downstream effector of the Hippo pathway. Reverse transcription-quantitative real-time polymerase chain reaction (RT-qPCR) was used to analyze the expressions of YAP1 binding transcription factor TEA-DNA binding proteins (TEAD) and downstream malignant behavior-promoting molecules CYR61, EDN1, AREG, and CTGF. Transwell test of the DCLK1-overexpressing cells treated with the Hippo pathway inhibitor Verteporfin was used to examine whether the malignant behavior-promoting ability was blocked. Analysis of changes in the proliferation index of experimental cells used real-time label-free cells. Results: TCGA combined with GTEx data analysis showed that the expressions of DCLK1 and YAP1 molecules in pancreatic cancer tissues were significantly higher than those in adjacent tissues (P<0.05). Moreover, DCLK1was positively correlated with the expressions of many effectors in the Hippo pathway, including LATS1 (r=0.53, P<0.001), LATS2 (r=0.34, P<0.001), MOB1B (r=0.40, P<0.001). In addition, the tissue microarray of pancreatic cancer patients was stained with multicolor fluorescence, indicated that the high expression of DCLK1 in pancreatic cancer patients was accompanied by the up-regulated expression of YAP1. The expression of DCLK1 in pancreatic cancer cell lines was analyzed by the CCLE database. The results showed that the expression of DCLK1 in AsPC-1 and PANC-1 cells was low. Thus, we overexpressed DCLK1 in AsPC-1 and PANC-1 cell lines and found that DCLK1 overexpression in pancreatic cancer cell lines promoted YAP1 expression and accessible to the nucleus. In addition, DCLK1 up-regulated the expression of YAP1 binding transcription factor TEAD and increased the mRNA expression levels of downstream malignant behavior-promoting molecules. Finally, Verteporfin, an inhibitor of the Hippo pathway, could antagonize the cell's malignant behavior-promoting ability mediated by high expression of DCLK1. We found that the number of migrated cells with DCLK1 overexpressing AsPC-1 group was 68.33±7.09, which was significantly higher than 22.00±4.58 of DCLK1 overexpressing cells treated with Verteporfin (P<0.05). Similarly, the migration number of PANC-1 cells overexpressing DCLK1 was 65.66±8.73, which was significantly higher than 37.00±6.00 of the control group and 32.33±9.61 of Hippo pathway inhibitor-treated group (P<0.05). Meanwhile, the number of invasive cells in the DCLK1-overexpressed group was significantly higher than that in the DCLK1 wild-type group cells, while the Verteporfin-treated DCLK1-overexpressed cells showed a significant decrease. In addition, we monitored the cell proliferation index using the real-time cellular analysis (RTCA) assay, and the proliferation index of DCLK1-overexpressed AsPC-1 cells was 0.66±0.04, which was significantly higher than 0.38±0.01 of DCLK1 wild-type AsPC-1 cells (P<0.05) as well as 0.05±0.03 of DCLK1-overexpressed AsPC1 cells treated with Verteporfin (P<0.05). PANC-1 cells showed the same pattern, with a proliferation index of 0.77±0.04 for DCLK1-overexpressed PANC-1 cells, significantly higher than DCLK1-overexpressed PANC1 cells after Verteporfin treatment (0.14±0.05, P<0.05). Conclusion: The expression of DCLK1 is remarkably associated with the Hippo pathway, it promotes the migration, invasion, and proliferation of pancreatic cancer cells by activating the Hippo pathway.

Content and sentiment surveillance (CSI): A critical component for modeling modern epidemics

Comprehensive surveillance systems are the key to provide accurate data for effective modeling. Traditional symptom-based case surveillance has been joined with recent genomic, serologic, and environment surveillance to provide more integrated disease surveillance systems. A major gap in comprehensive disease surveillance is to accurately monitor potential population behavioral changes in real-time. Population-wide behaviors such as compliance with various interventions and vaccination acceptance significantly influence and drive the overall epidemic dynamics in the society. Original infoveillance utilizes online query data (e.g., Google and Wikipedia search of a specific content topic such as an epidemic) and later focuses on large volumes of online discourse data about the from social media platforms and further augments epidemic modeling. It mainly uses number of posts to approximate public awareness of the disease, and further compares with observed epidemic dynamics for better projection. The current COVID-19 pandemic shows that there is an urgency to further harness the rich, detailed content and sentiment information, which can provide more accurate and granular information on public awareness and perceptions toward multiple aspects of the disease, especially various interventions. In this perspective paper, we describe a novel conceptual analytical framework of content and sentiment infoveillance (CSI) and integration with epidemic modeling. This CSI framework includes data retrieval and pre-processing; information extraction via natural language processing to identify and quantify detailed time, location, content, and sentiment information; and integrating infoveillance with common epidemic modeling techniques of both mechanistic and data-driven methods. CSI complements and significantly enhances current epidemic models for more informed decision by integrating behavioral aspects from detailed, instantaneous infoveillance from massive social media data.

[Efficacy and safety of daptomycin in the treatment of gram-positive infective endocarditis: a meta-analysis]

Objective: To assess the efficacy and safety of daptomycin in the treatment of gram-positive infective endocarditis (IE) systematically. Methods: China Biology Medicine Database (CBM), China National Knowledge Internet (CNKI), Wanfang Data, VIP Database, PubMed, Embase, the Cochrane Library, and Web of Science were searched from the time of establishing databases to April 2022 to obtain relevant controlled and uncontrolled studies of daptomycin for gram-positive infective endocarditis, using key search terms ("daptomycin","gram-positive bacterial infections","endocarditis"). We performed literature screening according to inclusion/exclusion criteria, data extraction, and quality assessment, and performed random-effects meta-analyses for pooled results data using R software. Results: A total of 11 studies (including 13 articles) were included. The findings in the three controlled studies showed that in the treatment of staphylococcus aureus endocarditis, there was no statistically significant differences in in-hospital death risk (RR=0.66, 95%CI: 0.24-1.84, P=0.427) and 6-month death risk (RR=1.27, 95%CI: 0.75-2.14, P=0.374) for daptomycin versus anti-staphylococcal penicillin or vancomycin; in the treatment of enterococcal endocarditis, there was no statistically significant difference in death risk (both P>0.05) for daptomycin versus ampicillin combined with ceftriaxone (RR=0.39, 95%CI: 0.06-2.49) and ampicillin or vancomycin plus or minus gentamicin (RR=0.42, 95%CI: 0.05-3.36); and for daptomycin versus ampicillin or vancomycin combined with an aminoglycoside antibiotic, the differences in in-hospital death risk (RR=0.80, 95%CI: 0.11-5.83) and 6-month death risk (RR=0.47, 95%CI: 0.07-3.21) were not statistically significant(both P>0.05). In a cost-effectiveness study, daptomycin as first-line treatment could save the medical cost of 4 037 pounds per patient compared with vancomycin over a longer period of patient treatment. The results of the meta-analysis of uncontrolled studies showed that the mean clinical success rate of daptomycin for left-side endocarditis was 77% (95%CI: 70% to 83%; I²=28%), for MSSA-infective right-side endocarditis was 87% (95%CI: 73%-95%), and for MRSA-infective right-side endocarditis was 78% (95%CI: 38%-95%; I²=49%); while the mortality rate [mean mortality rate for left-side endocarditis was 13% (95%CI: 11%-17%; I²=0); the mortality rate for right-side endocarditis was reported in only 2 studies, 3% and 27%, respectively] or the rate of daptomycin-related adverse events (4%) was within the acceptable ranges for clinical practice. Conclusions: The death risk in the treatment of infective endocarditis with dattomycin is comparable to that of other antibiotics, and the clinical success rate is higher. Some efficacy may be achieved with daptomycin while other treatments are not effective in treating IE.

A Novel Approach to Characterize State-level Food Environment and Predict Obesity Rate Using Social Media Data: Correlational Study

BACKGROUND

Community obesity outcomes can reflect the food environment to which the community belongs. Recent studies have suggested that the local food environment can be measured by the degree of food accessibility, and survey data are normally used to calculate food accessibility. However, compared with survey data, social media data are organic, continuously updated, and cheaper to collect.

OBJECTIVE

The objective of our study was to use publicly available social media data to learn the relationship between food environment and obesity rates at the state level.

METHODS

To characterize the caloric information of the local food environment, we used food categories from Yelp and collected caloric information from MyFitnessPal for each category based on their popular dishes. We then calculated the average calories for each category and created a weighted score for each state. We also calculated 2 other dimensions from the concept of access, acceptability and affordability, to build obesity prediction models.

RESULTS

The local food environment characterized using only publicly available social media data had a statistically significant correlation with the state obesity rate. We achieved a Pearson correlation of 0.796 between the predicted obesity rate and the reported obesity rate from the Behavioral Risk Factor Surveillance System across US states and the District of Columbia. The model with 3 generated feature sets achieved the best performance.

CONCLUSIONS

Our study proposed a method for characterizing state-level food environments only using continuously updated social media data. State-level food environments were accurately described using social media data, and the model also showed a disparity in the available food between states with different obesity rates. The proposed method should elastically apply to local food environments of different sizes and predict obesity rates effectively.

Input feature design and its impact on the performance of deep learning models for predicting fluence maps in intensity-modulated radiation therapy

Objective. Deep learning (DL) models for fluence map prediction (FMP) have great potential to reduce treatment planning time in intensity-modulated radiation therapy (IMRT) by avoiding the lengthy inverse optimization process. This study aims to improve the rigor of input feature design in a DL-FMP model by examining how different designs of input features influence model prediction performance.Approach. This study included 231 head-and-neck intensity-modulated radiation therapy patients. Three input feature designs were investigated. The first design (D1) assumed that information of all critical structures from all beam angles should be combined to predict fluence maps. The second design (D2) assumed that local anatomical information was sufficient for predicting radiation intensity of a beamlet at a respective beam angle. The third design (D3) assumed the need for both local anatomical information and inter-beam modulation to predict radiation intensity values of the beamlets that intersect at a voxel. For each input design, we tailored the DL model accordingly. All models were trained using the same set of ground truth plans (GT plans). The plans generated by DL models (DL plans) were analyzed using key dose-volume metrics. One-way ANOVA with multiple comparisons correction (Bonferroni method) was performed (significance level = 0.05).Main results. For PTV-related metrics, all DL plans had significantly higher maximum dose (p < 0.001), conformity index (p < 0.001), and heterogeneity index (p < 0.001) compared to GT plans, with D2 being the worst performer. Meanwhile, except for cord+5 mm (p < 0.001), DL plans of all designs resulted in OAR dose metrics that are comparable to those of GT plans.Significance. Local anatomical information contains most of the information that DL models need to predict fluence maps for clinically acceptable OAR sparing. Input features from beam angles are needed to achieve the best PTV coverage. These results provide valuable insights for further improvement of DL-FMP models and DL models in general.

Statins and Left Ventricular Ejection Fraction Following Doxorubicin Treatment

BACKGROUND

Statins taken for cardiovascular indications by patients with breast cancer and lymphoma during doxorubicin treatment may attenuate left ventricular ejection fraction (LVEF) decline, but the effect of statins on LVEF among patients with no cardiovascular indications is unknown.

METHODS

A double-blind, placebo-controlled, 24-month randomized trial of 40 mg of atorvastatin per day administered to patients with breast cancer and lymphoma receiving doxorubicin was conducted within the National Cancer Institute Community Oncology Research Program across 31 sites in the United States. At pretreatment and then 6 and 24 months after initiating doxorubicin, we assessed left ventricular (LV) volumes, strain, mass, and LVEF through cardiac magnetic resonance imaging, along with cognitive function and serum markers of inflammation. The primary outcome was the difference in 24-month LVEF between placebo and treatment groups, adjusted for pretreatment LVEF.

RESULTS

A total of 279 participants were enrolled in the trial. Participants had a mean (±SD) age of 49±12 years; 92% were women; and 83% were White. The mean (±SD) LVEF values were 61.7±5.5% before treatment and 57.4±6.8% at 24 months in the placebo group and 62.6±6.4% before treatment and 57.7±5.6% at 24 months in the atorvastatin group. On the basis of a multiple imputed data set for missing data and adjusted for each individual's pretreatment LVEF, 24-month declines in LVEF averaged 3.3±0.6 percentage points and 3.2±0.7 percentage points, for those randomly assigned to placebo versus statins, respectively (P=0.93). Across both treatment arms, similar percentages of individuals experienced changes of more than 10 percentage points in LVEF, LV strain, LV mass, cognition, and inflammation biomarkers, including among those with greater than 90% drug compliance.

CONCLUSIONS

In patients with breast cancer and lymphoma with no existing indication for statin therapy, prospective statin administration did not affect LVEF declines 2 years after doxorubicin. (Funded by the National Institutes of Health; ClinicalTrials.gov number, NCT01988571.).

The role of booster vaccination and ongoing viral evolution in seasonal circulation of SARS-CoV-2

Periodic resurgences of COVID-19 in the coming years can be expected, while public health interventions may be able to reduce their intensity. We used a transmission model to assess how the use of booster doses and non-pharmaceutical interventions (NPIs) amid ongoing pathogen evolution might influence future transmission waves. We find that incidence is likely to increase as NPIs relax, with a second seasonally driven surge expected in autumn 2022. However, booster doses can greatly reduce the intensity of both waves and reduce cumulative deaths by 20% between 7 January 2022 and 7 January 2023. Reintroducing NPIs during the autumn as incidence begins to increase again could also be impactful. Combining boosters and NPIs results in a 30% decrease in cumulative deaths, with potential for greater impacts if variant-adapted boosters are used. Reintroducing these NPIs in autumn 2022 as transmission rates increase provides similar benefits to sustaining NPIs indefinitely (307 000 deaths with indefinite NPIs and boosters compared with 304 000 deaths with transient NPIs and boosters). If novel variants with increased transmissibility or immune escape emerge, deaths will be higher, but vaccination and NPIs are expected to remain effective tools to decrease both cumulative and peak health system burden, providing proportionally similar relative impacts.

Randomized trial of atorvastatin during and following receipt of doxorubicin for breast cancer and lymphoma (WF-98213)

12072

Background: Statins taken for cardiovascular (CV) indications by breast cancer (BC) and lymphoma survivors during doxorubicin (DOX) treatment may attenuate left ventricular ejection fraction (LVEF) decline, but statin impact among these survivors with no CV indications is unknown. Methods: In 279 patients from 31 cancer centers, we conducted a double blind, placebo-controlled, 24-month randomized trial of 40mg/day atorvastatin among those receiving DOX for BC or lymphoma. At pretreatment, six and 24 months after initiating DOX for BC or lymphoma, we assessed LV volumes, strain, mass, and LVEF (via cardiac magnetic resonance), cognitive function and serum markers of inflammation. Using a linear model adjusted for pretreatment measures, our primary analysis assessed change in LVEF over time by randomization group. Results: Participants were aged 49±12 years; 92% women, 83% white race. The mean pooled LVEF decline from pretreatment to 24 months was 62.2±6.0% to 57.6±6.3% (p < 0.001). Adjusting for pretreatment LVEF, 24-month declines in LVEF averaged 3.5±0.5% and 3.3±0.5% respectively for placebo vs statins (p = 0.83). Both randomized groups were similar for: incidence of > 10% change in LVEF, LV strain, LV mass, cognition and inflammation biomarkers, including among those > 90% study drug compliant (p > 0.05 for all). Conclusions: In BC and lymphoma survivors with no existing indication for statin therapy, prospective statin administration does not appear to impact LVEF declines two years after doxorubicin. Clinical trial information: NCT01988571. [Table: see text]

Machine learning models for accurate pretreatment prediction of chemotherapy associated LV dysfunction in patients with breast cancer and lymphoma receiving chemotherapy (WF-98213 PREVENT and CCCWFU9912 DETECT IV)

1553

Background: Cancer survivors receiving potentially cardiotoxic chemotherapy are at increased risk for developing left ventricular (LV) dysfunction. We implemented machine learning (ML) models to predict future LV dysfunction in patients with breast cancer or lymphoma scheduled to receive potentially cardiotoxic chemotherapy. Methods: We utilized prospectively collected data from NIH studies R01HL118740 (supported by the Wake Forest NCORP Research Base (UG1CA189824)) and R01CA167821. Data included measurements of LV function and demographic factors before, during, and 24 months after initiating potentially cardiotoxic chemotherapy. The two datasets were used both separately and collectively in the development of multiple ML models including penalized linear regression, support vector machine, and random forest (RF). A data preprocessing step properly handled missing information, data imbalance, and encoding. Hyperparameter tuning was performed using cross validation of training data. The final models were assessed with a 20% hold-out test dataset. Cardiotoxicity was defined as a pre- to 24-month post cancer treatment decline in LV ejection fraction (LVEF) of > 10% or to an absolute value of < 50%. Results: 276 patients were included in ML models (7% men, 93% women; age 52±13 years). The RF model based on the combined dataset had the best performance with a prediction accuracy, sensitivity, and specificity of 0.94, 0.81, and 0.98, respectively. The most important variables assessed pre-treatment as measured by the Gini impurity factor were in descending order, LVEF, global LV circumferential strain, LV end-systolic volume, body mass index, LV stroke volume, LV end-diastolic volume, and LV mass. Conclusions: Prior to cancer treatment, supervised ML methods such as RF models predicted declines in LVEF of > 10% and/or to absolute values below 50% would occur 24 months after initiating chemotherapy for breast cancer or lymphoma. With further improvement and validation using larger datasets, these models may play an important role in cardio-oncology care during and following cancer treatment.

727 BOOSTING BONE HEALTH: IMPROVING JUNIOR DOCTORS’ CONFIDENCE IN ASSESSING AND MANAGING FRAGILITY FRACTURES

Introduction

Fragility fractures are a major disease burden in the UK. With an ageing population and number of fragility fractures predicted to double in 50 years, prevention in this high-risk population needs to be addressed. This audit aimed to examine the assessment of fracture risk in patients presenting with fragility fractures and improve awareness amongst trainee doctors through education.

Methods

A retrospective study was conducted on patients over 65 years admitted with fragility fractures, excluding neck of femur, from January to March 2021 (n = 51). Data was collected on Fracture Risk Assessment Tool (FRAX) scores, dual energy X-ray absorptiometry (DEXA) scans, and risk factors including body mass index (BMI), previous fragility fracture, smoking, alcohol intake, and serum calcium and vitamin D. A teaching seminar for junior doctors was delivered to increase confidence in assessing and managing fragility fractures.

Results

The mean age of patients was 79, with most common presentations being proximal humerus, distal femur and ankle fractures. 46% of patients had a previous fragility fracture. Smoking and alcohol history were documented in 72% and 60% of patients respectively, and 29% had BMIs calculated. 68% had calcium and 45% had vitamin D checked. DEXA scans occurred in 12%, all of whom had osteopenia or osteoporosis. Over half of patients were already on bone protection and 28% were subsequently started on bisphosphonates. A teaching session was delivered to junior doctors (n = 10), leading to improved confidence in assessing fracture risk by 30%, and improved confidence in managing fragility fractures by 35%. Knowledge of FRAX score increased from 62% to 100%.

Conclusion

A significant proportion of the over-65 population are likely to present with fragility fractures. Improving awareness and confidence amongst junior doctors can lead to identification of risk factors and help better prevent and manage fragility fractures in this high-risk population.

Prediction and verification of survival in patients with non-small-cell lung cancer based on an integrated radiomics nomogram

AIM

To develop and validate a nomogram to predict 1-, 2-, and 5-year survival in patients with non-small-cell lung cancer (NSCLC) by combining optimised radiomics features, clinicopathological factors, and conventional image features extracted from three-dimensional (3D) computed tomography (CT) images.

MATERIALS AND METHODS

A total of 172 patients with NSCLC were selected to construct the model, and 74 and 72 patients were selected for internal validation and external testing, respectively. A total of 828 radiomics features were extracted from each patient's 3D CT images. Univariable Cox regression and least absolute shrinkage and selection operator (LASSO) regression were used to select features and generate a radiomics signature (radscore). The performance of the nomogram was evaluated by calibration curves, clinical practicability, and the c-index. Kaplan-Meier (KM) analysis was used to compare the overall survival (OS) between the two subgroups.

RESULT

The radiomics features of the NSCLC patients correlated significantly with survival time. The c-indexes of the nomogram in the training cohort, internal validation cohort, and external test cohort were 0.670, 0.658, and 0.660, respectively. The calibration curves showed that the predicted survival time was close to the actual survival time. Decision curve analysis shows that the nomogram could be useful in the clinic. According to KM analysis, the 1-, 2- and 5-year survival rates of the low-risk group were higher than those of the high-risk group.

CONCLUSION

The nomogram, combining the radscore, clinicopathological factors, and conventional CT parameters, can improve the accuracy of survival prediction in patients with NSCLC.

Clinical outcomes of keratinized mucosa augmentation in jaws reconstructed with fibula or iliac bone flaps

This prospective study was undertaken to evaluate the treatment outcomes of keratinized mucosa augmentation (KMA) on the buccal and palatal/lingual sides of implants in jaws reconstructed after oncological surgery. Forty-two implants in 12 patients whose jaws had been reconstructed with a fibula or iliac bone flap were included. KMA was performed at 3 months after implant placement; this included an apically displaced partial-thickness flap and a free gingival graft (FGG) around the implants to increase the keratinized mucosa width (KMW). Patients were followed up for at least 6 months post-surgery. KMW, shrinkage, and patient pain and discomfort measured on a visual analogue scale were analysed. A histological analysis was performed of tissue epithelium from two patients. The results showed that KMW was >2 mm on both the buccal and palatal/lingual sides during follow-up. Before surgery, histological analysis showed epithelium with no epithelial spikes; normal keratinized epithelial spikes were observed at 8 weeks after KMA. Greater KMW was observed around implants in reconstructed maxillae than around those in reconstructed mandibles (P < 0.001). Patients felt more pain at the donor site than at the recipient site during the first 3 days post-surgery. KMA with FGG was predictable in reconstructed jaws and may help maintain the long-term stability of implants.

Assessing the robustness of artificial intelligence powered planning tools in radiotherapy clinical settings-a phantom simulation approach

Background

Artificial intelligence (AI) based radiotherapy treatment planning tools have gained interest in automating the treatment planning process. It is essential to understand their overall robustness in various clinical scenarios. This is an existing gap between many AI based tools and their actual clinical deployment. This study works to fill the gap for AI based treatment planning by investigating a clinical robustness assessment (CRA) tool for the AI based planning methods using a phantom simulation approach.

Methods

A cylindrical phantom was created in the treatment planning system (TPS) with the axial dimension of 30 cm by 18 cm. Key structures involved in pancreas stereotactic body radiation therapy (SBRT) including PTV25, PTV33, C-Loop, stomach, bowel and liver were created within the phantom. Several simulation scenarios were created to mimic multiple scenarios of anatomical changes, including displacement, expansion, rotation and combination of three. The goal of treatment planning was to deliver 25 Gy to PTV25 and 33 Gy to PTV33 in 5 fractions in simultaneous integral boost (SIB) manner while limiting luminal organ-at-risk (OAR) max dose to be under 29 Gy. A previously developed deep learning based AI treatment planning tool for pancreas SBRT was identified as the validation object. For each scenario, the anatomy information was fed into the AI tool and the final fluence map associated to the plan was generated, which was subsequently sent to TPS for leaf sequencing and dose calculation. The final auto plan's quality was analyzed against the treatment planning constraint. The final plans' quality was further analyzed to evaluate potential correlation with anatomical changes using the Manhattan plot.

Results

A total of 32 scenarios were simulated in this study. For all scenarios, the mean PTV25 V25Gy of the AI based auto plans was 96.7% while mean PTV33 V33Gy was 82.2%. Large variation (16.3%) in PTV33 V33Gy was observed due to anatomical variations, a.k.a. proximity of luminal structure to PTV33. Mean max dose was 28.55, 27.68 and 24.63 Gy for C-Loop, bowel and stomach, respectively. Using D_0.03cc as max dose surrogate, the value was 28.03, 27.12 and 23.84 Gy for C-Loop, bowel and stomach, respectively. Max dose constraint of 29 Gy was achieved for 81.3% cases for C-Loop and stomach, and 78.1% for bowel. Using D_0.03cc as max dose surrogate, the passing rate was 90.6% for C-Loop, and 81.3% for bowel and stomach. Manhattan plot revealed high correlation between the OAR over dose and the minimal distance between the PTV33 and OAR.

Conclusions

The results showed promising robustness of the pancreas SBRT AI tool, providing important evidence of its readiness for clinical implementation. The established workflow could guide the process of assuring clinical readiness of future AI based treatment planning tools.

Transfer learning for fluence map prediction in adrenal stereotactic body radiation therapy

Objective:To design a deep transfer learning framework for modeling fluence map predictions for stereotactic body radiation therapy (SBRT) of adrenal cancer and similar sites that usually have a small number of cases.Approach:We developed a transfer learning framework for adrenal SBRT planning that leverages knowledge in a pancreas SBRT planning model. Treatment plans from the two sites had different dose prescriptions and beam settings but both prioritized gastrointestinal sparing. A base framework was first trained with 100 pancreas cases. This framework consists of two convolutional neural networks (CNN), which predict individual beam doses (BD-CNN) and fluence maps (FM-CNN) sequentially for 9-beam intensity-modulated radiation therapy (IMRT) plans. Forty-five adrenal plans were split into training/validation/test sets with the ratio of 20/10/15. The base BD-CNN was re-trained with transfer learning using 5/10/15/20 adrenal training cases to produce multiple candidate adrenal BD-CNN models. The base FM-CNN was directly used for adrenal cases. The deep learning (DL) plans were evaluated by several clinically relevant dosimetric endpoints, producing a percentage score relative to the clinical plans.Main results:Transfer learning significantly reduced the number of training cases and training time needed to train such a DL framework. The adrenal transfer learning model trained with 5/10/15/20 cases achieved validation plan scores of 85.4/91.2/90.7/89.4, suggesting that model performance saturated with 10 training cases. Meanwhile, a model using all 20 adrenal training cases without transfer learning only scored 80.5. For the final test set, the 5/10/15/20-case models achieved scores of 73.5/75.3/78.9/83.3.Significance:It is feasible to use deep transfer learning to train an IMRT fluence prediction framework. This technique could adapt to different dose prescriptions and beam configurations. This framework potentially enables DL modeling for clinical sites that have a limited dataset, either due to few cases or due to rapid technology evolution.

Artificial intelligence applications in intensity modulated radiation treatment planning: an overview

Artificial intelligence (AI) refers to methods that improve and automate challenging human tasks by systematically capturing and applying relevant knowledge in these tasks. Over the past decades, a number of approaches have been developed to address different types and needs of system intelligence ranging from search strategies to knowledge representation and inference to robotic planning. In the context of radiation treatment planning, multiple AI approaches may be adopted to improve the planning quality and efficiency. For example, knowledge representation and inference methods may improve dose prescription by integrating and reasoning about the domain knowledge described in many clinical guidelines and clinical trials reports. In this review, we will focus on the most studied AI approach in intensity modulated radiation therapy (IMRT)/volumetric modulated arc therapy (VMAT)-machine learning (ML) and describe our recent efforts in applying ML to improve the quality, consistency, and efficiency of IMRT/VMAT planning. With the available high-quality data, we can build models to accurately predict critical variables for each step of the planning process and thus automate and improve its outcomes. Specific to the IMRT/VMAT planning process, we can build models for each of the four critical components in the process: dose-volume histogram (DVH), Dose, Fluence, and Human Planner. These models can be divided into two general groups. The first group focuses on encoding prior experience and knowledge through ML and more recently deep learning (DL) from prior clinical plans and using these models to predict the optimal DVH (DVH prediction model), or 3D dose distribution (dose prediction model), or fluence map (fluence map model). The goal of these models is to reduce or remove the trial-and-error process and guarantee consistently high-quality plans. The second group of models focuses on mimicking human planners' decision-making process (planning strategy model) during the iterative adjustments/guidance of the optimization engine. Each critical step of the IMRT/VMAT treatment planning process can be improved and automated by AI methods. As more training data becomes available and more sophisticated models are developed, we can expect that the AI methods in treatment planning will continue to improve accuracy, efficiency, and robustness.

A data-driven approach to optimal beam/arc angle selection for liver stereotactic body radiation therapy treatment planning

BACKGROUND

Stereotactic body radiation therapy (SBRT) for liver cancer has shown promising therapeutic effects. Effective treatment relies not only on the precise delivery provided by image-guided radiation therapy (IGRT) but also high dose gradient formed around the treatment volume to spare functional liver tissue, which is highly dependent on the beam/arc angle selection. In this study, we aim to develop a decision support model to learn human planner's beam navigation approach for beam angle/arc angle selection for liver SBRT.

METHODS

A total of 27 liver SBRT/HIGRT patients (10 IMRT, 17 VMAT/DCA) were included in this study. A dosimetric budget index was defined for each beam angle/control point considering dose penetration through the patient body and liver tissue. Optimal beam angle setting (beam angles for IMRT and start/terminal angle for VMAT/DCA) was determined by minimizing the loss function defined as the sum of total dosimetric budget index and beam span penalty function. Leave-one-out validation was exercised on all 27 cases while weighting coefficients in the loss function was tuned in nested cross validation. To compare the efficacy of the model, a model plan was generated using automatically generated beam setting while retaining the original optimization constraints in the clinical plan. Model plan was normalized to the same planning target volume (PTV) V100% as the clinical plans. Dosimetric endpoints including PTV D98%, D2%, liver V20Gy and total MU were compared between two plan groups. Wilcoxon Signed-Rank test was performed with the null hypothesis being that no difference exists between two plan groups.

RESULTS

Beam setting prediction was instantaneous. Mean PTV D98% was 91.3% and 91.3% (P=0.566), while mean PTV D2% was 107.9% and 108.1% (P=0.164) for clinical plan and model plan respectively. Liver V20Gy showed no significant difference (P=0.590) with 23.3% for clinical plan and 23.4% for the model plan. Total MU is comparable (P=0.256) between the clinical plan (avg. 2,389.6) and model plan (avg. 2,319.6).

CONCLUSIONS

The evidence driven beam setting model yielded similar plan quality as hand-crafted clinical plan. It is capable of capturing human's knowledge in beam selection decision making. This model could facilitate decision making for beam angle selection while eliminating lengthy trial-and-error process of adjusting beam setting during liver SBRT treatment planning.

Insights of an AI agent via analysis of prediction errors: a case study of fluence map prediction for radiation therapy planning

Purpose.We have previously reported an artificial intelligence (AI) agent that automatically generates intensity-modulated radiation therapy (IMRT) plans via fluence map prediction, by-passing inverse planning. This AI agent achieved clinically comparable quality for prostate cases, but its performance on head-and-neck patients leaves room for improvement. This study aims to collect insights of the deep-learning-based (DL-based) fluence map prediction model by systematically analyzing its prediction errors.Methods.From the modeling perspective, the DL model's output is the fluence maps of IMRT plans. However, from the clinical planning perspective, the plan quality evaluation should be based on the clinical dosimetric criteria such as dose-volume histograms. To account for the complex and non-intuitive relationships between fluence map prediction errors and the corresponding dose distribution changes, we propose a novel error analysis approach that systematically examines plan dosimetric changes that are induced by varying amounts of fluence prediction errors. We investigated four decomposition modes of model prediction errors. The two spatial domain decompositions are based on fluence intensity and fluence gradient. The two frequency domain decompositions are based on Fourier-space banded frequency rings and Fourier-space truncated low-frequency disks. The decomposed error was analyzed for its impact on the resulting plans' dosimetric metrics. The analysis was conducted on 15 test cases spared from the 200 training and 16 validation cases used to train the model.Results.Most planning target volume metrics were significantly correlated with most error decompositions. The Fourier space disk radii had the largest Spearman's coefficients. The low-frequency region within a disk of ∼20% Fourier space contained most of errors that impact overall plan quality.Conclusions.This study demonstrates the feasibility of using fluence map prediction error analysis to understand the AI agent's performance. Such insights will help fine-tune the DL models in architecture design and loss function selection.

Transcript expression profiling of fibromelanosis-related genes in black-bone chickens

1. The aim of the present study was to identify differentially expressed genes (DEGs) and metabolic pathways involved in this phenotype. Fibromelanosis is the most striking feature of black-bone chickens, such as the Silkie and Dongxiang indigenous breeds. Due to the accumulation of eumelanin in connective tissues, fibromelanosis manifests as black colouration of the skin, muscles, gut, and periosteum. Studies on fibromelanosis can provide useful information pertaining to human diseases and offer commercial value to the poultry industry. However, the genetic basis of fibromelanosis remains unclear.2. Digital gene expression analysis was performed on black and white skin samples collected from the HW1 black-bone chicken line to detect differences in genome-wide expression patterns. A total of >30 billion bp were sequenced, and 2,707,926,466 bp and 2,948,782,964 bp of clean data obtained for creation of libraries for black and white skin, respectively. In total, 252 DEGs from 15,508 mapped genes were identified with 83 up-regulated in white skin and 169 up-regulated in black skin.3. Gene ontology analysis highlighted that genes from the extracellular region and associated components were abundant among the DEGs. Pathway analysis revealed that many DEGs were linked to amino acid metabolism and the immune system. qRT-PCR validation using 14 genes showed good conformity with the sequence analysis of fibromelanosis-related genes.4. The results showed that L-dopachrometautomerase precursor (DCT), tyrosine aminotransferase (TAT), 4-hydroxyphenylpyruvate dioxygenase (HPD) from the tyrosine metabolism pathway, coagulation factor II (F2), fibrinogen beta chain (FGB), plasminogen (PLG) and complement component 7 (C7) from the complement and coagulation cascades were important genes in the fibromelanosis process in black-bone chickens. These candidate genes require further correlation analysis and functional verification.

Plasma miR-146a and miR-365 expression and inflammatory factors in patients with osteoarthritis

OBJECTIVE

To investigate the expression levels of micro-ribonucleic acid (miR)-146a and miR-365 in the plasma of osteoarthritis (OA) patients, to study their expression with the inflammatory factors and the severity of disease in patients and to analyse their diagnostic significance.

MATERIALS AND METHODS

A total of 42 OA patients diagnosed with OA and treated in our hospital from January 2017 to January 2018 were selected as the subjects, and 28 healthy people were enrolled as controls. The expressions of interleukin-1 beta (IL-1β) and IL-6 in the plasma of OA patients were detected via immunohistochemical staining. Moreover, the knee joint function of OA patients was evaluated by Lysholm score, Western Ontario and McMaster Universities (WOMAC) score and Visual Analogue Scale (VAS) score. The expression levels of plasma miR-146a and miR-365 in OA patients were measured through RT-PCR. Besides, the significance of the expression levels of miR-146a and miR-365 for the diagnosis of OA was analysed by ROC curves.

RESULTS

As compared with healthy people, OA patients had elevated expression levels of plasma IL-1β and IL-6, decreased Lysholm score, increased WOMAC and VAS scores as well as significantly up-regulated levels of plasma miR-146a and miR-365, which were of important significance for diagnosis.

CONCLUSION

The expression levels of plasma miR-146a, miR-365 and inflammatory factors are notably higher, the disease is more severe, and the function of knee joint movement is weaker in OA patients than those in healthy controls. It can be concluded that the levels of both miR-146a and miR-365 can serve as biomarkers of OA diagnosis.

Factors associated with Scrub Typhus infection: A case-control study from Luhe, China

INTRODUCTION

Scrub typhus (ST) is an acute febrile infection and remains a significant health problem globally. This study aimed to determine the factors associated with ST infection in Luhe District, China.

MATERIAL AND METHODS

The case-control study was conducted among 116 cases identified through passive surveillance systems over three years.The control subjects were 232 living in the same village for more than six months without any history of ST infection were selected by matching to the age (within 5-years) and identified through active surveillance. Statistical analyses were performed using SPSS v. 25.0 for Windows (IBM SPSS, Chicago, IL, USA).

RESULTS

The mean age of confirmed persons was 58.1(SD=10.15) years, while control subjects were 56.14 (11.57).There is no significant difference in gender, age, education, and occupations between case and control. Farmers had the most significant number of cases among occupational groups. The three factors that were significantly associated with an increased odds of having ST infection are bundling or moving waste straw (OR: 1.94, 95%CI; 0.99,381), morning exercise in the park or field (OR: 4.74 95%CI; 1.19, 18.95), and working as labourer in the vegetable field (OR:1.02, 95%CI:1.02,3.19).

CONCLUSIONS

Our findings suggested establishing a prevention and control strategy for these groups to lower ST development risk.

[Contrasting Misinformation and Real-Information Dissemination Network Structures on Social Media During a Health Emergency]

Objetivos.

Elaborar un esquema operativo integral para detectar la información errónea principal sobre el zika distribuida en Twitter® en el 2016; reconstruir las redes por las que se difunde información mediante retuiteo; contrastar la información verídica frente a la errónea con diversos parámetros; e investigar cómo se difundió en las redes sociales la información errónea sobre el zika durante la epidemia.

Métodos.

Revisamos sistemáticamente los 5 000 tuits más retuiteados con información sobre el zika en inglés, definimos “información errónea” a partir de la evidencia, buscamos tuits que tuvieran información errónea y conformamos un grupo equiparable de tuits con información verídica. Elaboramos un algoritmo para reconstruir las redes de retuiteo de 266 tuits con información errónea y 458 tuits equiparables con información verídica. Calculamos y comparamos nueve parámetros para caracterizar la estructura de las redes a varios niveles, entre los dos grupos.

Resultados.

En los nueve parámetros se aprecian diferencias estadísticamente significativas entre el grupo de información verídica y el de información errónea. La información errónea en general se difunde mediante estructuras más sofisticadas que la información verídica. También hay una considerable variabilidad intragrupal.

Conclusiones.

Las redes de difusión de la información errónea sobre el zika en Twitter fueron sustancialmente diferentes que las de información verídica, lo cual indica que la información errónea se sirve de mecanismos de difusión distintos. Nuestro estudio permitirá formar una comprensión más holística de los desafíos que plantea la información errónea sobre salud en las redes sociales.

Both intermuscular fat and LVEF decline promote heart failure symptoms in cancer survivors

Background

Approximately 20% of cancer survivors treated with chemotherapy experience worsening heart failure (HF) symptoms post-cancer treatment. While research has predominantly investigated the role of cardiotoxic treatments, much less attention has focused on other risk factors, such as adiposity. However, emerging data in cancer survivors indicates that adiposity may also impact a variety of cardiovascular outcomes. Methods: In a prospective study of 62 patients diagnosed with cancer followed for 24 months from cancer diagnosis through to survivorship (post-cancer treatment), we ascertained baseline fat depots including intermuscular fat (IMF) of the erector spinae muscles; and pre- and post-cancer treatment left ventricular ejection fraction (LVEF) and HF symptoms at baseline and 24-months, respectively. Linear regression was used to model independent variables in relation to HF symptoms at 24-months.

Results

Baseline IMF and LVEF change over 24-months significantly interacted to predict HF score at 24-months. The highest HF symptom score was observed for participants who experienced high IMF at baseline and a high decline in LVEF over 24-months (HF score = 11.0) versus all other categories of baseline IMF and LVEF change.

Conclusions

Together IMF and LVEF decline may play an important role in the worsening of HF symptoms in cancer survivors. The finding that IMF at cancer diagnosis led to elevated HF scores post-treatment suggests that IMF may be a potential target for intervention studies.

An artificial intelligence-driven agent for real-time head-and-neck IMRT plan generation using conditional generative adversarial network (cGAN)

PURPOSE

To develop an artificial intelligence (AI) agent for fully automated rapid head-and-neck intensity-modulated radiation therapy (IMRT) plan generation without time-consuming dose-volume-based inverse planning.

METHODS

This AI agent was trained via implementing a conditional generative adversarial network (cGAN) architecture. The generator, PyraNet, is a novel deep learning network that implements 28 classic ResNet blocks in pyramid-like concatenations. The discriminator is a customized four-layer DenseNet. The AI agent first generates multiple customized two-dimensional projections at nine template beam angles from a patient's three-dimensional computed tomography (CT) volume and structures. These projections are then stacked as four-dimensional inputs of PyraNet, from which nine radiation fluence maps of the corresponding template beam angles are generated simultaneously. Finally, the predicted fluence maps are automatically postprocessed by Gaussian deconvolution operations and imported into a commercial treatment planning system (TPS) for plan integrity check and visualization. The AI agent was built and tested upon 231 oropharyngeal IMRT plans from a TPS plan library. 200/16/15 plans were assigned for training/validation/testing, respectively. Only the primary plans in the sequential boost regime were studied. All plans were normalized to 44 Gy prescription (2 Gy/fx). A customized Harr wavelet loss was adopted for fluence map comparison during the training of the PyraNet. For test cases, isodose distributions in AI plans and TPS plans were qualitatively evaluated for overall dose distributions. Key dosimetric metrics were compared by Wilcoxon signed-rank tests with a significance level of 0.05.

RESULTS

All 15 AI plans were successfully generated. Isodose gradients outside of PTV in AI plans were comparable to those of the TPS plans. After PTV coverage normalization, D_mean of left parotid (D_AI  = 23.1 ± 2.4 Gy; D_TPS  = 23.1 ± 2.0 Gy), right parotid (D_AI  = 23.8 ± 3.0 Gy; D_TPS  = 23.9 ± 2.3 Gy), and oral cavity (D_AI  = 24.7 ± 6.0 Gy; D_TPS  = 23.9 ± 4.3 Gy) in the AI plans and the TPS plans were comparable without statistical significance. AI plans achieved comparable results for maximum dose at 0.01cc of brainstem (D_AI  = 15.0 ± 2.1 Gy; D_TPS  = 15.5 ± 2.7 Gy) and cord + 5mm (D_AI  = 27.5 ± 2.3 Gy; D_TPS  = 25.8 ± 1.9 Gy) without clinically relevant differences, but body D_max results (D_AI  = 121.1 ± 3.9 Gy; D_TPS  = 109.0 ± 0.9 Gy) were higher than the TPS plan results. The AI agent needed ~3 s for predicting fluence maps of an IMRT plan.

CONCLUSIONS

With rapid and fully automated execution, the developed AI agent can generate complex head-and-neck IMRT plans with acceptable dosimetry quality. This approach holds great potential for clinical applications in preplanning decision-making and real-time planning.

A Multimodality Machine Learning Approach to Differentiate Severe and Nonsevere COVID-19: Model Development and Validation

BACKGROUND

Effectively and efficiently diagnosing patients who have COVID-19 with the accurate clinical type of the disease is essential to achieve optimal outcomes for the patients as well as to reduce the risk of overloading the health care system. Currently, severe and nonsevere COVID-19 types are differentiated by only a few features, which do not comprehensively characterize the complicated pathological, physiological, and immunological responses to SARS-CoV-2 infection in the different disease types. In addition, these type-defining features may not be readily testable at the time of diagnosis.

OBJECTIVE

In this study, we aimed to use a machine learning approach to understand COVID-19 more comprehensively, accurately differentiate severe and nonsevere COVID-19 clinical types based on multiple medical features, and provide reliable predictions of the clinical type of the disease.

METHODS

For this study, we recruited 214 confirmed patients with nonsevere COVID-19 and 148 patients with severe COVID-19. The clinical characteristics (26 features) and laboratory test results (26 features) upon admission were acquired as two input modalities. Exploratory analyses demonstrated that these features differed substantially between two clinical types. Machine learning random forest models based on all the features in each modality as well as on the top 5 features in each modality combined were developed and validated to differentiate COVID-19 clinical types.

RESULTS

Using clinical and laboratory results independently as input, the random forest models achieved >90% and >95% predictive accuracy, respectively. The importance scores of the input features were further evaluated, and the top 5 features from each modality were identified (age, hypertension, cardiovascular disease, gender, and diabetes for the clinical features modality, and dimerized plasmin fragment D, high sensitivity troponin I, absolute neutrophil count, interleukin 6, and lactate dehydrogenase for the laboratory testing modality, in descending order). Using these top 10 multimodal features as the only input instead of all 52 features combined, the random forest model was able to achieve 97% predictive accuracy.

CONCLUSIONS

Our findings shed light on how the human body reacts to SARS-CoV-2 infection as a unit and provide insights on effectively evaluating the disease severity of patients with COVID-19 based on more common medical features when gold standard features are not available. We suggest that clinical information can be used as an initial screening tool for self-evaluation and triage, while laboratory test results should be applied when accuracy is the priority.

Knowledge Models as Teaching Aid for Training Intensity Modulated Radiation Therapy Planning: A Lung Cancer Case Study

Purpose: Artificial intelligence (AI) employs knowledge models that often behave as a black-box to the majority of users and are not designed to improve the skill level of users. In this study, we aim to demonstrate the feasibility that AI can serve as an effective teaching aid to train individuals to develop optimal intensity modulated radiation therapy (IMRT) plans.

Methods and Materials: The training program is composed of a host of training cases and a tutoring system that consists of a front-end visualization module powered by knowledge models and a scoring system. The current tutoring system includes a beam angle prediction model and a dose-volume histogram (DVH) prediction model. The scoring system consists of physician chosen criteria for clinical plan evaluation as well as specially designed criteria for learning guidance. The training program includes six lung/mediastinum IMRT patients: one benchmark case and five training cases. A plan for the benchmark case is completed by each trainee entirely independently pre- and post-training. Five training cases cover a wide spectrum of complexity from easy (2), intermediate (1) to hard (2). Five trainees completed the training program with the help of one trainer. Plans designed by the trainees were evaluated by both the scoring system and a radiation oncologist to quantify planning quality.

Results: For the benchmark case, trainees scored an average of 21.6% of the total max points pre-training and improved to an average of 51.8% post-training. In comparison, the benchmark case's clinical plans score an average of 54.1% of the total max points. Two of the five trainees' post-training plans on the benchmark case were rated as comparable to the clinically delivered plans by the physician and all five were noticeably improved by the physician's standards. The total training time for each trainee ranged between 9 and 12 h.

Conclusion: This first attempt at a knowledge model based training program brought unexperienced planners to a level close to experienced planners in fewer than 2 days. The proposed tutoring system can serve as an important component in an AI ecosystem that will enable clinical practitioners to effectively and confidently use KBP.

[The 485th case: fever of undetermined origin and hypoxemia]

A 49-year-old male was admitted to Peking Union Medical College Hospital presented with fever for more than half a year. The patient was diagnosed as Sjogren's syndrome at local hospital. After oral prednisone 60 mg per day was given, the fever alleviated, but recurred after prednisone tapered to 40 mg/d. Both blood culture and stool culture were positive for Salmonella enteritidis. Antibiotics including ceftazidime, ceftriaxone, cilastatin-imipenem were sequentially administrated for 4 weeks, yet not effective. Although there were not respiratory symptoms or certain abnormalities on high-resolution chest CT, arterial blood gas indicated hypoxemia. Serum lactate dehydrogenase and β2 micro-globulin were elevated, and the lung function test demonstrated significant impairment of diffusion function. Positron emission tomography-computed tomography (PET/CT)scan suggested that high fluorodeoxyglucose uptake was diffusely seen in both lungs. The patient was finally diagnosed as pulmonary intravascular large B-cell lymphoma (IVLBCL) by transbronchial lung biopsy. This case aims to emphasize the differentiation diagnoses of pulmonary intravascular lymphoma from common situations.

[Consistency of effective orifice area of prosthetic mitral valve estimated using 2-dimensional and 3-dimensional transesophageal echocardiography]

OBJECTIVE

To analyze the consistency of effective orifice area (EOA) of prosthetic mitral valve estimated using 2- dimensional (2D) and 3-dimensional (3D) transesophageal echocardiography (TEE).

OBJECTIVE

This study was conducted among 34 patients undergoing mitral valve replacement surgery in Nanjing First Hospital between March and June in 2019. The diameter of the left ventricular outflow tract (LVOT) measured by 2D-TEE was used to calculate the cross sectional area of LVOT (CSALVOT). In 3D-TEE method, LVOT area was measured directly by planimetry on an enface view. The EOAs of the prosthetic mitral valve were calculated for both methods using the continuity equation. Bland-Altman plot consistency test was used to analyze the consistency between the two sets of EOA results, and linear regression analysis was used to analyze their correlation.

OBJECTIVE

The EOA of the prosthetic mitral valve differed significantly between 2D method and 3D method (2.22±0.71 cm² vs 2.35±0.70 cm², P < 0.001) with a mean difference of -0.14±0.20 cm² and 95% coherence boundaries of (-0.53, 0.25 cm²). The regression equation for EOA-3D and EOA-2D is y=0.27 + 0.94x, showing a good correlation between the two methods.

OBJECTIVE

EOA estimation of the prosthetic mitral valve using 2D and 3D TEE has a good consistency, and the results estimated by the 2D method are slightly lower by about 6% than those by the 3D method.

Deep Learning-Based Fluence Map Prediction for Pancreas Stereotactic Body Radiation Therapy With Simultaneous Integrated Boost

Purpose

Treatment planning for pancreas stereotactic body radiation therapy (SBRT) is a challenging task, especially with simultaneous integrated boost treatment approaches. We propose a deep learning (DL) framework to accurately predict fluence maps from patient anatomy and directly generate intensity modulated radiation therapy plans.

Methods and Materials

The framework employs 2 convolutional neural networks (CNNs) to sequentially generate beam dose prediction and fluence map prediction, creating a deliverable 9-beam intensity modulated radiation therapy plan. Within the beam dose prediction CNN, axial slices of combined structure contour masks are used to predict 3-dimensional (3D) beam doses for each beam. Each 3D beam dose is projected along its beam’s-eye-view to form a 2D beam dose map, which is subsequently used by the fluence map prediction CNN to predict its fluence map. Finally, the 9 predicted fluence maps are imported into the treatment planning system to finalize the plan by leaf sequencing and dose calculation. One hundred patients receiving pancreas SBRT were retrospectively collected for this study. Benchmark plans with unified simultaneous integrated boost prescription (25/33 Gy) were manually optimized for each case. The data set was split into 80/20 cases for training and testing. We evaluated the proposed DL framework by assessing both the fluence maps and the final predicted plans. Further, clinical acceptability of the plans was evaluated by a physician specializing in gastrointestinal cancer.

Results

The DL-based planning was, on average, completed in under 2 minutes. In testing, the predicted plans achieved similar dose distribution compared with the benchmark plans (-1.5% deviation for planning target volume 33 V_33Gy), with slightly higher planning target volume maximum (+1.03 Gy) and organ at risk maximum (+0.95 Gy) doses. After renormalization, the physician rated 19 cases clinically acceptable and 1 case requiring minor improvement.

Conclusions

The DL framework can effectively plan pancreas SBRT cases within 2 minutes. The predicted plans are clinically deliverable, with plan quality approaching that of manual planning.

Autoimmune experimental orchitis and chronic glomerulonephritis with end stage renal disease are controlled by Cgnz1 for susceptibility to end organ damage

Cgnz1 on chromosome 1 mapped into a 1.34 Mb region of chromosome 1 in NZM2328 confers the progression of immune complex (IC)-mediated glomerulonephritis (GN) from acute GN (aGN) to chronic GN (cGN) with severe proteinuria and end stage renal disease in female mice. This genetic locus mediates podocyte susceptibility to IC-mediated damage. Taking advantage of the published observation that Cgnz1 is derived from NZW and that NZW is susceptible to orchitis, epididymitis and vasitis while C57L/J is resistant to these diseases, the possibility that this genetic region also confers germ cells susceptible to damage with aspermatogenesis and sterility in an active experimental autoimmune orchitis (EAO) model was investigated. Male mice from multiple intrachromosome (chromosome 1) recombinant strains were subjected to immunization with a sperm homogenate in CFA with concomitant administration of Bordetella pertussis toxin. There was concordance of the progression from aGN to cGN, severe proteinuria and end stage renal disease with susceptibility of EAO in NZM2328 and its congenic strains with various chromosome 1 genetic intervals introgressed from C57L/J to NZM2328. Both resistant and susceptible strains made comparable anti-testis and anti-sperm Abs. Thus the genetic interval that determines susceptibility to EAO is identical to that of Cgnz1 and mapped to the 1.34 Mb region in chromosone 1. This region likely confers germ cells in the male gonad susceptible to damage by immunologically mediated inflammation. This region has been tentatively renamed Cgnz1/Eaoz1. These observations further emphasize the importance of end organ susceptibility to damage in the pathogenesis of both systemic and organ specific autoimmune diseases.

Accurately Differentiating Between Patients With COVID-19, Patients With Other Viral Infections, and Healthy Individuals: Multimodal Late Fusion Learning Approach

BACKGROUND

Effectively identifying patients with COVID-19 using nonpolymerase chain reaction biomedical data is critical for achieving optimal clinical outcomes. Currently, there is a lack of comprehensive understanding in various biomedical features and appropriate analytical approaches for enabling the early detection and effective diagnosis of patients with COVID-19.

OBJECTIVE

We aimed to combine low-dimensional clinical and lab testing data, as well as high-dimensional computed tomography (CT) imaging data, to accurately differentiate between healthy individuals, patients with COVID-19, and patients with non-COVID viral pneumonia, especially at the early stage of infection.

METHODS

In this study, we recruited 214 patients with nonsevere COVID-19, 148 patients with severe COVID-19, 198 noninfected healthy participants, and 129 patients with non-COVID viral pneumonia. The participants' clinical information (ie, 23 features), lab testing results (ie, 10 features), and CT scans upon admission were acquired and used as 3 input feature modalities. To enable the late fusion of multimodal features, we constructed a deep learning model to extract a 10-feature high-level representation of CT scans. We then developed 3 machine learning models (ie, k-nearest neighbor, random forest, and support vector machine models) based on the combined 43 features from all 3 modalities to differentiate between the following 4 classes: nonsevere, severe, healthy, and viral pneumonia.

RESULTS

Multimodal features provided substantial performance gain from the use of any single feature modality. All 3 machine learning models had high overall prediction accuracy (95.4%-97.7%) and high class-specific prediction accuracy (90.6%-99.9%).

CONCLUSIONS

Compared to the existing binary classification benchmarks that are often focused on single-feature modality, this study's hybrid deep learning-machine learning framework provided a novel and effective breakthrough for clinical applications. Our findings, which come from a relatively large sample size, and analytical workflow will supplement and assist with clinical decision support for current COVID-19 diagnostic methods and other clinical applications with high-dimensional multimodal biomedical features.

A Novel Machine Learning Framework for Comparison of Viral COVID-19-Related Sina Weibo and Twitter Posts: Workflow Development and Content Analysis

Background

Social media plays a critical role in health communications, especially during global health emergencies such as the current COVID-19 pandemic. However, there is a lack of a universal analytical framework to extract, quantify, and compare content features in public discourse of emerging health issues on different social media platforms across a broad sociocultural spectrum.

Objective

We aimed to develop a novel and universal content feature extraction and analytical framework and contrast how content features differ with sociocultural background in discussions of the emerging COVID-19 global health crisis on major social media platforms.

Methods

We sampled the 1000 most shared viral Twitter and Sina Weibo posts regarding COVID-19, developed a comprehensive coding scheme to identify 77 potential features across six major categories (eg, clinical and epidemiological, countermeasures, politics and policy, responses), quantified feature values (0 or 1, indicating whether or not the content feature is mentioned in the post) in each viral post across social media platforms, and performed subsequent comparative analyses. Machine learning dimension reduction and clustering analysis were then applied to harness the power of social media data and provide more unbiased characterization of web-based health communications.

Results

There were substantially different distributions, prevalence, and associations of content features in public discourse about the COVID-19 pandemic on the two social media platforms. Weibo users were more likely to focus on the disease itself and health aspects, while Twitter users engaged more about policy, politics, and other societal issues.

Conclusions

We extracted a rich set of content features from social media data to accurately characterize public discourse related to COVID-19 in different sociocultural backgrounds. In addition, this universal framework can be adopted to analyze social media discussions of other emerging health issues beyond the COVID-19 pandemic.