Generalizable Model Research Articles

Mapping the Landscape: A Review of Digital Health Models for Equitable Access to Universal Health Coverage

Digital health is the appropriate application of technology to enhance the health sector. With Universal Health Coverage (UHC), insufficient money is not a major hindrance to receiving the full range of high-quality healthcare services if and when needed. Strategies, models, and frameworks continue to be formulated to guide operations, as well as in the regulation of healthcare. This study provides a thorough analysis of digital health models for equitable access to UHC by highlighting key factors of these models while identifying and analyzing knowledge gaps. Considering UHC and the aspect of inclusivity as espoused in the Sustainable Development Goal 3 (SDG3), which speaks of health for all in a population, this study explores models that cover a general population and were designed with equity as a key component. The study methodology is a scoping review that uses a manual search of digital libraries and repositories, employing tailored search terms. From the results, though models exist that address equity, more work is required to formulate generalizable digital health models for equitable access to UHC, and majorly for developing economies. Moreover, it is a call to consistently adapt models that meet the target needs of a population at any given time.

Racial and ethnic socioenvironmental inequity and neuroimaging in psychiatry: a brief review of the past and recommendations for the future.

Neuroimaging is a major tool that holds immense translational potential for understanding psychiatric disorder phenomenology and treatment. However, although epidemiological and social research highlights the many ways inequity and representativeness influences mental health, there is a lack of consideration of how such issues may impact neuroimaging features in psychiatric research. More specifically, the potential extent to which racialized inequities may affect underlying neurobiology and impact the generalizability of neural models of disorders is unclear. The present review synthesizes research focused on understanding the potential consequences of racial/ethnic inequities relevant to neuroimaging in psychiatry. We first discuss historical and contemporary drivers of inequities that persist today. We then discuss the neurobiological consequences of these inequities as revealed through current research, and note emergent research demonstrating the impact such inequities have on our ability to use neuroimaging to understand psychiatric disease. We end with a set of recommendations and practices to move the field towards more equitable approaches that will advance our abilities to develop truly generalizable neurobiological models of psychiatric disorders.

Population-level normative models reveal race- and socioeconomic-related variability in cortical thickness of threat neurocircuitry

The inequitable distribution of economic resources and exposure to adversity between racial groups contributes to mental health disparities within the United States. Consideration of the potential neurodevelopmental consequences, however, has been limited particularly for neurocircuitry known to regulate the emotional response to threat. Characterizing the consequences of inequity on threat neurocircuitry is critical for robust and generalizable neurobiological models of psychiatric illness. Here we use data from the Adolescent Brain and Cognitive Development Study 4.0 release to investigate the contributions of individual and neighborhood-level economic resources and exposure to discrimination. We investigate the potential appearance of race-related differences using both standard methods and through population-level normative modeling. We show that, in a sample of white and Black adolescents, racial inequities in socioeconomic factors largely contribute to the appearance of race-related differences in cortical thickness of threat neurocircuitry. The race-related differences are preserved through the use of population-level models and such models also preserve associations between cortical thickness and specific socioeconomic factors. The present findings highlight that such socioeconomic inequities largely underlie race-related differences in brain morphology. The present findings provide important new insight for the generation of generalizable neurobiological models of psychiatric illness.

Deep learning survival model predicts outcome after intracerebral hemorrhage from initial CT scan.

Predicting functional impairment after intracerebral hemorrhage (ICH) provides valuable information for planning of patient care and rehabilitation strategies. Current prognostic tools are limited in making long term predictions and require multiple expert-defined inputs and interpretation that make their clinical implementation challenging. This study aimed to predict long term functional impairment of ICH patients from admission non-contrast CT scans, leveraging deep learning models in a survival analysis framework. We used the admission non-contrast CT scans from 882 patients from the Massachusetts General Hospital ICH Study for training, hyperparameter optimization, and model selection, and 146 patients from the Yale New Haven ICH Study for external validation of a deep learning model predicting functional outcome. Disability (modified Rankin scale [mRS] > 2), severe disability (mRS > 4), and dependent living status were assessed via telephone interviews after 6, 12, and 24 months. The prediction methods were evaluated by the c-index and compared with ICH score and FUNC score. Using non-contrast CT, our deep learning model achieved higher prediction accuracy of post-ICH dependent living, disability, and severe disability by 6, 12, and 24 months (c-index 0.742 [95% CI -0.700 to 0.778], 0.712 [95% CI -0.674 to 0.752], 0.779 [95% CI -0.733 to 0.832] respectively) compared with the ICH score (c-index 0.673 [95% CI -0.662 to 0.688], 0.647 [95% CI -0.637 to 0.661] and 0.697 [95% CI -0.675 to 0.717]) and FUNC score (c-index 0.701 [95% CI- 0.698 to 0.723], 0.668 [95% CI -0.657 to 0.680] and 0.727 [95% CI -0.708 to 0.753]). In the external independent Yale-ICH cohort, similar performance metrics were obtained for disability and severe disability (c-index 0.725 [95% CI -0.673 to 0.781] and 0.747 [95% CI -0.676 to 0.807], respectively). Similar AUC of predicting each outcome at 6 months, 1 and 2 years after ICH was achieved compared with ICH score and FUNC score. We developed a generalizable deep learning model to predict onset of dependent living and disability after ICH, which could help to guide treatment decisions, advise relatives in the acute setting, optimize rehabilitation strategies, and anticipate long-term care needs.

Enhanced Cell Tracking Using A GAN-based Super-Resolution Video-to-Video Time-Lapse Microscopy Generative Model.

Cells are among the most dynamic entities, constantly undergoing various processes such as growth, division, movement, and interaction with other cells as well as the environment. Time-lapse microscopy is central to capturing these dynamic behaviors, providing detailed temporal and spatial information that allows biologists to observe and analyze cellular activities in real-time. The analysis of time-lapse microscopy data relies on two fundamental tasks: cell segmentation and cell tracking. Integrating deep learning into bioimage analysis has revolutionized cell segmentation, producing models with high precision across a wide range of biological images. However, developing generalizable deep-learning models for tracking cells over time remains challenging due to the scarcity of large, diverse annotated datasets of time-lapse movies of cells. To address this bottleneck, we propose a GAN-based time-lapse microscopy generator, termed tGAN, designed to significantly enhance the quality and diversity of synthetic annotated time-lapse microscopy data. Our model features a dual-resolution architecture that adeptly synthesizes both low and high-resolution images, uniquely capturing the intricate dynamics of cellular processes essential for accurate tracking. We demonstrate the performance of tGAN in generating high-quality, realistic, annotated time-lapse videos. Our findings indicate that tGAN decreases dependency on extensive manual annotation to enhance the precision of cell tracking models for time-lapse microscopy.

In-home Gait Abnormality Detection through Footstep-Induced Floor Vibration Sensing and Person-Invariant Contrastive Learning.

Detecting gait abnormalities is crucial for assessing fall risks and early identification of neuromusculoskeletal disorders such as Parkinson's and stroke. Traditional assessments in gait clinics are infrequent and pose barriers, particularly for disadvantaged populations. Previous efforts have explored sensor-based approaches for in-home gait assessments, yet they face limitations such as visual obstructions (cameras), limited coverage (pressure mats), and the need for device carrying (wearables and insoles). To overcome these limitations, we introduce an in-home gait abnormality detection system using footstep-induced floor vibrations, enabling low-cost, non-intrusive, device-free gait health monitoring. The main research challenge is the high uncertainty in floor vibrations due to gait variations among people, making it challenging to develop a generalizable model for new patients. To address this, we analyze time-frequency-domain features of floor vibration data during specific gait phases and develop a feature transformation method through contrastive learning to address the between-people gait variation challenge. Our method transforms the features from vibrations to an embedding space where samples from different people stay close to each other (robust to people variation) while normal and abnormal gait samples are far apart (sensitive to gait abnormality). After that, gait abnormalities are detected by a downstream classifier after feature transformation. We evaluated our approach through a real-world walking experiment with 21 participants and achieved an 85% to 95% mean accuracy in detecting various gait abnormalities. This novel method overcomes prior limitations in in-home gait assessments, offering accessible gait abnormality detection without the need for intrusive devices or labels for new patients.

Application of machine learning in a rodent malaria model for rapid, accurate, and consistent parasite counts.

Rodent malaria models serve as important preclinical antimalarial and vaccine testing tools. Evaluating treatment outcomes in these models often requires manually counting parasite-infected red blood cells (iRBCs), a time-consuming process, which can be inconsistent between individuals and labs. We have developed an easy-to-use machine learning (ML)-based software, Malaria Screener R, to expedite and standardize such studies by automating the counting of Plasmodium iRBCs in rodents. This software can process Giemsa-stained blood smear images captured by any camera-equipped microscope. It features an intuitive graphical user interface that facilitates image processing and visualization of the results. The software has been developed as a desktop application that processes images on standard Windows and Mac OS computers. A previous ML model created by the authors designed to count P. falciparum -infected human RBCs did not perform well counting Plasmodium -infected mouse RBCs. We leveraged that model by loading the pre-trained weights and training the algorithm with newly collected data to target P. yoelii and P. berghei mouse iRBCs. This new model reliably measured both P. yoelii and P. berghei parasitemia (R 2 = 0.9916). Additional rounds of training data to incorporate variances due to length of Giemsa staining, microscopes etc, have produced a generalizable model, meeting WHO Competency Level 1 for the sub-category of parasite counting using independent microscopes. Reliable, automated analyses of blood-stage parasitemia will facilitate rapid and consistent evaluation of novel vaccines and antimalarials across labs in an easily accessible in vivo malaria model.

Accurate and generalizable soil liquefaction prediction model based on the CatBoost algorithm

Accurate and generalizable soil liquefaction prediction model based on the CatBoost algorithm

MTJNet: Multi-task joint learning network for advancing medicinal plant and leaf classification

Identifying and classifying medicinal plants is crucial for pharmaceutical research, traditional medicine, and biodiversity conservation. However, manual classification is time-consuming, error-prone, and requires expert knowledge. This problem statement highlights the need for an automated, efficient, and accurate method by which to distinguish between different species and ensure the quality and safety of medicinal plant leaves. The state-of-the-art methods employ only leaf or plant images for the classification; however, these methods work in particular scenarios (only leaf or plant). In this study, we first integrate the dataset of medicinal plants with corresponding leaves to develop a generalizable model and then apply pre-processing techniques (using vein morphometric features and Sobel edge detection) to highlight the significant characteristics in the images. Then, we propose a novel multi-task joint learning network (MTJNet) for classifying medicinal plant leaves. The proposed MTJNet includes local and global feature extractors that retrieve prominent features for robust classification. Further, we blend the features extracted from the local and global networks to enhance the contextual features. Last, we assign the embedded features to dense layers for additional feature extraction and classification. To evaluate the proposed MTJNet, we employ an Indian medicinal leaf dataset and achieve a precision of 99.60%, a recall of 99.62%, an accuracy of 99.71%, and an F1 score of 99.58%. The experimental results show that the MTJNet statistically defeats prevalent models, thereby proving its effectiveness for medical and industrial applications.

Triplet Adaptation Framework for Robust Semi-Supervised Learning.

Semi-supervised learning (SSL) suffers from severe performance degradation when labeled and unlabeled data come from inconsistent and imbalanced distribution. Nonetheless, there is a lack of theoretical guidance regarding a remedy for this issue. To bridge the gap between theoretical insights and practical solutions, we embark to an analysis of generalization bound of classic SSL algorithms. This analysis reveals that distribution inconsistency between unlabeled and labeled data can cause a significant generalization error bound. Motivated by this theoretical insight, we present a Triplet Adaptation Framework (TAF) to reduce the distribution divergence and improve the generalization of SSL models. TAF comprises three adapters: Balanced Residual Adapter, aiming to map the class distribution of labeled and unlabeled data to a uniform distribution for reducing class distribution divergence; Representation Adapter, aiming to map the representation distribution of unlabeled data to labeled one for reducing representation distribution divergence; and Pseudo-Label Adapter, aiming to align the predicted pseudo-labels with the class distribution of unlabeled data, thereby preventing erroneous pseudo-labels from exacerbating representation divergence. These three adapters collaborate synergistically to reduce the generalization bound, ultimately achieving a more robust and generalizable SSL model. Extensive experiments across various robust SSL scenarios validate the efficacy of our method.

BAMFORESTS: Bamberg Benchmark Forest Dataset of Individual Tree Crowns in Very-High-Resolution UAV Images

The anthropogenic climate crisis results in the gradual loss of tree species in locations where they were previously able to grow. This leads to increasing workloads and requirements for foresters and arborists as they are forced to restructure their forests and city parks. The advancements in computer vision (CV)—especially in supervised deep learning (DL)—can help cope with these new tasks. However, they rely on large, carefully annotated datasets to produce good and generalizable models. This paper presents BAMFORESTS: a dataset with 27,160 individually delineated tree crowns in 105 ha of very-high-resolution UAV imagery gathered with two different sensors from two drones. BAMFORESTS covers four areas of coniferous, mixed, and deciduous forests and city parks. The labels contain instance segmentations of individual trees, and the proposed splits are balanced by tree species and vitality. Furthermore, the dataset contains the corrected digital surface model (DSM), representing tree heights. BAMFORESTS is annotated in the COCO format and is especially suited for training deep neural networks (DNNs) to solve instance segmentation tasks. BAMFORESTS was created in the BaKIM project and is freely available under the CC BY 4.0 license.

Stratifying Risk for Postpartum Depression at Time of Hospital Discharge.

Postpartum depression (PPD) represents a major contributor to postpartum morbidity and mortality. Beyond efforts at routine screening, risk stratification models could enable more targeted interventions in settings with limited resources. Thus, we aimed to develop and estimate the performance of a generalizable risk stratification model for PPD in patients without a history of depression using information collected as part of routine clinical care. We performed a retrospective cohort study of all individuals who delivered between 2017 and 2022 in one of two large academic medical centers and six community hospitals. An elastic net model was constructed and externally validated to predict PPD using sociodemographic factors, medical history, and prenatal depression screening information, all of which was known before discharge from the delivery hospitalization. The cohort included 29,168 individuals; 2,703 (9.3%) met at least one criterion for postpartum depression in the 6 months following delivery. In the external validation data, the model had good discrimination and remained well-calibrated: area under the receiver operating characteristic curve 0.721 (95% CI: 0.707-0.734), Brier calibration score 0.088 (95% CI: 0.084 - 0.092). At a specificity of 90%, the positive predictive value was 28.0% (95% CI: 26.0-30.1%), and the negative predictive value was 92.2% (95% CI: 91.8-92.7%). These findings demonstrate that a simple machine-learning model can be used to stratify the risk for PPD before delivery hospitalization discharge. This tool could help identify patients within a practice at the highest risk and facilitate individualized postpartum care planning regarding the prevention of, screening for, and management of PPD at the start of the postpartum period and potentially the onset of symptoms.

Using the Buckingham π Theorem for Multi-System Transfer Learning: A Case-Study with 3 Vehicles Sharing a Database

Many advanced driver assistance schemes or autonomous vehicle controllers are based on a motion model of the vehicle behavior, i.e., a function predicting how the vehicle will react to a given control input. Data-driven models, based on experimental or simulated data, are very useful, especially for vehicles difficult to model analytically, for instance, ground vehicles for which the ground-tire interaction is hard to model from first principles. However, learning schemes are limited by the difficulty of collecting large amounts of experimental data or having to rely on high-fidelity simulations. This paper explores the potential of an approach that uses dimensionless numbers based on Buckingham’s π theorem to improve the efficiency of data for learning models, with the goal of facilitating knowledge sharing between similar systems. A case study using car-like vehicles compares traditional and dimensionless models on simulated and experimental data to validate the benefits of the new dimensionless learning approach. Preliminary results from the case study presented show that this new dimensionless approach could accelerate the learning rate and improve the accuracy of the model prediction when transferring the learned model between various similar vehicles. Prediction accuracy improvements with the dimensionless scheme when using a shared database, that is, predicting the motion of a vehicle based on data from various different vehicles was found to be 480% more accurate for predicting a simple no-slip maneuver based on simulated data and 11% more accurate to predict a highly dynamic braking maneuver based on experimental data. A modified physics-informed learning scheme with hand-crafted dimensionless features was also shown to increase the improvement to precision gains of 917% and 28% respectively. A comparative study also shows that using Buckingham’s π theorem is a much more effective preprocessing step for this task than principal component analysis (PCA) or simply normalizing the data. These results show that the use of dimensionless variables is a promising tool to help in the task of learning a more generalizable motion model for vehicles, and hence potentially taking advantage of the data generated by fleets of vehicles on the road even though they are not identical.

Big data analysis for Covid-19 in hospital information systems.

The COVID-19 pandemic has triggered a global public health crisis, affecting hundreds of countries. With the increasing number of infected cases, developing automated COVID-19 identification tools based on CT images can effectively assist clinical diagnosis and reduce the tedious workload of image interpretation. To expand the dataset for machine learning methods, it is necessary to aggregate cases from different medical systems to learn robust and generalizable models. This paper proposes a novel deep learning joint framework that can effectively handle heterogeneous datasets with distribution discrepancies for accurate COVID-19 identification. We address the cross-site domain shift by redesigning the COVID-Net's network architecture and learning strategy, and independent feature normalization in latent space to improve prediction accuracy and learning efficiency. Additionally, we propose using a contrastive training objective to enhance the domain invariance of semantic embeddings and boost classification performance on each dataset. We develop and evaluate our method with two large-scale public COVID-19 diagnosis datasets containing CT images. Extensive experiments show that our method consistently improves the performance both datasets, outperforming the original COVID-Net trained on each dataset by 13.27% and 15.15% in AUC respectively, also exceeding existing state-of-the-art multi-site learning methods.

Investigating environmentally sustainable consumption: A diary study of home‐based consumption behaviors

AbstractThis study analyzes three environmentally sustainable household consumption behaviors (optimizing the use of domestic water, minimizing food waste, and minimizing plastic packaging usage) through the model of goal‐directed behavior. The findings show that attitudes, subjective norms, perceived behavioral control, anticipated emotions, and habits are all significant predictors of the desire to adopt sustainable consumption behaviors, which directly fosters the intention to adopt these behaviors. Intention–behavior links were unique for each behavior; minimizing plastic packaging usage was the most difficult behavior to implement. This study offers useful insights into people's sustainable consumption goals and their intentions to adopt responsible consumption behaviors. A generalizable model of environmentally sustainable household behaviors that considers the three behaviors simultaneously is presented. This study suggests that business and policy strategies that could successfully promote sustainability in the household might proceed by, for example, empowering consumers or changing their habits.

Shortcut learning in medical AI hinders generalization: method for estimating AI model generalization without external data

Healthcare datasets are becoming larger and more complex, necessitating the development of accurate and generalizable AI models for medical applications. Unstructured datasets, including medical imaging, electrocardiograms, and natural language data, are gaining attention with advancements in deep convolutional neural networks and large language models. However, estimating the generalizability of these models to new healthcare settings without extensive validation on external data remains challenging. In experiments across 13 datasets including X-rays, CTs, ECGs, clinical discharge summaries, and lung auscultation data, our results demonstrate that model performance is frequently overestimated by up to 20% on average due to shortcut learning of hidden data acquisition biases (DAB). Shortcut learning refers to a phenomenon in which an AI model learns to solve a task based on spurious correlations present in the data as opposed to features directly related to the task itself. We propose an open source, bias-corrected external accuracy estimate, PEst, that better estimates external accuracy to within 4% on average by measuring and calibrating for DAB-induced shortcut learning.

Generalized machine learning models to predict significant wave height utilizing wind and atmospheric parameters

Significant wave height (SWH) is a key parameter for wave energy extraction, ship navigation, oil and gas extraction, coastal structure construction, etc. Direct measurements of SWH using buoys are expensive and accurate over a limited area while numerical models are computationally expensive, inaccurate, with limited generalizability. Thus, this work focuses on developing generalizable machine learning models for predicting SWH from wind parameters (speed, direction, and gust) and atmospheric parameters (temperature and pressure). Two deep learning models (Artificial Neural Network (ANN) and Self Normalizing Neural Network (SNN) and two gradient boosting tree-based models (XGBoost and LightGBM) have been used in this study. Three different data sets were collected from the National Data Buoy Center: Data Set-1 (DS1): 12 years of data from 47 stations; Data Set-2 (DS2): 14 months of additional data from 6 stations randomly selected from DS1; Data Set-3 (DS3): 13 years data from completely 6 new stations. DS1 was split into training, testing, and validation datasets. Training and hyper-parameter tuning was done on the train and validation dataset, while the performance of the models was evaluated on the DS1 test dataset, DS2, and DS3, employing three error metrics: Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-square score (R2). The collected data underwent data cleaning, preprocessing, and exploratory data analysis before modeling. The deep learning models have demonstrated superior fitting capacity to the tree-based models, achieving the lowest MSE (0.047), MAE (0.153), and highest R2 score (0.953) on test data. However, the gradient boosting models demonstrate better generalizing capacity than the deep learning models on DS2 and DS3. This study helps further Sustainable Development Goal 7 (SDG 7) by allowing fast and cheap assessment of wave height for ocean energy site development.

For the good of the party, for the good of the nation: ingroup projection can motivate support for political violence

Support for political violence in the United States appears to be growing. We outline a model that positions ingroup projection—seeing ingroup values as the shared values of a larger inclusive societal group—as a key psychological process through which identification with political ingroups (Democrats/Republicans) and with national superordinate categories (Americans) influence support for political violence. We tested this model in two studies. Study 1 (N = 297) included original survey data collected during the 2016 US Presidential election, and analyses revealed that identification with Democrats or Republicans and identification with Americans both had positive indirect effects on support for political violence that were mediated by ingroup projection. Study 2 (N = 642) provided a preregistered replication of these results using original data collected during the 2022 US Midterm Senate elections. These results provide insight into the psychological processes that underlie support for political violence in the United States and elucidate a generalizable model for understanding destructive intergroup behaviors in a variety of real-world intergroup contexts.

Federated 3D multi-organ segmentation with partially labeled and unlabeled data.

This paper considers a new problem setting for multi-organ segmentation based on the following observations. In reality, (1) collecting a large-scale dataset from various institutes is usually impeded due to privacy issues; (2) many images are not labeled since the slice-by-slice annotation is costly; and (3) datasets may exhibit inconsistent, partial annotations across different institutes. Learning a federated model from these distributed, partially labeled, and unlabeled samples is an unexplored problem. To simulate this multi-organ segmentation problem, several distributed clients and a central server are maintained. The central server coordinates with clients to learn a global model using distributed private datasets, which comprise a small part of partially labeled images and a large part of unlabeled images. To address this problem, a practical framework that unifies partially supervised learning (PSL), semi-supervised learning (SSL), and federated learning (FL) paradigms with PSL, SSL, and FL modules is proposed. The PSL module manages to learn from partially labeled samples. The SSL module extracts valuable information from unlabeled data. Besides, the FL module aggregates local information from distributed clients to generate a global statistical model. With the collaboration of three modules, the presented scheme could take advantage of these distributed imperfect datasets to train a generalizable model. The proposed method was extensively evaluated with multiple abdominal CT datasets, achieving an average result of 84.83% in Dice and 41.62mm in 95HD for multi-organ (liver, spleen, and stomach) segmentation. Moreover, its efficacy in transfer learning further demonstrated its good generalization ability for downstream segmentation tasks. This study considers a novel problem of multi-organ segmentation, which aims to develop a generalizable model using distributed, partially labeled, and unlabeled CT images. A practical framework is presented, which, through extensive validation, has proved to be an effective solution, demonstrating strong potential in addressing this challenging problem.

DNA lesion bypass and the stochastic dynamics of transcription-coupled repair

DNA base damage is a major source of oncogenic mutations and disruption to gene expression. The stalling of RNA polymerase II (RNAP) at sites of DNA damage and the subsequent triggering of repair processes have major roles in shaping the genome-wide distribution of mutations, clearing barriers to transcription, and minimizing the production of miscoded gene products. Despite its importance for genetic integrity, key mechanistic features of this transcription-coupled repair (TCR) process are controversial or unknown. Here, we exploited a well-powered in vivo mammalian model system to explore the mechanistic properties and parameters of TCR for alkylation damage at fine spatial resolution and with discrimination of the damaged DNA strand. For rigorous interpretation, a generalizable mathematical model of DNA damage and TCR was developed. Fitting experimental data to the model and simulation revealed that RNA polymerases frequently bypass lesions without triggering repair, indicating that small alkylation adducts are unlikely to be an efficient barrier to gene expression. Following a burst of damage, the efficiency of transcription-coupled repair gradually decays through gene bodies with implications for the occurrence and accurate inference of driver mutations in cancer. The reinitation of transcription from the repair site is not a general feature of transcription-coupled repair, and the observed data is consistent with reinitiation never taking place. Collectively, these results reveal how the directional but stochastic activity of TCR shapes the distribution of mutations following DNA damage.