Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

A survey on deep learning in medical image analysis

Summary Background Since December, 2019, Wuhan, China, has experienced an outbreak of coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Epidemiological and clinical characteristics of patients with COVID-19 have been reported but risk factors for mortality and a detailed clinical course of illness, including viral shedding, have not been well described. Methods In this retrospective, multicentre cohort study, we included all adult inpatients (≥18 years old) with laboratory-confirmed COVID-19 from Jinyintan Hospital and Wuhan Pulmonary Hospital (Wuhan, China) who had been discharged or had died by Jan 31, 2020. Demographic, clinical, treatment, and laboratory data, including serial samples for viral RNA detection, were extracted from electronic medical records and compared between survivors and non-survivors. We used univariable and multivariable logistic regression methods to explore the risk factors associated with in-hospital death. Findings 191 patients (135 from Jinyintan Hospital and 56 from Wuhan Pulmonary Hospital) were included in this study, of whom 137 were discharged and 54 died in hospital. 91 (48%) patients had a comorbidity, with hypertension being the most common (58 [30%] patients), followed by diabetes (36 [19%] patients) and coronary heart disease (15 [8%] patients). Multivariable regression showed increasing odds of in-hospital death associated with older age (odds ratio 1·10, 95% CI 1·03–1·17, per year increase; p=0·0043), higher Sequential Organ Failure Assessment (SOFA) score (5·65, 2·61–12·23; p Interpretation The potential risk factors of older age, high SOFA score, and d-dimer greater than 1 μg/mL could help clinicians to identify patients with poor prognosis at an early stage. Prolonged viral shedding provides the rationale for a strategy of isolation of infected patients and optimal antiviral interventions in the future. Funding Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences; National Science Grant for Distinguished Young Scholars; National Key Research and Development Program of China; The Beijing Science and Technology Project; and Major Projects of National Science and Technology on New Drug Creation and Development.

Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study

6-month consequences of COVID-19 in patients discharged from hospital: a cohort study.

Objective To review and appraise the validity and usefulness of published and preprint reports of prediction models for diagnosing coronavirus disease 2019 (covid-19) in patients with suspected infection, for prognosis of patients with covid-19, and for detecting people in the general population at increased risk of covid-19 infection or being admitted to hospital with the disease. Design Living systematic review and critical appraisal by the COVID-PRECISE (Precise Risk Estimation to optimise covid-19 Care for Infected or Suspected patients in diverse sEttings) group. Data sources PubMed and Embase through Ovid, up to 1 July 2020, supplemented with arXiv, medRxiv, and bioRxiv up to 5 May 2020. Study selection Studies that developed or validated a multivariable covid-19 related prediction model. Data extraction At least two authors independently extracted data using the CHARMS (critical appraisal and data extraction for systematic reviews of prediction modelling studies) checklist; risk of bias was assessed using PROBAST (prediction model risk of bias assessment tool). Results 37 421 titles were screened, and 169 studies describing 232 prediction models were included. The review identified seven models for identifying people at risk in the general population; 118 diagnostic models for detecting covid-19 (75 were based on medical imaging, 10 to diagnose disease severity); and 107 prognostic models for predicting mortality risk, progression to severe disease, intensive care unit admission, ventilation, intubation, or length of hospital stay. The most frequent types of predictors included in the covid-19 prediction models are vital signs, age, comorbidities, and image features. Flu-like symptoms are frequently predictive in diagnostic models, while sex, C reactive protein, and lymphocyte counts are frequent prognostic factors. Reported C index estimates from the strongest form of validation available per model ranged from 0.71 to 0.99 in prediction models for the general population, from 0.65 to more than 0.99 in diagnostic models, and from 0.54 to 0.99 in prognostic models. All models were rated at high or unclear risk of bias, mostly because of non-representative selection of control patients, exclusion of patients who had not experienced the event of interest by the end of the study, high risk of model overfitting, and unclear reporting. Many models did not include a description of the target population (n=27, 12%) or care setting (n=75, 32%), and only 11 (5%) were externally validated by a calibration plot. The Jehi diagnostic model and the 4C mortality score were identified as promising models. Conclusion Prediction models for covid-19 are quickly entering the academic literature to support medical decision making at a time when they are urgently needed. This review indicates that almost all pubished prediction models are poorly reported, and at high risk of bias such that their reported predictive performance is probably optimistic. However, we have identified two (one diagnostic and one prognostic) promising models that should soon be validated in multiple cohorts, preferably through collaborative efforts and data sharing to also allow an investigation of the stability and heterogeneity in their performance across populations and settings. Details on all reviewed models are publicly available at https://www.covprecise.org/. Methodological guidance as provided in this paper should be followed because unreliable predictions could cause more harm than benefit in guiding clinical decisions. Finally, prediction model authors should adhere to the TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) reporting guideline. Systematic review registration Protocol https://osf.io/ehc47/, registration https://osf.io/wy245. Readers’ note This article is a living systematic review that will be updated to reflect emerging evidence. Updates may occur for up to two years from the date of original publication. This version is update 3 of the original article published on 7 April 2020 (BMJ 2020;369:m1328). Previous updates can be found as data supplements (https://www.bmj.com/content/369/bmj.m1328/related#datasupp). When citing this paper please consider adding the update number and date of access for clarity.

https://www.bmj.com/content/bmj/369/bmj.m1328.full.pdf

Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal

Parkinson’s Disease (PD) is the most common motor neurodegenerative disease in elderly population. Transcranial sonography (TCS) has become a popular imaging tool for diagnosis of PD in clinical practice. Moreover, several pioneering work have developed the computer-aided diagnosis (CAD) for PD with the transcranial B-mode sonography (TBS). It is worth noting that TCS not only has the TBS modality, but also can image the blood flow of major cerebral arteries, which is named transcranial Doppler sonography (TDS). TDS also has been applied to evaluate PD patients with orthostatic hypotension. However, the TDS-based CAD for PD has not been investigated. Since TBS and TDS provide the complementary structural and functional information about brain, it is feasible to develop a multi-modal TCS-based CAD for PD by combining both TBS and TDS. Therefore, in this work, we propose a multiple kernel learning (MKL) based CAD for PD with multi-modal TCS imaging. Particularly, the statistical and texture features are extracted from the midbrain region from TBS images, and the features about blood flow are calculated from the spectrum curves in TDS. The multi-modal features are then fed to a MKL classifier for classification of PD. The experimental results show that the multi-modal TCS-based method outperforms both the single-modal TBS- and TDS-based algorithm, which suggests the feasibility and effectiveness of combining TBS and TDS for diagnosis of PD.

Multiple Kernel Learning Based Classification of Parkinson’s Disease With Multi-Modal Transcranial Sonography

Transcranial sonography (TCS) has gained increasing application for diagnosis of Parkinson's disease (PD) in clinical practice in recent years, because most PD patients, even in the early stage of PD, have abnormal hyperechogenicity of the substantia nigra (SN) in brainstem shown in TCS images. Therefore, the region of interest (ROI) for feature extraction should cover the SN region in a computer-aided diagnosis (CAD) system. The ROI size naturally affects the feature representation. However, there currently exist no unified standard for determining the size of ROI. In this work, we quantitatively compare the performance of TCS-based CAD with three sizes of ROIs, namely the entire midbrain (EM) region, the half of midbrain (HoM) region and the SN region. The experimental results on the original extracted features and the features by dimensionality reduction show that ROI covering the EM region achieves the overall best diagnosis performance. The results indicates that the neighboring regions around SN might also have abnormal symptoms, which cannot be clearly observed with naked eyes. It suggests that the large ROI includes more information for feature representation to improve the diagnosis performance of TCS-based CAD for PD.

Impact of region of interest size on transcranial sonography based computer-aided diagnosis for Parkinson's disease.

To explore the long-term trajectories considering pneumonia volumes and lymphocyte counts with individual data in COVID-19. A cohort of 257 convalescent COVID-19 patients (131 male and 126 females) were included. Group-based multi-trajectory modelling was applied to identify different trajectories in terms of pneumonia lesion percentage and lymphocyte counts covering the time from onset to post-discharge follow-ups. We studied the basic characteristics and disease severity associated with the trajectories. We characterised four distinct trajectory subgroups. (1) Group 1 (13.9%), pneumonia increased until a peak lesion percentage of 1.9% (IQR 0.7–4.4) before absorption. The slightly decreased lymphocyte rapidly recovered to the top half of the normal range. (2) Group 2 (44.7%), the peak lesion percentage was 7.2% (IQR 3.2–12.7). The abnormal lymphocyte count restored to normal soon. (3) Group 3 (26.0%), the peak lesion percentage reached 14.2% (IQR 8.5–19.8). The lymphocytes continuously dropped to 0.75 × 109/L after one day post-onset before slowly recovering. (4) Group 4 (15.4%), the peak lesion percentage reached 41.4% (IQR 34.8–47.9), much higher than other groups. Lymphopenia was aggravated until the lymphocytes declined to 0.80 × 109/L on the fourth day and slowly recovered later. Patients in the higher order groups were older and more likely to have hypertension and diabetes (all P values < 0.05), and have more severe disease. Our findings provide new insights to understand the heterogeneous natural courses of COVID-19 patients and the associations of distinct trajectories with disease severity, which is essential to improve the early risk assessment, patient monitoring, and follow-up schedule.

/pdf/longitudinal-trajectories-of-pneumonia-lesions-and-b4b2yr5xjd.pdf

Longitudinal trajectories of pneumonia lesions and lymphocyte counts associated with disease severity among convalescent COVID-19 patients: a group-based multi-trajectory analysis.

Purpose: Accurate prediction of the progression to severe stroke in initially diagnosed nonsevere patients with acute-subacute anterior circulation nonlacuna ischemic infarction (ASACNLII) is important in making clinical decision. This study aimed to apply a machine learning method to predict if the initially diagnosed nonsevere patients with ASACNLII would progress to severe stroke by using diffusion-weighted images and clinical information on admission. Methods: This retrospective study enrolled 344 patients with ASACNLII from June 2017 to August 2020 on admission, and 108 cases progressed to severe stroke during hospitalization within 3-21 days. The entire data were randomized into a training set (n = 271) and an independent test set (n = 73). A U-Net neural network was employed for automatic segmentation and volume measurement of the ischemic lesions. Predictive models were developed and used for evaluating the progression to severe stroke using different feature sets (the volume data, the clinical data, and the combination) and machine learning methods (random forest, support vector machine, and logistic regression). Results: The U-Net showed high correlation with manual segmentation in terms of Dice coefficient of 0.806 and R2 value of the volume measurements of 0.960 in the test set. The random forest classifier of the volume + clinical combination achieved the best area under the receiver operating characteristic curve of 0.8358 (95% CI 0.7321-0.9269), and the accuracy, sensitivity, and specificity were 0.7780 (0.7397-0.7945), 0.7695 (0.6102-0.9074), and 0.8686 (0.6923-1.0), respectively. The Shapley additive explanation diagram showed the volume variable as the most important predictor. Conclusion: The U-Net was fully automatic and showed a high correlation with manual segmentation. An integrated approach combining clinical variables and stroke lesion volumes that were derived from the advanced machine learning algorithms had high accuracy in predicting the progression to severe stroke in ASACNLII patients.

/pdf/prediction-of-progression-to-severe-stroke-in-initially-474iq4hndg.pdf

Prediction of Progression to Severe Stroke in Initially Diagnosed Anterior Circulation Ischemic Cerebral Infarction.

The transcranial sonography (TCS) based computer-aided diagnosis (CAD) for Parkinson’s disease (PD) has attracted considerable attention. The learning using privileged information (LUPI) is a new learning paradigm, in which, the privileged information (PI) is only available for model training, but unavailable in the testing stage. The Random vector functional link network plus (RVFL+) algorithm is a newly proposed LUPI algorithm, which has shown its effectiveness for classification task. Moreover, the kernel-based RVFL+ (KRVFL+) has been proposed to overcome the randomness in RVFL+. In this work, we propose a cascaded KRVFL+ (cKRVFL+) algorithm for the single-modal TCS-based PD diagnosis. The predicted value of the former KRVFL+ classifier is adopted as the PI for the current KRVFL+, and only the KRVFL+ in the last layer is finally used as classifiers during the testing stage. This cascaded structure progressively promotes the discrimination performance of KRVFL+ classifier. The experimental results show the effectiveness of the cascaded LUPI classifier framework for single-modality TCS based diagnosis of PD, and the proposed cKRVFL+ algorithm achieves the best performance.

Qi Zhang

Papers

Multiple Kernel Learning Based Classification of Parkinson’s Disease With Multi-Modal Transcranial Sonography

Impact of region of interest size on transcranial sonography based computer-aided diagnosis for Parkinson's disease.

Longitudinal trajectories of pneumonia lesions and lymphocyte counts associated with disease severity among convalescent COVID-19 patients: a group-based multi-trajectory analysis.

Prediction of Progression to Severe Stroke in Initially Diagnosed Anterior Circulation Ischemic Cerebral Infarction.

Transcranial Sonography Based Diagnosis Of Parkinson’s Disease Via Cascaded Kernel RVFL+