Hunting imaging biomarkers in pulmonary fibrosis: Benchmarks of the AIIB23 challenge (preprint)

Airway-related quantitative imaging biomarkers are crucial for examination, diagnosis, and prognosis in pulmonary diseases. However, the manual delineation of airway trees remains prohibitively time-consuming. While significant efforts have been made towards enhancing airway modelling, current public-available datasets concentrate on lung diseases with moderate morphological variations. The intricate honeycombing patterns present in the lung tissues of fibrotic lung disease patients exacerbate the challenges, often leading to various prediction errors. To address this issue, the 'Airway-Informed Quantitative CT Imaging Biomarker for Fibrotic Lung Disease 2023' (AIIB23) competition was organized in conjunction with the official 2023 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). The airway structures were meticulously annotated by three experienced radiologists. Competitors were encouraged to develop automatic airway segmentation models with high robustness and generalization abilities, followed by exploring the most correlated QIB of mortality prediction. A training set of 120 high-resolution computerised tomography (HRCT) scans were publicly released with expert annotations and mortality status. The online validation set incorporated 52 HRCT scans from patients with fibrotic lung disease and the offline test set included 140 cases from fibrosis and COVID-19 patients. The results have shown that the capacity of extracting airway trees from patients with fibrotic lung disease could be enhanced by introducing voxel-wise weighted general union loss and continuity loss. In addition to the competitive image biomarkers for prognosis, a strong airway-derived biomarker (Hazard ratio>1.5, p<0.0001) was revealed for survival prognostication compared with existing clinical measurements, clinician assessment and AI-based biomarkers.

Multi-site, Multi-domain Airway Tree Modeling (ATM'22): A Public Benchmark for Pulmonary Airway Segmentation (preprint)

Open international challenges are becoming the de facto standard for assessing computer vision and image analysis algorithms. In recent years, new methods have extended the reach of pulmonary airway segmentation that is closer to the limit of image resolution. Since EXACT'09 pulmonary airway segmentation, limited effort has been directed to quantitative comparison of newly emerged algorithms driven by the maturity of deep learning based approaches and clinical drive for resolving finer details of distal airways for early intervention of pulmonary diseases. Thus far, public annotated datasets are extremely limited, hindering the development of data-driven methods and detailed performance evaluation of new algorithms. To provide a benchmark for the medical imaging community, we organized the Multi-site, Multi-domain Airway Tree Modeling (ATM'22), which was held as an official challenge event during the MICCAI 2022 conference. ATM'22 provides large-scale CT scans with detailed pulmonary airway annotation, including 500 CT scans (300 for training, 50 for validation, and 150 for testing). The dataset was collected from different sites and it further included a portion of noisy COVID-19 CTs with ground-glass opacity and consolidation. Twenty-three teams participated in the entire phase of the challenge and the algorithms for the top ten teams are reviewed in this paper. Quantitative and qualitative results revealed that deep learning models embedded with the topological continuity enhancement achieved superior performance in general. ATM'22 challenge holds as an open-call design, the training data and the gold standard evaluation are available upon successful registration via its homepage.

A Comprehensive Benchmark for COVID-19 Predictive Modeling Using Electronic Health Records in Intensive Care (preprint)

The COVID-19 pandemic has posed a heavy burden to the healthcare system worldwide and caused huge social disruption and economic loss. Many deep learning models have been proposed to conduct clinical predictive tasks such as mortality prediction for COVID-19 patients in intensive care units using Electronic Health Record (EHR) data. Despite their initial success in certain clinical applications, there is currently a lack of benchmarking results to achieve a fair comparison so that we can select the optimal model for clinical use. Furthermore, there is a discrepancy between the formulation of traditional prediction tasks and real-world clinical practice in intensive care. To fill these gaps, we propose two clinical prediction tasks, Outcome-specific length-of-stay prediction and Early mortality prediction for COVID-19 patients in intensive care units. The two tasks are adapted from the naive length-of-stay and mortality prediction tasks to accommodate the clinical practice for COVID-19 patients. We propose fair, detailed, open-source data-preprocessing pipelines and evaluate 17 state-of-the-art predictive models on two tasks, including 5 machine learning models, 6 basic deep learning models and 6 deep learning predictive models specifically designed for EHR data. We provide benchmarking results using data from two real-world COVID-19 EHR datasets. One dataset is publicly available without needing any inquiry and another dataset can be accessed on request. We provide fair, reproducible benchmarking results for two tasks. We deploy all experiment results and models on an online platform. We also allow clinicians and researchers to upload their data to the platform and get quick prediction results using our trained models. We hope our efforts can further facilitate deep learning and machine learning research for COVID-19 predictive modeling.

Smartphone Ownership, Digital Literacy, and the Mediating Role of Connectedness and Loneliness In Improving The Wellbeing among Community-Dwelling Singaporean Older Adults of Low Socio-Economic Status (preprint)

Importance: Safe-distancing measures used during the COVID-19 pandemic may exacerbate social isolation and loneliness with their attending negative consequences. Digital technology may mitigate the negative impact of safe-distancing measures; however, older adults of low socioeconomic status (SES) who may not be digitally literate remain a vulnerable population. Objective: To examine the relationship between digital literacy and social connectedness, loneliness, wellbeing, and quality of life (QOL) amongst older adults. To identify demographic factors associated with smartphone ownership, digital literacy, and willingness to enroll in a home-based digital literacy program. Design: Cross-sectional study. Setting: Convenience sampling of older adults receiving financial aid or living in rental flat referred to a volunteer-led digital literacy program.Participants: 302 community dwelling older adults who are ≥55 years old. Main Outcomes: Smartphone ownership, self-reported digital literacy, willingness to enroll in a digital literacy program; social connectedness (Lubben Social Connectedness Scale, LSNS-6), loneliness (UCLA 3-item scale, UCLA-3), wellbeing (Personal Wellbeing Score), and QOL (EQ-5D-3L [utility index], EQ VAS). Results: Social digital literacy had a positive indirect effect on both the wellbeing and QOL (mediated by social connectedness and perceived loneliness) of older adults, while instrumental digital literacy had a negative indirect effect on the two outcomes. 59.9% of participants owned an internet-enabled phone (smartphone). The median digital literacy index is 3 (score ranging from 0 to 13). Older adults who are younger and more educated were more likely to own a smartphone; while older adults who are more educated, Chinese (ethnic majority), have a smartphone, and lower digital literacy index were more likely to enroll in a home-based digital literacy education program.Conclusions and Relevance: During the COVID-19 pandemic, community dwelling older adults of low SES are socially isolated, lonely, and have low digital literacy. Interventions to improve digital literacy (especially the social domain) may help to reduce social isolation and loneliness, ultimately improving wellbeing and QOL.

CovidCare: Transferring Knowledge from Existing EMR to Emerging Epidemic for Interpretable Prognosis (preprint)

Due to the characteristics of COVID-19, the epidemic develops rapidly and overwhelms health service systems worldwide. Many patients suffer from systemic life-threatening problems and need to be carefully monitored in ICUs. Thus the intelligent prognosis is in an urgent need to assist physicians to take an early intervention, prevent the adverse outcome, and optimize the medical resource allocation. However, in the early stage of the epidemic outbreak, the data available for analysis is limited due to the lack of effective diagnostic mechanisms, rarity of the cases, and privacy concerns. In this paper, we propose a deep-learning-based approach, CovidCare, which leverages the existing electronic medical records to enhance the prognosis for inpatients with emerging infectious diseases. It learns to embed the COVID-19-related medical features based on massive existing EMR data via transfer learning. The transferred parameters are further trained to imitate the teacher model's representation behavior based on knowledge distillation, which embeds the health status more comprehensively in the source dataset. We conduct the length of stay prediction experiments for patients on a real-world COVID-19 dataset. The experiment results indicate that our proposed model consistently outperforms the comparative baseline methods. CovidCare also reveals that, 1) hs-cTnI, hs-CRP and Platelet Counts are the most fatal biomarkers, whose abnormal values usually indicate emergency adverse outcome. 2) Normal values of gamma-GT, AP and eGFR indicate the overall improvement of health. The medical findings extracted by CovidCare are empirically confirmed by human experts and medical literatures.

Disrupted Rhythms of Life, Work and Entertainment Behaviours and Their Associations with Mental Health Problems under the Stress of COVID-19 Epidemic: A Survey in 5854 Chinese People with Different Backgrounds (preprint)

BACKGROUND and OBJECTIVE The rhythms of life, work and entertainment behaviours are considered as the external behavioural manifestations of biological rhythm.To evaluate the distinctive disrupted rhythms of behaviours and their associations with mental health problems in people with different backgrounds under the stress of COVID-19 epidemic.SUBJECTS AND METHODS A cross-sectional study was conducted from 10-17 March 2020 under the stress of COVID-19 epidemic.A structured e-questionnaire containing general information,rhythm scale(subscale1 for life-work rhythms and subscale2 for entertainment rhythm) and Zung's self-rating depression and anxiety scale(SDS and SAS) were filled and the data were analysed.RESULTS Overall 5854 participants were included.Significant differences were found in rhythm, SDS and SAS scores among people with different backgrounds (all P<0.05). Subjects with female gender and poor health status were mostly suffered from disrupted rhythms of life- work-entertainment behaviours, combined with depression and anxiety. Nurses and subjects being divorced or with chronic disease with psychosomatic diseases were mostly suffered from disrupted rhythms of life-work behaviours, combined with depression and anxiety. Subjects with aged 26-30 years, or annual income of 50,000-100,000CY were mostly suffered from disrupted rhythms of life-work combined with depression. Subjects with income over 300,000CY were mostly suffered from disrupted rhythm of entertainment combined with anxiety.The prevalence rates of depression and anxiety in people with the high-scores of rhythm disruption increased by 34.50% and 47.16%, respectively, compared with those with low-scores.People with the high-scores of rhythm disruption had higher SDS and SAS scores, compared to those with low scores (all P<0.001). The independent related factors of disrupted rhythms included gender,age,marital status, health status,annual income and chronic diseases with psychosomatic diseases using logistic regression.The disrupted rhythms of life and work behaviours was positively correlated with both SDS and SAS scores.CONCLUSIONS The disrupted rhythms of life, work and entertainment behaviours were closely associated with mental health problems.The disrupted rhythms of behaviours are frequent and fluxible,triggering more severe mental health problems under the stress of COVID-19 epidemic.The physicians should be aware of their importance when evaluating their interviewees or patients’ mental health and achieving maximization of therapeutic efficacy by integrating the intervention of circadian rhythm and its behaviour.

Cloning, Prokaryotic Soluble Expression, and Analysis of Antiviral Activity of Two Novel Feline IFN-ω Proteins

Cats are becoming more popular as household companions and pets, forming close relationships with humans. Although feline viral diseases can pose serious health hazards to pet cats, commercialized preventative vaccines are lacking. Interferons (IFNs), especially type I IFNs (IFN-α, IFN-ß, and interferon omega (IFN-ω)), have been explored as effective therapeutic drugs against viral diseases in cats. Nevertheless, there is limited knowledge regarding feline IFN-ω (feIFN-ω), compared to IFN-α and IFN-ß. In this study, we cloned the genes encoding feIFN-ωa and feIFN-ωb from cat spleen lymphocytes. Homology and phylogenetic tree analysis revealed that these two genes belonged to new subtypes of feIFN-ω. The recombinant feIFN-ωa and feIFN-ωb proteins were expressed in their soluble forms in Escherichia coli, followed by purification. Both proteins exhibited effective anti-vesicular stomatitis virus (VSV) activity in Vero, F81 (feline kidney cell), Madin-Darby bovine kidney (MDBK), Madin-Darby canine kidney (MDCK), and porcine kidney (PK-15) cells, showing broader cross-species antiviral activity than the INTERCAT IFN antiviral drug. Furthermore, the recombinant feIFN-ωa and feIFN-ωb proteins demonstrated antiviral activity against VSV, feline coronavirus (FCoV), canine parvovirus (CPV), bovine viral diarrhea virus (BVDV), and porcine epidemic diarrhea virus (PEDV), indicating better broad-spectrum antiviral activity than the INTERCAT IFN. The two novel feIFN-ω proteins (feIFN-ωa and feIFN-ωb) described in this study show promising potential to serve as effective therapeutic agents for treating viral infections in pet cats.