Cerebrospinal fluid reference proteins increase accuracy and interpretability of biomarkers for brain diseases.

Cerebrospinal fluid (CSF) biomarkers reflect brain pathophysiology and are used extensively in translational research as well as in clinical practice for diagnosis of neurological diseases, e.g., Alzheimer's disease (AD). However, CSF biomarker concentrations may be influenced by non-disease related inter-individual variability. Here we use a data-driven approach to demonstrate the existence of inter-individual variability in mean standardized CSF protein levels. We show that these non-disease related differences cause many commonly reported CSF biomarkers to be highly correlated, thereby producing misleading results if not accounted for. To adjust for this inter-individual variability, we identified and evaluated high-performing reference proteins which improved the diagnostic accuracy of key CSF AD biomarkers. Our reference protein method attenuates the risk for false positive findings, and improves the sensitivity and specificity of CSF biomarkers, with broad implications for both research and clinical practice.

The use of accelerometer bracelets to evaluate arm motor function over a stroke rehabilitation period - an explorative observational study.

BACKGROUND: Assessments of arm motor function are usually based on clinical examinations or self-reported rating scales. Wrist-worn accelerometers can be a good complement to measure movement patterns after stroke. Currently there is limited knowledge of how accelerometry correlate to clinically used scales. The purpose of this study was therefore to evaluate the relationship between intermittent measurements of wrist-worn accelerometers and the patient's progression of arm motor function assessed by routine clinical outcome measures during a rehabilitation period. METHODS: Patients enrolled in in-hospital rehabilitation following a stroke were invited. Included patients were asked to wear wrist accelerometers for 24 h at the start (T1) and end (T2) of their rehabilitation period. On both occasions arm motor function was assessed by the modified Motor Assessment Scale (M_MAS) and the Motor Activity Log (MAL). The recorded accelerometry was compared to M_MAS and MAL. RESULTS: 20 patients were included, of which 18 completed all measurements and were therefore included in the final analysis. The resulting Spearman's rank correlation coefficient showed a strong positive correlation between measured wrist acceleration in the affected arm and M-MAS and MAL values at T1, 0.94 (p < 0.05) for M_MAS and 0.74 (p < 0.05) for the MAL values, and a slightly weaker positive correlation at T2, 0.57 (p < 0.05) for M_MAS and 0.46 - 0.45 (p = 0.06) for the MAL values. However, no correlation was seen for the difference between the two sessions. CONCLUSIONS: The results confirm that the wrist acceleration can differentiate between the affected and non-affected arm, and that there is a positive correlation between accelerometry and clinical measures. Many of the patients did not change their M-MAS or MAL scores during the rehabilitation period, which may explain why no correlation was seen for the difference between measurements during the rehabilitation period. Further studies should include continuous accelerometry throughout the rehabilitation period to reduce the impact of day-to-day variability.

Deep learning prediction of quantitative coronary angiography values using myocardial perfusion images with a CZT camera.

PURPOSE: Evaluate the prediction of quantitative coronary angiography (QCA) values from MPI, by means of deep learning. METHODS: 546 patients (67% men) undergoing stress 99mTc-tetrofosmin MPI in a CZT camera in the upright and supine position were included (1092 MPIs). Patients were divided into two groups: ICA group included 271 patients who performed an ICA within 6 months of MPI and a control group with 275 patients with low pre-test probability for CAD and a normal MPI. QCA analyses were performed using radiologic software and verified by an expert reader. Left ventricular myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. A deep learning model was trained using a double cross-validation scheme such that all data could be used as test data as well. RESULTS: Area under the receiver-operating characteristic curve for the prediction of QCA, with > 50% narrowing of the artery, by deep learning for the external test cohort: per patient 85% [95% confidence interval (CI) 84%-87%] and per vessel; LAD 74% (CI 72%-76%), RCA 85% (CI 83%-86%), LCx 81% (CI 78%-84%), and average 80% (CI 77%-83%). CONCLUSION: Deep learning can predict the presence of different QCA percentages of coronary artery stenosis from MPIs.

Detection of Unilateral Arm Paresis after Stroke by Wearable Accelerometers and Machine Learning.

Recent advances in stroke treatment have provided effective tools to successfully treat ischemic stroke, but still a majority of patients are not treated due to late arrival to hospital. With modern stroke treatment, earlier arrival would greatly improve the overall treatment results. This prospective study was performed to asses the capability of bilateral accelerometers worn in bracelets 24/7 to detect unilateral arm paralysis, a hallmark symptom of stroke, early enough to receive treatment. Classical machine learning algorithms as well as state-of-the-art deep neural networks were evaluated on detection times between 15 min and 120 min. Motion data were collected using triaxial accelerometer bracelets worn on both arms for 24 h. Eighty-four stroke patients with unilateral arm motor impairment and 101 healthy subjects participated in the study. Accelerometer data were divided into data windows of different lengths and analyzed using multiple machine learning algorithms. The results show that all algorithms performed well in separating the two groups early enough to be clinically relevant, based on wrist-worn accelerometers. The two evaluated deep learning models, fully convolutional network and InceptionTime, performed better than the classical machine learning models with an AUC score between 0.947-0.957 on 15 min data windows and up to 0.993-0.994 on 120 min data windows. Window lengths longer than 90 min only marginally improved performance. The difference in performance between the deep learning models and the classical models was statistically significant according to a non-parametric Friedman test followed by a post-hoc Nemenyi test. Introduction of wearable stroke detection devices may dramatically increase the portion of stroke patients eligible for revascularization and shorten the time to treatment. Since the treatment effect is highly time-dependent, early stroke detection may dramatically improve stroke outcomes.

An Artificial Intelligence-based Support Tool for Automation and Standardisation of Gleason Grading in Prostate Biopsies.

BACKGROUND: Gleason grading is the standard diagnostic method for prostate cancer and is essential for determining prognosis and treatment. The dearth of expert pathologists, the inter- and intraobserver variability, as well as the labour intensity of Gleason grading all necessitate the development of a user-friendly tool for robust standardisation. OBJECTIVE: To develop an artificial intelligence (AI) algorithm, based on machine learning and convolutional neural networks, as a tool for improved standardisation in Gleason grading in prostate cancer biopsies. DESIGN, SETTING, AND PARTICIPANTS: A total of 698 prostate biopsy sections from 174 patients were used for training. The training sections were annotated by two senior consultant pathologists. The final algorithm was tested on 37 biopsy sections from 21 patients, with digitised slide images from two different scanners. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Correlation, sensitivity, and specificity parameters were calculated. RESULTS AND LIMITATIONS: The algorithm shows high accuracy in detecting cancer areas (sensitivity: 100%, specificity: 68%). Compared with the pathologists, the algorithm also performed well in detecting cancer areas (intraclass correlation coefficient [ICC]: 0.99) and assigning the Gleason patterns correctly: Gleason patterns 3 and 4 (ICC: 0.96 and 0.94, respectively), and to a lesser extent, Gleason pattern 5 (ICC: 0.82). Similar results were obtained using two different scanners. CONCLUSIONS: Our AI-based algorithm can reliably detect prostate cancer and quantify the Gleason patterns in core needle biopsies, with similar accuracy as pathologists. The results are reproducible on images from different scanners with a proven low level of intraobserver variability. We believe that this AI tool could be regarded as an efficient and interactive tool for pathologists. PATIENT SUMMARY: We developed a sensitive artificial intelligence tool for prostate biopsies, which detects and grades cancer with similar accuracy to pathologists. This tool holds promise to improve the diagnosis of prostate cancer.

Cellular traction forces: a useful parameter in cancer research.

The search for new cancer biomarkers is essential for fundamental research, diagnostics, as well as for patient treatment and monitoring. Whereas most cancer biomarkers are biomolecules, an increasing number of studies show that mechanical cues are promising biomarker candidates. Although cell deformability has been shown to be a possible cancer biomarker, cellular forces as cancer biomarkers have been left largely unexplored. Here, we measure traction forces of cancer and normal-like cells at high spatial resolution using a robust method based on dense vertical arrays of nanowires. A force map is created using automated image analysis based on the localization of the fluorescent tips of the nanowires. We show that the force distribution and magnitude differ between MCF7 breast cancer cells and MCF10A normal-like breast epithelial cells, and that monitoring traction forces can be used to investigate the effects of anticancer drugs.

Action sequencing in the spontaneous swimming behavior of zebrafish larvae - implications for drug development.

All motile organisms need to organize their motor output to obtain functional goals. In vertebrates, natural behaviors are generally composed of a relatively large set of motor components which in turn are combined into a rich repertoire of complex actions. It is therefore an experimental challenge to investigate the organizational principles of natural behaviors. Using the relatively simple locomotion pattern of 10 days old zebrafish larvae we have here characterized the basic organizational principles governing the swimming behavior. Our results show that transitions between different behavioral states can be described by a model combining a stochastic component with a control signal. By dividing swimming bouts into a limited number of categories, we show that similar types of swimming behavior as well as stand-stills between bouts were temporally clustered, indicating a basic level of action sequencing. Finally, we show that pharmacological manipulations known to induce alterations in the organization of motor behavior in mammals, mainly through basal ganglia interactions, have related effects in zebrafish larvae. This latter finding may be of specific relevance to the field of drug development given the growing importance of zebrafish larvae in phenotypic screening for novel drug candidates acting on central nervous system targets.

Smooth pursuit detection in binocular eye-tracking data with automatic video-based performance evaluation.

An increasing number of researchers record binocular eye-tracking signals from participants viewing moving stimuli, but the majority of event-detection algorithms are monocular and do not consider smooth pursuit movements. The purposes of the present study are to develop an algorithm that discriminates between fixations and smooth pursuit movements in binocular eye-tracking signals and to evaluate its performance using an automated video-based strategy. The proposed algorithm uses a clustering approach that takes both spatial and temporal aspects of the binocular eye-tracking signal into account, and is evaluated using a novel video-based evaluation strategy based on automatically detected moving objects in the video stimuli. The binocular algorithm detects 98% of fixations in image stimuli compared to 95% when only one eye is used, while for video stimuli, both the binocular and monocular algorithms detect around 40% of smooth pursuit movements. The present article shows that using binocular information for discrimination of fixations and smooth pursuit movements is advantageous in static stimuli, without impairing the algorithm's ability to detect smooth pursuit movements in video and moving-dot stimuli. With an automated evaluation strategy, time-consuming manual annotations are avoided and a larger amount of data can be used in the evaluation process.

Exploratory study of EEG burst characteristics in preterm infants.

In this paper, we study machine learning techniques and features of electroencephalography activity bursts for predicting outcome in extremely preterm infants. It was previously shown that the distribution of interburst interval durations predicts clinical outcome, but in previous work the information within the bursts has been neglected. In this paper, we perform exploratory analysis of feature extraction of burst characteristics and use machine learning techniques to show that such features could be used for outcome prediction. The results are promising, but further verification in larger datasets is needed to obtain conclusive results.

A pilot study of facial, cranial and brain MRI morphometry in men with schizophrenia: part 2.

This pilot study applies a new 3D morphometric MR method to test the hypothesis that men with schizophrenia (vs. controls) have deviant facial shapes and landmark relations in cranio/facial/brain (CFB) regions. This constitutes Part 2 of paired articles in this issue of Psychiatry Research: Neuroimaging, in which Part 1 presents the new method in detail. MRI coordinates from CFB landmarks of 23 patients and 15 controls were identified and then aligned with the Procrustes model, leaving shape as the only unit-less geometrical information. Men with schizophrenia had significantly longer mid- and lower-facial heights, and greater lower (left) facial depth, with a tendency toward rotation along the facial midline. This supports findings from earlier anthropometric and 3D studies of the "exterior" (face). In contrast, none of the patient-control differences for the new "interior" (cranial-brain) distances reached statistical significance. These results need to be retested on a larger sample of both sexes.