Recognition of intraglomerular histological features with deep learning in protocol transplant biopsies and their association with kidney function and prognosis.

Background: The Banff Classification may not adequately address protocol transplant biopsies categorized as normal in patients experiencing unexplained graft function deterioration. This study seeks to employ convolutional neural networks to automate the segmentation of glomerular cells and capillaries and assess their correlation with transplant function. Methods: A total of 215 patients were categorized into three groups. In the Training cohort, glomerular cells and capillaries from 37 patients were manually annotated to train the networks. The Test cohort (24 patients) compared manual annotations vs automated predictions, while the Application cohort (154 protocol transplant biopsies) examined predicted factors in relation to kidney function and prognosis. Results: In the Test cohort, the networks recognized histological structures with Precision, Recall, F-score and Intersection Over Union exceeding 0.92, 0.85, 0.89 and 0.74, respectively. Univariate analysis revealed associations between the estimated glomerular filtration rate (eGFR) at biopsy and relative endothelial area (r = 0.19, P = .027), endothelial cell density (r = 0.20, P = .017), mean parietal epithelial cell area (r = -0.38, P < .001), parietal epithelial cell density (r = 0.29, P < .001) and mesangial cell density (r = 0.22, P = .010). Multivariate analysis retained only endothelial cell density as associated with eGFR (Beta = 0.13, P = .040). Endothelial cell density (r = -0.22, P = .010) and mean podocyte area (r = 0.21, P = .016) were linked to proteinuria at biopsy. Over 44 ± 29 months, 25 patients (16%) reached the primary composite endpoint (dialysis initiation, or 30% eGFR sustained decline), with relative endothelial area, mean endothelial cell area and parietal epithelial cell density below medians linked to this endpoint [hazard ratios, respectively, of 2.63 (P = .048), 2.60 (P = .039) and 3.23 (P = .019)]. Conclusion: This study automated the measurement of intraglomerular cells and capillaries. Our results suggest that the precise segmentation of endothelial and epithelial cells may serve as a potential future marker for the risk of graft loss.

Automated evaluation with deep learning of total interstitial inflammation and peritubular capillaritis on kidney biopsies.

BACKGROUND: Interstitial inflammation and peritubular capillaritis are observed in many diseases on native and transplant kidney biopsies. A precise and automated evaluation of these histological criteria could help stratify patients' kidney prognoses and facilitate therapeutic management. METHODS: We used a convolutional neural network to evaluate those criteria on kidney biopsies. A total of 423 kidney samples from various diseases were included; 83 kidney samples were used for the neural network training, 106 for comparing manual annotations on limited areas to automated predictions, and 234 to compare automated and visual gradings. RESULTS: The precision, recall and F-score for leukocyte detection were, respectively, 81%, 71% and 76%. Regarding peritubular capillaries detection the precision, recall and F-score were, respectively, 82%, 83% and 82%. There was a strong correlation between the predicted and observed grading of total inflammation, as for the grading of capillaritis (r = 0.89 and r = 0.82, respectively, all P < .0001). The areas under the receiver operating characteristics curves for the prediction of pathologists' Banff total inflammation (ti) and peritubular capillaritis (ptc) scores were respectively all above 0.94 and 0.86. The kappa coefficients between the visual and the neural networks' scores were respectively 0.74, 0.78 and 0.68 for ti ≥1, ti ≥2 and ti ≥3, and 0.62, 0.64 and 0.79 for ptc ≥1, ptc ≥2 and ptc ≥3. In a subgroup of patients with immunoglobulin A nephropathy, the inflammation severity was highly correlated to kidney function at biopsy on univariate and multivariate analyses. CONCLUSION: We developed a tool using deep learning that scores the total inflammation and capillaritis, demonstrating the potential of artificial intelligence in kidney pathology.

Identifying health conditions associated with Alzheimer's disease up to 15 years before diagnosis: an agnostic study of French and British health records.

BACKGROUND: The identification of modifiable risk factors for Alzheimer's disease is paramount for early prevention and the targeting of new interventions. We aimed to assess the associations between health conditions diagnosed in primary care and the risk of incident Alzheimer's disease over time, up to 15 years before a first Alzheimer's disease diagnosis. METHODS: In this agnostic study of French and British health records, data from 20 214 patients with Alzheimer's disease in the UK and 19 458 patients with Alzheimer's disease in France were extracted from The Health Improvement Network database. We considered data recorded from Jan 1, 1996, to March 31, 2020 in the UK and from Jan 4, 1998, to Feb 20, 2019, in France. For each Alzheimer's disease case, a control was randomly assigned after matching for sex and age at last visit. We agnostically tested the associations between 123 different diagnoses of the International Classification of Diseases, 10th revision, extracted from health records, and Alzheimer's disease, by running a conditional logistic regression to account for matching of cases and controls. We focused on three time periods before diagnosis of Alzheimer's disease, to separate risk factors from early symptoms and comorbidities. FINDINGS: Unadjusted odds ratios (ORs) and 95% CIs for the association between Alzheimer's disease and various health conditions were estimated, and p values were corrected for multiple comparisons. In both the British and French studies, ten health conditions were significantly positively associated with increased Alzheimer's disease risk, in a window of exposure from 2-10 years before Alzheimer's disease diagnosis, comprising major depressive disorder (UK OR 1·34, 95% CI 1·23-1·46; France OR 1·73, 1·57-1·91), anxiety (UK OR 1·36, 1·25-1·47; France OR 1·50, 1·36-1·65), reaction to severe stress and adjustment disorders (UK OR 1·40, 1·24-1·59; France OR 1·83, 1·55-2·15), hearing loss (UK OR 1·19, 1·11-1·28; France OR 1·51, 1·21-1·89), constipation (UK OR 1·31, 1·22-1·41; France OR 1·59, 1·44-1·75), spondylosis (UK OR 1·26, 1·14-1·39; France OR 1·62, 1·44-1·81), abnormal weight loss (UK OR 1·47, 1·33-1·63; France OR 1·88, 1·56-2·26), malaise and fatigue (UK OR 1·23, 1·14-1·32; France OR 1·59, 1·46-1·73), memory loss (UK OR 7·63, 6·65-8·76; France OR 4·41, 3·07-6·34), and syncope and collapse (UK OR 1·23, 1·10-1·37; France OR 1·57, 1·26-1·96). Depression was the first comorbid condition associated with Alzheimer's disease, appearing at least 9 years before the first clinical diagnosis, followed by anxiety, constipation, and abnormal weight loss. INTERPRETATION: These results from two independent primary care databases provide new evidence on the temporality of risk factors and early signs of Alzheimer's disease that are observable at the general practitioner level. These results could guide the implementation of new primary and secondary prevention policies. FUNDING: Agence Nationale de la Recherche.

Changes in the use of psychotropic drugs during the course of Alzheimer's disease: A large-scale longitudinal study of French medical records.

INTRODUCTION: We aim to understand how patients with Alzheimer's disease (AD) are treated by identifying in a longitudinal fashion the late-life changes in patients' medical history that precede and follow AD diagnosis. METHODS: We use prescription history of 34,782 patients followed between 1996 and 2019 by French general practitioners. We compare patients with an AD diagnosis, patients with mild cognitive impairment (MCI), and patients free of mental disorders. We use a generalized mixed-effects model to study the longitudinal changes in the prescription of eight drug types for a period 15 years before diagnosis and 10 years after. RESULTS: In the decades preceding diagnosis, we find that future AD patients are treated significantly more than MCI patients with most psychotropic drugs and that most studied drugs are increasingly prescribed with age. At the time of diagnosis, all psychotropic drugs except benzodiazepines show a significant increase in prescription, while other drugs are significantly less prescribed. In the 10 years after diagnosis, nearly all categories of drugs are less and less prescribed including antidementia drugs. DISCUSSION: Pre-diagnosis differences between future AD patients and MCI patients may indicate that subtle cognitive changes are recognized and treated as psychiatric symptoms. The disclosure of AD diagnosis drastically changes patients' care, priority being given to the management of psychiatric symptoms. The decrease of all prescriptions in the late stages may reflect treatment discontinuation and simplification of therapeutic procedures. This study therefore provides new insights into the medical practices for management of AD.

A machine learning approach to screen for preclinical Alzheimer's disease.

Combining multimodal biomarkers could help in the early diagnosis of Alzheimer's disease (AD). We included 304 cognitively normal individuals from the INSIGHT-preAD cohort. Amyloid and neurodegeneration were assessed on 18F-florbetapir and 18F-fluorodeoxyglucose PET, respectively. We used a nested cross-validation approach with non-invasive features (electroencephalography [EEG], APOE4 genotype, demographic, neuropsychological and MRI data) to predict: 1/ amyloid status; 2/ neurodegeneration status; 3/ decline to prodromal AD at 5-year follow-up. Importantly, EEG was most strongly predictive of neurodegeneration, even when reducing the number of channels from 224 down to 4, as 4-channel EEG best predicted neurodegeneration (negative predictive value [NPV] = 82%, positive predictive value [PPV] = 38%, 77% specificity, 45% sensitivity). The combination of demographic, neuropsychological data, APOE4 and hippocampal volumetry most strongly predicted amyloid (80% NPV, 41% PPV, 70% specificity, 58% sensitivity) and most strongly predicted decline to prodromal AD at 5 years (97% NPV, 14% PPV, 83% specificity, 50% sensitivity). Thus, machine learning can help to screen patients at high risk of preclinical AD using non-invasive and affordable biomarkers.

Predicting the progression of mild cognitive impairment using machine learning: A systematic, quantitative and critical review.

We performed a systematic review of studies focusing on the automatic prediction of the progression of mild cognitive impairment to Alzheimer's disease (AD) dementia, and a quantitative analysis of the methodological choices impacting performance. This review included 172 articles, from which 234 experiments were extracted. For each of them, we reported the used data set, the feature types, the algorithm type, performance and potential methodological issues. The impact of these characteristics on the performance was evaluated using a multivariate mixed effect linear regressions. We found that using cognitive, fluorodeoxyglucose-positron emission tomography or potentially electroencephalography and magnetoencephalography variables significantly improved predictive performance compared to not including them, whereas including other modalities, in particular T1 magnetic resonance imaging, did not show a significant effect. The good performance of cognitive assessments questions the wide use of imaging for predicting the progression to AD and advocates for exploring further fine domain-specific cognitive assessments. We also identified several methodological issues, including the absence of a test set, or its use for feature selection or parameter tuning in nearly a fourth of the papers. Other issues, found in 15% of the studies, cast doubts on the relevance of the method to clinical practice. We also highlight that short-term predictions are likely not to be better than predicting that subjects stay stable over time. These issues highlight the importance of adhering to good practices for the use of machine learning as a decision support system for the clinical practice.

Ensemble Learning of Convolutional Neural Network, Support Vector Machine, and Best Linear Unbiased Predictor for Brain Age Prediction: ARAMIS Contribution to the Predictive Analytics Competition 2019 Challenge.

We ranked third in the Predictive Analytics Competition (PAC) 2019 challenge by achieving a mean absolute error (MAE) of 3.33 years in predicting age from T1-weighted MRI brain images. Our approach combined seven algorithms that allow generating predictions when the number of features exceeds the number of observations, in particular, two versions of best linear unbiased predictor (BLUP), support vector machine (SVM), two shallow convolutional neural networks (CNNs), and the famous ResNet and Inception V1. Ensemble learning was derived from estimating weights via linear regression in a hold-out subset of the training sample. We further evaluated and identified factors that could influence prediction accuracy: choice of algorithm, ensemble learning, and features used as input/MRI image processing. Our prediction error was correlated with age, and absolute error was greater for older participants, suggesting to increase the training sample for this subgroup. Our results may be used to guide researchers to build age predictors on healthy individuals, which can be used in research and in the clinics as non-specific predictors of disease status.

Reduction of recruitment costs in preclinical AD trials: validation of automatic pre-screening algorithm for brain amyloidosis.

We propose a method for recruiting asymptomatic Amyloid positive individuals in clinical trials, using a two-step process. We first select during a pre-screening phase a subset of individuals which are more likely to be amyloid positive based on the automatic analysis of data acquired during routine clinical practice, before doing a confirmatory PET-scan to these selected individuals only. This method leads to an increased number of recruitments and to a reduced number of PET-scans, resulting in a decrease in overall recruitment costs. We validate our method on three different cohorts, and consider five different classification algorithms for the pre-screening phase. We show that the best results are obtained using solely cognitive, genetic and socio-demographic features, as the slight increased performance when using MRI or longitudinal data is balanced by the cost increase they induce. We show that the proposed method generalizes well when tested on an independent cohort, and that the characteristics of the selected set of individuals are identical to the characteristics of a population selected in a standard way. The proposed approach shows how Machine Learning can be used effectively in practice to optimize recruitment costs in clinical trials.