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

General General

Bone age assessment based on deep neural networks with annotation-free cascaded critical bone region extraction.

In Frontiers in artificial intelligence

Bone age assessment (BAA) from hand radiographs is crucial for diagnosing endocrinology disorders in adolescents and supplying therapeutic investigation. In practice, due to the conventional clinical assessment being a subjective estimation, the accuracy of BAA relies highly on the pediatrician's professionalism and experience. Recently, many deep learning methods have been proposed for the automatic estimation of bone age and had good results. However, these methods do not exploit sufficient discriminative information or require additional manual annotations of critical bone regions that are important biological identifiers in skeletal maturity, which may restrict the clinical application of these approaches. In this research, we propose a novel two-stage deep learning method for BAA without any manual region annotation, which consists of a cascaded critical bone region extraction network and a gender-assisted bone age estimation network. First, the cascaded critical bone region extraction network automatically and sequentially locates two discriminative bone regions via the visual heat maps. Second, in order to obtain an accurate BAA, the extracted critical bone regions are fed into the gender-assisted bone age estimation network. The results showed that the proposed method achieved a mean absolute error (MAE) of 5.45 months on the public dataset Radiological Society of North America (RSNA) and 3.34 months on our private dataset.

Li Zhangyong, Chen Wang, Ju Yang, Chen Yong, Hou Zhengjun, Li Xinwei, Jiang Yuhao

2023

bone age assessment, critical bone region extraction network, gender-assisted bone age estimation network, two-stage deep learning method, visual heat map

Public Health Public Health

An AI-enabled research support tool for the classification system of COVID-19.

In Frontiers in public health

The outbreak of COVID-19, a little more than 2 years ago, drastically affected all segments of society throughout the world. While at one end, the microbiologists, virologists, and medical practitioners were trying to find the cure for the infection; the Governments were laying emphasis on precautionary measures like lockdowns to lower the spread of the virus. This pandemic is perhaps also the first one of its kind in history that has research articles in all possible areas as like: medicine, sociology, psychology, supply chain management, mathematical modeling, etc. A lot of work is still continuing in this area, which is very important also for better preparedness if such a situation arises in future. The objective of the present study is to build a research support tool that will help the researchers swiftly identify the relevant literature on a specific field or topic regarding COVID-19 through a hierarchical classification system. The three main tasks done during this study are data preparation, data annotation and text data classification through bi-directional long short-term memory (bi-LSTM).

Tiwari Arti, Bhattacharjee Kamanasish, Pant Millie, Srivastava Shilpa, Snasel Vaclav

2023

Artificial Intelligence, COVID-19, bi-directional LSTM, classification, long short-term memory

General General

Precision recruitment for high-risk participants in a COVID-19 cohort study.

In Contemporary clinical trials communications

BACKGROUND : Studies for developing diagnostics and treatments for infectious diseases usually require observing the onset of infection during the study period. However, when the infection base rate incidence is low, the cohort size required to measure an effect becomes large, and recruitment becomes costly and prolonged. We developed a model for reducing recruiting time and resources in a COVID-19 detection study by targeting recruitment to high-risk individuals.

METHODS : We conducted an observational longitudinal cohort study at individual sites throughout the U.S., enrolling adults who were members of an online health and research platform. Through direct and longitudinal connection with research participants, we applied machine learning techniques to compute individual risk scores from individually permissioned data about socioeconomic and behavioral data, in combination with predicted local prevalence data. The modeled risk scores were then used to target candidates for enrollment in a hypothetical COVID-19 detection study. The main outcome measure was the incidence rate of COVID-19 according to the risk model compared with incidence rates in actual vaccine trials.

RESULTS : When we used risk scores from 66,040 participants to recruit a balanced cohort of participants for a COVID-19 detection study, we obtained a 4- to 7-fold greater COVID-19 infection incidence rate compared with similar real-world study cohorts.

CONCLUSION : This risk model offers the possibility of reducing costs, increasing the power of analyses, and shortening study periods by targeting for recruitment participants at higher risk.

Mezlini Aziz M, Caddigan Eamon, Shapiro Allison, Ramirez Ernesto, Kondow-McConaghy Helena M, Yang Justin, DeMarco Kerry, Naraghi-Arani Pejman, Foschini Luca

2023-Jun

CDC, Centers for Disease Control and Prevention, COVID-19, Clinical trials, GAMs, generalized additive models, Risk modeling

General General

Non-Asymptotic Pointwise and Worst-Case Bounds for Classical Spectrum Estimators

ArXiv Preprint

Spectrum estimation is a fundamental methodology in the analysis of time-series data, with applications including medicine, speech analysis, and control design. The asymptotic theory of spectrum estimation is well-understood, but the theory is limited when the number of samples is fixed and finite. This paper gives non-asymptotic error bounds for a broad class of spectral estimators, both pointwise (at specific frequencies) and in the worst case over all frequencies. The general method is used to derive error bounds for the classical Blackman-Tukey, Bartlett, and Welch estimators.

Andrew Lamperski

2023-03-21

General General

Disembodied AI and the limits to machine understanding of students' embodied interactions.

In Frontiers in artificial intelligence

The embodiment turn in the Learning Sciences has fueled growth of multimodal learning analytics to understand embodied interactions and make consequential educational decisions about students more rapidly, more accurately, and more personalized than ever before. Managing demands of complexity and speed is leading to growing reliance by education systems on disembodied artificial intelligence (dAI) programs, which, ironically, are inherently incapable of interpreting students' embodied interactions. This is fueling a potential crisis of complexity. Augmented intelligence systems offer promising avenues for managing this crisis by integrating the strengths of omnipresent dAI to detect complex patterns of student behavior from multimodal datastreams, with the strengths of humans to meaningfully interpret embodied interactions in service of consequential decision making to achieve a balance between complexity, interpretability, and accountability for allocating education resources to children.

Nathan Mitchell J

2023

artificial intelligence, augmented intelligence, cognitive science, embodied learning, foundation models, learning sciences, multimodality

General General

Validation of the influence of biosignals on performance of machine learning algorithms for sleep stage classification.

In Digital health

BACKGROUND : Sleep stage identification is critical in multiple areas (e.g. medicine or psychology) to diagnose sleep-related disorders. Previous studies have reported that the performance of machine learning algorithms can be changed depending on the biosignals and feature-extraction processes in sleep stage classification.

METHODS : To compare as many conditions as possible, 414 experimental conditions were applied, considering the combination of different biosignals, biosignal length, and window length. Five biosignals in polysomnography (i.e. electrocardiogram (ECG), electroencephalogram (EEG), electromyogram (EMG), electrooculogram left, and electrooculogram right) were used to identify optimal signal combinations for classification. In addition, three different signal-length conditions and six different window-length conditions were applied. The validity of each condition was examined via classification performance from the XGBoost classifiers trained using 10-fold cross-validation. Furthermore, results considering feature importance were examined to validate the experimental results in terms of model explanation.

RESULTS : The combination of EEG + EMG + ECG with a 40 s window and 120 s signal length resulted in the best classification performance (precision: 0.853, recall: 0.855, F1-score: 0.853, and accuracy: 0.853). Compared to other conditions and feature importance results, EEG signals showed a relatively higher importance for classification in the present study.

CONCLUSION : We determined the optimal biosignal and window conditions for the feature-extraction process in machine learning algorithm-based sleep stage classification. Our experimental results inform researchers in the future conduct of related studies. To generalize our results, more diverse methodologies and conditions should be applied in future studies.

Choi Junggu, Kwon Seohyun, Park Sohyun, Han Sanghoon

2023

Sleep stage classification, biosignal, classification algorithm, machine learning, polysomnography