Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Assessing the Severity of Health States based on Social Media Posts

ArXiv Preprint

The unprecedented growth of Internet users has resulted in an abundance of unstructured information on social media including health forums, where patients request health-related information or opinions from other users. Previous studies have shown that online peer support has limited effectiveness without expert intervention. Therefore, a system capable of assessing the severity of health state from the patients' social media posts can help health professionals (HP) in prioritizing the user's post. In this study, we inspect the efficacy of different aspects of Natural Language Understanding (NLU) to identify the severity of the user's health state in relation to two perspectives(tasks) (a) Medical Condition (i.e., Recover, Exist, Deteriorate, Other) and (b) Medication (i.e., Effective, Ineffective, Serious Adverse Effect, Other) in online health communities. We propose a multiview learning framework that models both the textual content as well as contextual-information to assess the severity of the user's health state. Specifically, our model utilizes the NLU views such as sentiment, emotions, personality, and use of figurative language to extract the contextual information. The diverse NLU views demonstrate its effectiveness on both the tasks and as well as on the individual disease to assess a user's health.

Shweta Yadav, Joy Prakash Sain, Amit Sheth, Asif Ekbal, Sriparna Saha, Pushpak Bhattacharyya

2020-09-21

General General

Impact of lung segmentation on the diagnosis and explanation of COVID-19 in chest X-ray images

ArXiv Preprint

The COVID-19 pandemic is undoubtedly one of the biggest public health crises our society has ever faced. This paper's main objectives are to demonstrate the impact of lung segmentation in COVID-19 automatic identification using CXR images and evaluate which contents of the image decisively contribute to the identification. We have performed lung segmentation using a U-Net CNN architecture, and the classification using three well-known CNN architectures: VGG, ResNet, and Inception. To estimate the impact of lung segmentation, we applied some Explainable Artificial Intelligence (XAI), such as LIME and Grad-CAM. To evaluate our approach, we built a database named RYDLS-20-v2, following our previous publication and the COVIDx database guidelines. We evaluated the impact of creating a COVID-19 CXR image database from different sources, called database bias, and the COVID-19 generalization from one database to another, representing our less biased scenario. The experimental results of the segmentation achieved a Jaccard distance of 0.034 and a Dice coefficient of 0.982. In the best and more realistic scenario, we achieved an F1-Score of 0.74 and an area under the ROC curve of 0.9 for COVID-19 identification using segmented CXR images. Further testing and XAI techniques suggest that segmented CXR images represent a much more realistic and less biased performance. More importantly, the experiments conducted show that even after segmentation, there is a strong bias introduced by underlying factors from the data sources, and more efforts regarding the creation of a more significant and comprehensive database still need to be done.

Lucas O. Teixeira, Rodolfo M. Pereira, Diego Bertolini, Luiz S. Oliveira, Loris Nanni, Yandre M. G. Costa

2020-09-21

General General

Changing the Nature of Quantitative Biology Education: Data Science as a Driver.

In Bulletin of mathematical biology

We live in a data-rich world with rapidly growing databases with zettabytes of data. Innovation, computation, and technological advances have now tremendously accelerated the pace of discovery, providing driverless cars, robotic devices, expert healthcare systems, precision medicine, and automated discovery to mention a few. Even though the definition of the term data science continues to evolve, the sweeping impact it has already produced on society is undeniable. We are at a point when new discoveries through data science have enormous potential to advance progress but also to be used maliciously, with harmful ethical and social consequences. Perhaps nowhere is this more clearly exemplified than in the biological and medical sciences. The confluence of (1) machine learning, (2) mathematical modeling, (3) computation/simulation, and (4) big data have moved us from the sequencing of genomes to gene editing and individualized medicine; yet, unsettled policies regarding data privacy and ethical norms could potentially open doors for serious negative repercussions. The data science revolution has amplified the urgent need for a paradigm shift in undergraduate biology education. It has reaffirmed that data science education interacts and enhances mathematical education in advancing quantitative conceptual and skill development for the new generation of biologists. These connections encourage us to strive to cultivate a broadly skilled workforce of technologically savvy problem-solvers, skilled at handling the unique challenges pertaining to biological data, and capable of collaborating across various disciplines in the sciences, the humanities, and the social sciences. To accomplish this, we suggest development of open curricula that extend beyond the job certification rhetoric and combine data acumen with modeling, experimental, and computational methods through engaging projects, while also providing awareness and deep exploration of their societal implications. This process would benefit from embracing the pedagogy of experiential learning and involve students in open-ended explorations derived from authentic inquiries and ongoing research. On this foundation, we encourage development of flexible data science initiatives for the education of life science undergraduates within and across existing models.

Robeva Raina S, Jungck John R, Gross Louis J

2020-Sep-19

Big data, Data science education, Education reform, Mathematical biology education

General General

Addressing health disparities in the Food and Drug Administration's artificial intelligence and machine learning regulatory framework.

In Journal of the American Medical Informatics Association : JAMIA

The exponential growth of health data from devices, health applications, and electronic health records coupled with the development of data analysis tools such as machine learning offer opportunities to leverage these data to mitigate health disparities. However, these tools have also been shown to exacerbate inequities faced by marginalized groups. Focusing on health disparities should be part of good machine learning practice and regulatory oversight of software as medical devices. Using the Food and Drug Administration (FDA)'s proposed framework for regulating machine learning tools in medicine, I show that addressing health disparities during the premarket and postmarket stages of review can help anticipate and mitigate group harms.

Ferryman Kadija

2020-Sep-20

artificial intelligence, health disparities, health policy, machine learning

General General

Psychological aging, depression, and well-being.

In Aging ; h5-index 49.0

Aging is a multifactorial process, which affects the human body on every level and results in both biological and psychological changes. Multiple studies have demonstrated that a lower subjective age is associated with better mental and physical health, cognitive functions, well-being and satisfaction with life. In this work we propose a list of non-modifiable and modifiable factors that may possibly be influenced by subjective age and its changes across an individual's lifespan. These factors can be used for a future development of individual psychological aging clocks, which may be utilized as a sensitive measure for health status and overall life satisfaction. Furthermore, recent progress in artificial intelligence and biomarkers of biological aging have enabled scientists to discover and evaluate the efficacy of potential aging- and disease-modifying drugs and interventions. We propose that biomarkers of psychological age, which are just as important as those for biological age, may likewise be used for these purposes. Indeed, these two types of markers complement one another. We foresee the development of a broad range of parametric and deep psychological and biopsychological aging clocks, which may have implications for drug development and therapeutic interventions, and thus healthcare and other industries.

Mitina Maria, Young Sergey, Zhavoronkov Alex

2020-Sep-18

biological age, depression, psychological age, subjective age, well-being

Surgery Surgery

Combining deep learning with 3D stereophotogrammetry for craniosynostosis diagnosis.

In Scientific reports ; h5-index 158.0

Craniosynostosis is a condition in which cranial sutures fuse prematurely, causing problems in normal brain and skull growth in infants. To limit the extent of cosmetic and functional problems, swift diagnosis is needed. The goal of this study is to investigate if a deep learning algorithm is capable of correctly classifying the head shape of infants as either healthy controls, or as one of the following three craniosynostosis subtypes; scaphocephaly, trigonocephaly or anterior plagiocephaly. In order to acquire cranial shape data, 3D stereophotographs were made during routine pre-operative appointments of scaphocephaly (n = 76), trigonocephaly (n = 40) and anterior plagiocephaly (n = 27) patients. 3D Stereophotographs of healthy infants (n = 53) were made between the age of 3-6 months. The cranial shape data was sampled and a deep learning network was used to classify the cranial shape data as either: healthy control, scaphocephaly patient, trigonocephaly patient or anterior plagiocephaly patient. For the training and testing of the deep learning network, a stratified tenfold cross validation was used. During testing 195 out of 196 3D stereophotographs (99.5%) were correctly classified. This study shows that trained deep learning algorithms, based on 3D stereophotographs, can discriminate between craniosynostosis subtypes and healthy controls with high accuracy.

de Jong Guido, Bijlsma Elmar, Meulstee Jene, Wennen Myrte, van Lindert Erik, Maal Thomas, Aquarius René, Delye Hans

2020-Sep-18