Anomaly Scores Research Articles

Identifying geochemical anomalies associated with tungsten polymetallic mineralization using geographical detector and unsupervised machine learning methods: Application to the Nanling metallogenic belt, China

The identification of geochemical associations and anomalies related to mineralization is a critical aspect of mineral exploration. Conventional quantitative methods for determining these associations primarily involve correlating various geochemical elements with ore-forming elements and mineral deposits. However, these approaches often face challenges in elucidating the complex interrelationships among geochemical elements and are less effective in regions without known mineral deposits. The geographical detector has emerged as a powerful tool for detecting spatial heterogeneity and identifying key driving factors in mineralization processes. Since geochemical elements are regional variables characterized by spatial heterogeneity, the geographical detector is particularly suited for analyzing interactions among these elements. Additionally, unsupervised machine learning algorithms have proven adept at managing complex interrelations among geochemical elements and extracting deeper insights into mineralization patterns. Despite their advantages, these algorithms carry inherent systematic errors, which introduce uncertainties when relying on a single method, thereby increasing exploration risks. This study applies the geographical detector to the Nanling metallogenic belt, one of the most significant tungsten (W) polymetallic metallogenic belt in South China, to investigate the complex relationships between the ore-forming element W and other geochemical elements, as well as to identify associations pertinent to W polymetallic mineralization. Furthermore, 3 widely used unsupervised learning algorithms, including one-class support vector machines (OCSVM), isolation forest (IF), and deep auto-encoder neural networks (DAE), are employed to detect geochemical anomalies. A model averaging strategy is implemented to calculate the average and standard deviation of geochemical anomaly scores, providing robust anomaly predictions and the quantifying uncertainties associated with systematic errors across different algorithms. The enhanced prediction-area (P-A) plot is used to further assess these anomalies and their uncertainties. Key results include: (1) Geochemical elements such as Sn, Mo, Ag, and Bi have the largest impact on the enrichment of W, followed by Cu, Pb, and Be, with these elements often found in co-occurring or associated minerals linked to W polymetallic mineralization. Additional elements, including Nb, Th, Al2O3, U, As, F, Y, Cd, and Li, also contribute to W enrichment, reflecting the geochemical characteristics of plutons associated with W polymetallic deposits; (2) Element interactions are complex, with most showing nonlinear enhancement effects on W enrichment, which is critical for large-scale W mineralization in the region; (3) Among the machine learning algorithms, IF and OCSVM demonstrate superior and relatively stable performance, whereas DAE exhibits more scattered and disorganized anomaly detection, possibly due to limitation in the pixel-based anomaly recognition; (4) 6 prospective areas for mineral exploration have been identified based on geochemical anomaly scores and their associated uncertainties. This study not only introduces a novel methodology for quantitatively analyzing the complex relationships among geochemical elements, selecting relavant geochemical associations, and elucidating key geological processes related to mineralization. It also provides valuable insights for mineral exploration in the Nanling metallogenic belt.

Corruption-Based Anomaly Detection and Interpretation in Tabular Data

Recent advances in self-supervised learning (SSL) have proven crucial in effectively learning representations of unstructured data, encompassing text, images, and audio. Although the applications of these advances in anomaly detection have been explored extensively, applying SSL to tabular data presents challenges because of the absence of prior information on data structure. In response, we propose a framework for anomaly detection in tabular datasets using variable corruption. Through selective variable corruption and assignment of new labels based on the degree of corruption, our framework can effectively distinguish between normal and abnormal data. Furthermore, analyzing the impact of corruption on anomaly scores aids in the identification of important variables. Experimental results obtained from various tabular datasets validate the precision and applicability of the proposed method. The source code can be accessed at https://github.com/mokch/CAIT.

Anomaly detection scheme for lung CT images using vector quantized variational auto-encoder with support vector data description.

This study aims to develop an anomaly-detection scheme for lesions in CT images. Our database consists of lung CT images obtained from 1500 examinees. It includes 1200 normal and 300 abnormal cases. In this study, SVDD (Support Vector Data Description) mapping the normal latent variables into a hypersphere as small as possible on the latent space is introduced to VQ-VAE (Vector Quantized-Variational Auto-Encoder). VQ-VAE with SVDD is constructed from two encoders, two decoders, and an embedding space. The first encoder compresses the input image into the latent-variable map, whereas the second encoder maps the normal latent variables into a hypersphere as small as possible. The first decoder then up-samples the mapped latent variables into a latent-variable map with the original size. The second decoder finally reconstructs the input image from the latent-variable map replaced by the embedding representations. The data of each examinee is classified as abnormal or normal based on the anomaly score defined as the combination of the difference between the input image and the reconstructed image and the distance between the latent variables and the center of the hypersphere. The area under the ROC curve for VQ-VAE with SVDD was 0.76, showing an improvement when compared with the conventional VAE (0.63, p < .001). VQ-VAE with SVDD developed in this study can yield higher anomaly-detection accuracy than the conventional VAE. The proposed method is expected to be useful for identifying examinees with lesions and reducing interpretation time in CT screening.

Isolation Forest Anomaly Detection Algorithm Based On Multi-level Sub-subspace Partition

In the research of credit loan fraud detection, the isolation forest algorithm has attracted much attention because of its ability to efficiently process large-scale data sets. However, when facing high-dimensional data, the performance of the isolation forest algorithm is easily affected, resulting in deviation of the detection results. In order to solve the above problems, this paper proposes an isolation forest anomaly detection algorithm based on multi-level sub-subspace division. Firstly, the random forest algorithm is used to evaluate the importance of each feature, and the data is divided into different subspaces according to the importance of each feature, and the corresponding weight is assigned to each subspace. Then, the isolation forest algorithm is applied in each subspace for anomaly detection, and the anomaly score of each subspace is obtained. Finally, the anomaly score and weight of each subspace were combined to obtain the final anomaly detection score. In order to evaluate the effectiveness of the algorithm, the proposed algorithm was compared with other four algorithms on the credit loan fraud data set. The results show that the AUC index, accuracy, recall rate and F1 score of the proposed algorithm are higher than those of the comparison algorithms, showing high effectiveness.

Granular computing-based time series anomaly pattern detection with semantic interpretation

Time series analysis may suffer from the “curse of dimensionality” due to its high-dimensionality characteristics. In terms of this issue, information granulation offers an effective vehicle to process time series at a higher level of abstraction. To take this advantage, this study conducts an interpretable time series anomaly pattern detection under the framework of granular computing, where each time series is granulated into a series of semantics according to its patterns and the anomaly ones are identified based on the obtained semantics. First, the time series is partitioned into a predefined number of segments and trend-based information granules are formed for the data points in each time interval. Guided by the principle of justifiable granularity, the granular results maintaining the main features of the original time series realize informative feature extraction and meaningful dimensionality reduction. Then, to realize semantic anomaly pattern detection, the Axiomatic Fuzzy Set (AFS) theory is generalized to construct and compute with semantic time series, and an AFS-based anomaly score is proposed to discover anomaly patterns. In the experiments, the proposed method is conducted on both UCR data sets and real-world time series, where the detected anomaly patterns are equipped with well-defined semantics.

Hybrid Open-Set Segmentation With Synthetic Negative Data.

Open-set segmentation can be conceived by complementing closed-set classification with anomaly detection. Many of the existing dense anomaly detectors operate through generative modelling of regular data or by discriminating with respect to negative data. These two approaches optimize different objectives and therefore exhibit different failure modes. Consequently, we propose a novel anomaly score that fuses generative and discriminative cues. Our score can be implemented by upgrading any closed-set segmentation model with dense estimates of dataset posterior and unnormalized data likelihood. The resulting dense hybrid open-set models require negative training images that can be sampled from an auxiliary negative dataset, from a jointly trained generative model, or from a mixture of both sources. We evaluate our contributions on benchmarks for dense anomaly detection and open-set segmentation. The experiments reveal strong open-set performance in spite of negligible computational overhead.

Enhancing Unsupervised Anomaly Detection With Score-Guided Network.

Anomaly detection plays a crucial role in various real-world applications, including healthcare and finance systems. Owing to the limited number of anomaly labels in these complex systems, unsupervised anomaly detection methods have attracted great attention in recent years. Two major challenges faced by the existing unsupervised methods are as follows: 1) distinguishing between normal and abnormal data when they are highly mixed together and 2) defining an effective metric to maximize the gap between normal and abnormal data in a hypothesis space, which is built by a representation learner. To that end, this work proposes a novel scoring network with a score-guided regularization to learn and enlarge the anomaly score disparities between normal and abnormal data, enhancing the capability of anomaly detection. With such score-guided strategy, the representation learner can gradually learn more informative representation during the model training stage, especially for the samples in the transition field. Moreover, the scoring network can be incorporated into most of the deep unsupervised representation learning (URL)-based anomaly detection models and enhances them as a plug-in component. We next integrate the scoring network into an autoencoder (AE) and four state-of-the-art models to demonstrate the effectiveness and transferability of the design. These score-guided models are collectively called SG-Models. Extensive experiments on both synthetic and real-world datasets confirm the state-of-the-art performance of SG-Models.

Prevalence of and Risk Factors for Hearing Impairment in Craniofacial Microsomia

BackgroundWhile ear anomalies and hearing impairment are common in patients with craniofacial microsomia (CFM), their prevalence, characteristics, and relationship to speech-language development remain unclear. PurposeThis study analyzed the prevalence and risk factors for hearing impairment in patients with CFM. Study Design, Setting, SampleThis retrospective cohort study included patients with unilateral or bilateral CFM from a single center between January 1980 and July 2023 who had evidence of a hearing assessment at <18 years. Exclusion criteria were inconclusive CFM diagnosis by clinical examination and/or radiographs or incomplete medical records. Predictor VariablesThe predictor variables included presence or absence of cleft lip and/or palate, laterality of CFM, and external ear and mandibular anomaly scores measured using the Orbit, Mandible, Ear, Nerve, and Soft Tissue (OMENS) and Pruzansky-Kaban classifications. Main Outcome VariablesPrimary outcome variable was hearing impairment, measured through air and bone conduction audiometry and categorized by type, severity, and side. Secondary outcome variable was speech-language delay, evaluated through assessments of expressive and receptive language skills, vocabulary, speech intelligibility, general articulation, and phonological speech. CovariatesThe covariates included sex and age at first hearing assessment. AnalysesLogistic regression models were used to analyze the effect of predictors on outcomes. P-value <0.05 was considered significant. ResultsThe sample included 213 patients (61.5% male). Hearing assessments were performed at a mean age of 4.6 ± 4.8 years. Hearing impairment was found in 183 (85.9%) and was predominantly conductive (n=130, 91.5%). Of subjects with hearing impairment, 158 (86.3%) had external ear anomalies (P<0.001). In patients with unilateral CFM, 38 (21.8%) had bilateral hearing loss and 9 (5.2%) had contralateral-only hearing loss. Both M3 and E3 scores were associated with the presence and severity of hearing loss (P=0.01 and P<0.001, respectively). There was no significant association between hearing impairment and speech-language development (P>0.05). Conclusion and RelevanceAlthough the severity of mandibular and external ear anomalies was significantly associated with the prevalence and severity of hearing loss, clinicians should remain alert for concomitant or isolated contralateral hearing loss, given the high prevalence of hearing loss in ears without ipsilateral facial involvement or external abnormalities.

Anomaly detection via Gumbel Noise Score Matching.

We propose Gumbel Noise Score Matching (GNSM), a novel unsupervised method to detect anomalies in categorical data. GNSM accomplishes this by estimating the scores, i.e., the gradients of log likelihoods w.r.t. inputs, of continuously relaxed categorical distributions. We test our method on a suite of anomaly detection tabular datasets. GNSM achieves a consistently high performance across all experiments. We further demonstrate the flexibility of GNSM by applying it to image data where the model is tasked to detect poor segmentation predictions. Images ranked anomalous by GNSM show clear segmentation failures, with the anomaly scores strongly correlating with segmentation metrics computed on ground-truth. We outline the score matching training objective utilized by GNSM and provide an open-source implementation of our work.

An autoencoder model based on one-dimensional neural network for epileptic EEG anomaly detection

We propose an autoencoder model based on a one-dimensional convolutional neural network (1DCNN) as the feature extraction network for efficient detection of epileptic EEG anomalies. The local information of normal EEG signals was captured by utilizing the local feature extraction ability of 1DCNN for training of an autoencoder to learn the expression of normal EEG data in low dimensional feature space. With the difference between the input and output as the anomaly score, the threshold was determined by the optimal equilibrium point of the ROC curve, and the EEG signals exceeding the threshold were diagnosed as the seizure data. The performance of the 1DCNN-AE epilepsy detection model was evaluated using the publicly available CHB-MIT scalp EEG dataset and TUH scalp EEG dataset. The AUC of the 1DCNN-AE model reached 0.890 of CHB-MIT and 0.686 of TUH under the average level of patients, and the epilepsy detection rate reached 0.974 and 0.893, and these results were better than the latest epilepsy anomaly detection models LSTM-VAE and GRU-VAE. The 1DCNN model had a parameter quantity of 58.5M, which was at the same level with LSTM-VAE (47.4 M) and GRU-VAE (36.9 M) but with much smaller FLOPs (0.377 G) than LSTM-VAE (21.6 G) and GRU-VAE (16.2 G). The autoencoder model based one-dimensional convolutional neural network can effectively detect abnormal EEG signals in epileptic seizure.

Investigation of a surrogate measure-based safety index for predicting injury crashes at signalized intersections

Objectives The paper develops a machine learning-based safety index for classifying traffic conflicts that can be used to estimate the frequency of signalized intersection crashes, with a focus on the more severe ones that result in fatal and severe injury. The number of conflicts in different severity levels categorized by the safety index is used as an explanatory variable for developing statistical models for pro-actively estimating crashes. Methods Video-derived conflicts in different severity levels between left-turning vehicles and opposing through vehicles, a well-recognized severe injury crash typology at signalized intersections, were identified by jointly integrating the indicators of frequency and severity, using an autoencoder neural network integration method to develop anomaly scores. Regression models were then developed to relate crashes at the same intersections to the classified conflicts based on the value of their safety indexes. Cumulative Residual plots were investigated. Finally, equations defining the boundary between consecutive anomaly score levels were developed to facilitate application in practice. Results Regression models for total and fatal plus severe (FSI) crashes utilizing classified extreme conflicts based on anomaly scores were found to outperform the models using total conflicts. The improvement is more pronounced for FSI crashes. The results also suggest that the machine learning integration method can efficiently classify conflicts accurately according to crash severity levels since the higher anomaly score is associated with a higher crash severity level (i.e., FSI). Conclusions The proposed framework represents a methodological advancement in traffic conflict-based estimation of crashes using a machine learning model to classify conflicts by their anomaly scores. For jurisdictions without the resources to develop such a model to classify conflicts for their own datasets, the simple equations defining the boundary between consecutive anomaly score levels could be used as an approximation.

Fuzzy anomaly scores for Isolation Forest

The detection of anomalies in data presents a significant challenge in various applications. The Isolation Forest (IF) has gained attention due to its notable performance features, including high accuracy, efficiency, simplicity, and rapid computation. However, prior research has primarily concentrated on the constructing isolation trees (iTrees), overlooking the considerable influence of anomaly scoring methods on anomaly detection performance. This study introduces an innovative anomaly scoring method that integrates fuzzy concepts to enhance detection performance. Fuzzy concepts adeptly manage ambiguity and uncertainty, making them more readily applicable in anomaly scoring than in iTree training. Unlike conventional methods that assign a sample to a single child node in the decision path, the proposed fuzzy anomaly scoring method allows samples to be assigned to all child nodes with varying membership degrees based on the target sample. Consequently, this method aggregates the path lengths of all external nodes in a weighted manner, minimizing the impact of irrelevant splits on anomaly scores. Considering that even IF algorithms using informative splits select splits based on data distribution rather than label information, introducing fuzziness to the splits themselves can effectively mitigate performance degradation caused by irrelevant splits. Extensive experiments on 25 benchmark datasets demonstrated that the proposed anomaly scoring method significantly improved both the performance and stability of anomaly detection with the base IF algorithm, outperforming other IF algorithms and fuzzy rough set-based anomaly detection methods.

Delving into CLIP latent space for Video Anomaly Recognition

We tackle the complex problem of detecting and recognising anomalies in surveillance videos at the frame level, utilising only video-level supervision. We introduce the novel method AnomalyCLIP, the first to combine Vision and Language Models (VLMs), such as CLIP, with multiple instance learning for joint video anomaly detection and classification. Our approach specifically involves manipulating the latent CLIP feature space to identify the normal event subspace, which in turn allows us to effectively learn text-driven directions for abnormal events. When anomalous frames are projected onto these directions, they exhibit a large feature magnitude if they belong to a particular class. We also leverage a computationally efficient Transformer architecture to model short- and long-term temporal dependencies between frames, ultimately producing the final anomaly score and class prediction probabilities. We compare AnomalyCLIP against state-of-the-art methods considering three major anomaly detection benchmarks, i.e. ShanghaiTech, UCF-Crime, and XD-Violence, and empirically show that it outperforms baselines in recognising video anomalies. Project website and code are available at https://lucazanella.github.io/AnomalyCLIP/.

Enhancing cervical cancer cytology screening via artificial intelligence innovation

A double-check process helps prevent errors and ensures quality control. However, it may lead to decreased personal accountability, reduced effort, and declining quality checks. Introducing an artificial intelligence (AI)-based system in such scenarios could effectively address the risk of oversights. This study introduces an innovative AI-integrated workflow for cervical cytology screening that substantially improves efficiency and reduces the burden on cytologists. The AI model prioritizes cases for review based on anomaly scores and streamlines the first screening process to approximately 10 s per case. The model enhances the identification of high-risk cases via detailed microscopic observation, high anomaly scores cases, and a targeted review of low-score cases. The workflow highlights its capability for rapid, accurate, and less labor-intensive evaluations, demonstrating the potential to transform cervical cancer screening. This study highlights the importance of AI in modern medical diagnostics, particularly in areas with a high demand for accuracy and efficiency.

Multi-Channel Multi-Scale Convolution Attention Variational Autoencoder (MCA-VAE): An Interpretable Anomaly Detection Algorithm Based on Variational Autoencoder.

With the rapid development of industry, the risks factories face are increasing. Therefore, the anomaly detection algorithms deployed in factories need to have high accuracy, and they need to be able to promptly discover and locate the specific equipment causing the anomaly to restore the regular operation of the abnormal equipment. However, the neural network models currently deployed in factories cannot effectively capture both temporal features within dimensions and relationship features between dimensions; some algorithms that consider both types of features lack interpretability. Therefore, we propose a high-precision, interpretable anomaly detection algorithm based on variational autoencoder (VAE). We use a multi-scale local weight-sharing convolutional neural network structure to fully extract the temporal features within each dimension of the multi-dimensional time series. Then, we model the features from various aspects through multiple attention heads, extracting the relationship features between dimensions. We map the attention output results to the latent space distribution of the VAE and propose an optimization method to improve the reconstruction performance of the VAE, detecting anomalies through reconstruction errors. Regarding anomaly interpretability, we utilize the VAE probability distribution characteristics, decompose the obtained joint probability density into conditional probabilities on each dimension, and calculate the anomaly score, which provides helpful value for technicians. Experimental results show that our algorithm performed best in terms of F1 score and AUC value. The AUC value for anomaly detection is 0.982, and the F1 score is 0.905, which is 4% higher than the best-performing baseline algorithm, Transformer with a Discriminator for Anomaly Detection (TDAD). It also provides accurate anomaly interpretation capability.

Collaborative representation based unsupervised CNN for hyperspectral anomaly detection

The convolutional neural networks (CNNs) have shown high success in supervised analysis of hyperspectral images. But, the use of a supervised CNN is not possible for an unsupervised task such as hyperspectral anomaly detection. So, an unsupervised CNN with pre-determined convolutional kernels without requirement to labeled samples or training process is proposed in this work. The proposed method uses the collaborative representation (CR) for background estimate and introduces the global preserving projection (GPP) for dimensionality reduction of it. Then, the convolutional kernels are randomly selected from the reduced CR data. Moreover, two distances in inner and guard windows are defined, which difference of them results in the anomaly score. The CR based unsupervised CNN (CUCNN) method achieves high detection accuracy compared to its counterparts and is more than 9 times faster than other presented unsupervised CNN detectors.

Event-driven weakly supervised video anomaly detection

Inspired by the observations of human working manners, this work proposes an event-driven method for weakly supervised video anomaly detection. Complementary to the conventional snippet-level anomaly detection, this work designs an event analysis module to predict the event-level anomaly scores as well. It first generates event proposals simply via a temporal sliding window and then constructs a cascaded causal transformer to capture temporal dependencies for potential events of varying durations. Moreover, a dual-memory augmented self-attention scheme is also designed to capture global semantic dependencies for event feature enhancement. The network is learned with a standard multiple instance learning (MIL) loss, together with normal-abnormal contrastive learning losses. During inference, the snippet- and event-level anomaly scores are fused for anomaly detection. Experiments show that the event-level analysis helps to detect anomalous events more continuously and precisely. The performance of the proposed method on three public datasets demonstrates that the proposed approach is competitive with state-of-the-art methods.

Evaluation of cosmetic outcomes in breast reconstruction patients undergoing radiotherapy using an anomaly generative adversarial network model

Considering the rising prevalence of breast reconstruction followed by radiotherapy (RT), evaluating the cosmetic impact of RT is crucial. Currently, there are limited tools for objectively assessing cosmetic outcomes in patients who have undergone reconstruction. Therefore, we validated the cosmetic outcome using a previously developed anomaly Generative Adversarial Network (GAN)-based model and evaluated its utility. Between January 2016 and December 2020, we collected computed tomography (CT) images from 82 breast cancer patients who underwent immediate reconstruction surgery followed by radiotherapy. Among these patients, 38 received immediate implant insertion, while 44 underwent autologous breast reconstruction. Anomaly scores (AS) were estimated using an anomaly GAN model at pre-RT, 1st follow-up, 1-year (Post-1Y) and 2-year (Post-2Y) after RT. Subsequently, the scores were analyzed in a time-series manner, considering reconstruction types (implant versus autologous), RT techniques, and the incidence of major complications. The median age of the patients was 46 years (range 29–62). The AS between Post-1Y and Post-2Y demonstrated a positive relationship (coefficient 0.515, P < 0.001). The AS was significantly associated with objective cosmetic indices, namely Breast Contour Difference (P = 0.009) and Breast Area Difference (P = 0.004), at both Post-1Y and Post-2Y. Subgroup analysis stratified by type of breast reconstruction revealed significantly higher AS values in patients who underwent prosthetic implant insertion compared to those with autologous reconstruction at all follow-up time points (1st follow-up, P = 0.001; Post-1Y, P < 0.001; and Post-2Y, P < 0.001). A threshold AS of ≥ 1.9 was associated with a 10% predicted risk of developing major complications. The feasibility of an AS generated by a GAN model for predicting both cosmetic outcomes and the likelihood of complications following RT has been successfully validated. Further investigation involving a larger patient cohort is warranted.

Integrating adversarial training strategies into deep autoencoders: A novel aeroengine anomaly detection framework

The anomaly detection of aeroengines faces significant challenges, including high noise, complex parameter correlations, and imbalanced data. Current methods primarily rely on the reconstruction error of autoencoders to isolate anomalies. However, such methods are ineffective in detecting minor anomalies, as the reconstruction error for minor anomaly samples closely resembles that of normal samples. To address this problem, this paper proposes an innovative Deep Autoencoder Anomaly Detection Model (DAADM) for the anomaly detection of aeroengines. DAADM consists of two sub-networks: Anomaly Score Calculation Network (ASCN) and Deep Feature Extraction Network (DFEN). Firstly, ASCN introduces the adversarial training strategy into deep autoencoders, ensuring training stability while effectively isolating minor anomalies. Secondly, DFEN extracts deep-level features from input samples, providing a different perspective from ASCN to enhance sample information extraction. The combination of ASCN and DFEN compensates for their respective deficiencies, comprehensively considering input sample information, thereby promoting the capability of anomaly detection. Finally, the proposed DAADM is validated on real an aeroengine dataset and a public dataset. On the aeroengine dataset, the accuracy, recall, and F1 score of DAADM exceed the state-of-the-art method by 4.73%, 4.79%, and 5.76%, respectively. It is noteworthy that experimental results have proven that DAADM has strong anti-noise capabilities.

Quantifying impairment and disease severity using AI models trained on healthy subjects

Automatic assessment of impairment and disease severity is a key challenge in data-driven medicine. We propose a framework to address this challenge, which leverages AI models trained exclusively on healthy individuals. The COnfidence-Based chaRacterization of Anomalies (COBRA) score exploits the decrease in confidence of these models when presented with impaired or diseased patients to quantify their deviation from the healthy population. We applied the COBRA score to address a key limitation of current clinical evaluation of upper-body impairment in stroke patients. The gold-standard Fugl-Meyer Assessment (FMA) requires in-person administration by a trained assessor for 30-45 minutes, which restricts monitoring frequency and precludes physicians from adapting rehabilitation protocols to the progress of each patient. The COBRA score, computed automatically in under one minute, is shown to be strongly correlated with the FMA on an independent test cohort for two different data modalities: wearable sensors (ρ = 0.814, 95% CI [0.700,0.888]) and video (ρ = 0.736, 95% C.I [0.584, 0.838]). To demonstrate the generalizability of the approach to other conditions, the COBRA score was also applied to quantify severity of knee osteoarthritis from magnetic-resonance imaging scans, again achieving significant correlation with an independent clinical assessment (ρ = 0.644, 95% C.I [0.585,0.696]).