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

General General

Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edge

ArXiv Preprint

Despite significant improvements over the last few years, cloud-based healthcare applications continue to suffer from poor adoption due to their limitations in meeting stringent security, privacy, and quality of service requirements (such as low latency). The edge computing trend, along with techniques for distributed machine learning such as federated learning, have gained popularity as a viable solution in such settings. In this paper, we leverage the capabilities of edge computing in medicine by analyzing and evaluating the potential of intelligent processing of clinical visual data at the edge allowing the remote healthcare centers, lacking advanced diagnostic facilities, to benefit from the multi-modal data securely. To this aim, we utilize the emerging concept of clustered federated learning (CFL) for an automatic diagnosis of COVID-19. Such an automated system can help reduce the burden on healthcare systems across the world that has been under a lot of stress since the COVID-19 pandemic emerged in late 2019. We evaluate the performance of the proposed framework under different experimental setups on two benchmark datasets. Promising results are obtained on both datasets resulting in comparable results against the central baseline where the specialized models (i.e., each on a specific type of COVID-19 imagery) are trained with central data, and improvements of 16\% and 11\% in overall F1-Scores have been achieved over the multi-modal model trained in the conventional Federated Learning setup on X-ray and Ultrasound datasets, respectively. We also discuss in detail the associated challenges, technologies, tools, and techniques available for deploying ML at the edge in such privacy and delay-sensitive applications.

Adnan Qayyum, Kashif Ahmad, Muhammad Ahtazaz Ahsan, Ala Al-Fuqaha, Junaid Qadir

2021-01-19

General General

A New Approach for Automatic Segmentation and Evaluation of Pigmentation Lesion by using Active Contour Model and Speeded Up Robust Features

ArXiv Preprint

Digital image processing techniques have wide applications in different scientific fields including the medicine. By use of image processing algorithms, physicians have been more successful in diagnosis of different diseases and have achieved much better treatment results. In this paper, we propose an automatic method for segmenting the skin lesions and extracting features that are associated to them. At this aim, a combination of Speeded-Up Robust Features (SURF) and Active Contour Model (ACM), is used. In the suggested method, at first region of skin lesion is segmented from the whole skin image, and then some features like the mean, variance, RGB and HSV parameters are extracted from the segmented region. Comparing the segmentation results, by use of Otsu thresholding, our proposed method, shows the superiority of our procedure over the Otsu theresholding method. Segmentation of the skin lesion by the proposed method and Otsu thresholding compared the results with physician's manual method. The proposed method for skin lesion segmentation, which is a combination of SURF and ACM, gives the best result. For empirical evaluation of our method, we have applied it on twenty different skin lesion images. Obtained results confirm the high performance, speed and accuracy of our method.

Sara Mardanisamani, Zahra Karimi, Akram Jamshidzadeh, Mehran Yazdi, Melika Farshad, Amirmehdi Farshad

2021-01-18

General General

An attention model to analyse the risk of agitation and urinary tract infections in people with dementia

ArXiv Preprint

Behavioural symptoms and urinary tract infections (UTI) are among the most common problems faced by people with dementia. One of the key challenges in the management of these conditions is early detection and timely intervention in order to reduce distress and avoid unplanned hospital admissions. Using in-home sensing technologies and machine learning models for sensor data integration and analysis provides opportunities to detect and predict clinically significant events and changes in health status. We have developed an integrated platform to collect in-home sensor data and performed an observational study to apply machine learning models for agitation and UTI risk analysis. We collected a large dataset from 88 participants with a mean age of 82 and a standard deviation of 6.5 (47 females and 41 males) to evaluate a new deep learning model that utilises attention and rational mechanism. The proposed solution can process a large volume of data over a period of time and extract significant patterns in a time-series data (i.e. attention) and use the extracted features and patterns to train risk analysis models (i.e. rational). The proposed model can explain the predictions by indicating which time-steps and features are used in a long series of time-series data. The model provides a recall of 91\% and precision of 83\% in detecting the risk of agitation and UTIs. This model can be used for early detection of conditions such as UTIs and managing of neuropsychiatric symptoms such as agitation in association with initial treatment and early intervention approaches. In our study we have developed a set of clinical pathways for early interventions using the alerts generated by the proposed model and a clinical monitoring team has been set up to use the platform and respond to the alerts according to the created intervention plans.

Honglin Li, Roonak Rezvani, Magdalena Anita Kolanko, David J. Sharp, Maitreyee Wairagkar, Ravi Vaidyanathan, Ramin Nilforooshan, Payam Barnaghi

2021-01-18

General General

Inference for BART with Multinomial Outcomes

ArXiv Preprint

The multinomial probit Bayesian additive regression trees (MPBART) framework was proposed by Kindo et al. (KD), approximating the latent utilities in the multinomial probit (MNP) model with BART (Chipman et al. 2010). Compared to multinomial logistic models, MNP does not assume independent alternatives and the correlation structure among alternatives can be specified through multivariate Gaussian distributed latent utilities. We introduce two new algorithms for fitting the MPBART and show that the theoretical mixing rates of our proposals are equal or superior to the existing algorithm in KD. Through simulations, we explore the robustness of the methods to the choice of reference level, imbalance in outcome frequencies, and the specifications of prior hyperparameters for the utility error term. The work is motivated by the application of generating posterior predictive distributions for mortality and engagement in care among HIV-positive patients based on electronic health records (EHRs) from the Academic Model Providing Access to Healthcare (AMPATH) in Kenya. In both the application and simulations, we observe better performance using our proposals as compared to KD in terms of MCMC convergence rate and posterior predictive accuracy.

Yizhen Xu, Joseph W. Hogan, Michael J. Daniels, Rami Kantor, Ann Mwangi

2021-01-18

General General

SeqCor: correct the effect of guide RNA sequences in clustered regularly interspaced short palindromic repeats/Cas9 screening by machine learning algorithm.

In Journal of genetics and genomics = Yi chuan xue bao

Clustered regularly interspaced short palindromic repeats (CRISPR)/Cas9-based screening using various guide RNA (gRNA) libraries has been executed to identify functional components for a wide range of phenotypes with regard to numerous cell types and organisms. Using data from public CRISPR/Cas9-based screening experiments, we found that the sequences of gRNAs in the library influence CRISPR/Cas9-based screening. As building a standard strategy for correcting results of all gRNA libraries is impractical, we developed SeqCor, an open-source programming bundle that enables researchers to address the result bias potentially triggered by the composition of gRNA sequences via the organization of gRNA in the library used in CRISPR/Cas9-based screening. Furthermore, SeqCor completely computerizes the extraction of sequence features that may influence single-guide RNA knockout efficiency using a machine learning approach. Taken together, we have developed a software program bundle that ought to be beneficial to the CRISPR/Cas9-based screening platform.

Liu Xiaojian, Yang Yuanyuan, Qiu Yan, Reyad-Ul-Ferdous Md, Ding Qiurong, Wang Yi

2020-Nov-28

CRISPR/Cas9-based screening, Machine learning, SeqCor

General General

Prediction of lamb carcase C-site fat depth and GR tissue depth using a non-invasive portable microwave system.

In Meat science

The experiment evaluated the ability of portable ultra-wide band microwave coupled with a Vivaldi patch antenna to predict carcase C-site fat and GR tissue depth. For C-site, 1070 lambs, across 8 slaughter groups were scanned and for GR, 286 lambs across 2 slaughter groups. Prediction equations for reflected microwave signals were constructed with a partial least squares regression two-components model and a machine learning Ensemble Stacking technique. Models were trained and validated using cross validation methods in actual datasets and then in datasets balanced for tissue depth. The precision and accuracy indicators of microwave predicted C-site fat depth across pooled and balanced datasets were RMSEP 1.53 mm, R2 0.54, and bias of 0.03 mm. The precision and accuracy for GR tissue depth across pooled and balanced datasets were RMSEP 2.57 mm, R2 0.79 and bias of 0.33 mm. Using the AUS-MEAT fat score accreditation framework this device was able to accurately predict GR 92.7% of the time.

Marimuthu J, Loudon K M W, Gardner G E

2020-Dec-04

Accuracy, Ensemble, Machine leaning, Meat quality, Objective measurement, Precision