Proto-tool use for food processing in wild Arabian babblers: matching processing methods, substrates and prey types.

Cognition is a powerful adaptation, enabling animals to utilise resources that are unavailable without manipulation. Tool use and food processing are examples of using cognition to overcome the protective mechanisms of food resources. Here, we describe and examine the flexibility of proto-tool use (defined as the alteration of an object through object-substrate manipulation) for food processing in a cooperatively breeding bird, the Arabian babbler (Argya squamiceps). Field observations demonstrate that the birds transport different caterpillar species to different substrate types depending on the processing method needed to prepare the caterpillar for eating. Species with toxic setae (e.g. Casama innotata) are transported to be rubbed on rough substrates (e.g. sand) before consumption, while other species (e.g. Hyles livornica) are transported to be pounded against hard substrates until their inner organs are removed and only their external body part is consumed. These results are among the few to describe flexible proto-tool use for food processing in wild animals. They thereby contribute to the taxonomic mapping of proto-tool use and food processing in non-human species, which is a fundamental step to advance comparative studies on the evolution of these behaviours and their underlying cognitive mechanisms.

Examining cut mark residue with SEM to identify metal tool use: An experimental study.

In this manuscript, we explore the potential of studying metal residues in cut marks generated by copper and bronze knives. The method was developed in the forensic sciences for use with modern metals in order to identify microscopic particles of metal tools on bone surfaces. However, the study of residues in archaeological materials can be challenging due to the ways in which the bone remains may have been manipulated, both in the past and in more recent times. Using a scanning electron microscope (SEM), we detected microscopic fragments of bronze and copper knives along with contamination both inside and outside of the cut marks made by those knives. Copper and bronze residues were identified embedded in the bone inside the incisions and, in two cases, they left greenish stains caused by metal oxidation. In contrast, modern contamination of undetermined origin was found unattached to the bone and had a chemical composition not compatible with that of the knives. The amount of residue was influenced by the quantity of soft tissue between the bone and the knife during the butchering tasks. Bone cooking does not seem to influence the preservation of the residues. We anticipate that the approach used in this first exploratory study will emerge as a promising method for identifying the use of metal tools in archaeological bone remains.

Automatic identification of stone-handling behaviour in Japanese macaques using LabGym artificial intelligence.

The latest advances in artificial intelligence technology have opened doors to the video analysis of complex behaviours. In light of this, ethologists are actively exploring the potential of these innovations to streamline the time-intensive behavioural analysis process using video data. Several tools have been developed for this purpose in primatology in the past decade. Nonetheless, each tool grapples with technical constraints. To address these limitations, we have established a comprehensive protocol designed to harness the capabilities of a cutting-edge artificial intelligence-assisted software, LabGym. The primary objective of this study was to evaluate the suitability of LabGym for the analysis of primate behaviour, focusing on Japanese macaques as our model subjects. First, we developed a model that accurately detects Japanese macaques, allowing us to analyse their actions using LabGym. Our behavioural analysis model succeeded in recognising stone-handling-like behaviours on video. However, the absence of quantitative data within the specified time frame limits the ability of our study to draw definitive conclusions regarding the quality of the behavioural analysis. Nevertheless, to the best of our knowledge, this study represents the first instance of applying the LabGym tool specifically for the analysis of primate behaviours, with our model focusing on the automated recognition and categorisation of specific behaviours in Japanese macaques. It lays the groundwork for future research in this promising field to complexify our model using the latest version of LabGym and associated tools, such as multi-class detection and interactive behaviour analysis.

Water scooping: tool use by a wild bonobo (Pan paniscus) at LuiKotale, a case report.

Tool use diversity is often considered to differentiate our two closest living relatives: the chimpanzee (Pan troglodytes) and the bonobo (P. paniscus). Chimpanzees appear to have the largest repertoire of tools amongst nonhuman primates, and in this species, many forms of tool use enhance food and water acquisition. In captivity, bonobos seem as adept as chimpanzees in tool use complexity, including in the foraging context. However, in the wild, bonobos have only been observed engaging in habitual tool use in the contexts of comfort, play, self-directed behaviour and communication, whilst no tool-assisted food acquisition has been reported. Whereas captive bonobos use tools for drinking, so far, the only report from the wild populations comes down to four observations of moss sponges used at Lomako. Here, we present the first report of tool use in the form of water scooping by a wild bonobo at LuiKotale. An adult female was observed and videotaped whilst using an emptied Cola chlamydantha pod to scoop and drink water from a stream. We discuss the conditions for such observations and the importance of looking out for rare behaviours and attempt to put the observation into the context of the opportunity versus necessity hypotheses. By adding novel information on tool use, our report contributes to the ongoing efforts to differentiate population-specific traits in the behavioural ecology of the bonobo.

An empirical comparison of statistical methods for multiple cut-off diagnostic test accuracy meta-analysis of the Edinburgh postnatal depression scale (EPDS) depression screening tool using published results vs individual participant data.

BACKGROUND: Selective reporting of results from only well-performing cut-offs leads to biased estimates of accuracy in primary studies of questionnaire-based screening tools and in meta-analyses that synthesize results. Individual participant data meta-analysis (IPDMA) of sensitivity and specificity at each cut-off via bivariate random-effects models (BREMs) can overcome this problem. However, IPDMA is laborious and depends on the ability to successfully obtain primary datasets, and BREMs ignore the correlation between cut-offs within primary studies. METHODS: We compared the performance of three recent multiple cut-off models developed by Steinhauser et al., Jones et al., and Hoyer and Kuss, that account for missing cut-offs when meta-analyzing diagnostic accuracy studies with multiple cut-offs, to BREMs fitted at each cut-off. We used data from 22 studies of the accuracy of the Edinburgh Postnatal Depression Scale (EPDS; 4475 participants, 758 major depression cases). We fitted each of the three multiple cut-off models and BREMs to a dataset with results from only published cut-offs from each study (published data) and an IPD dataset with results for all cut-offs (full IPD data). We estimated pooled sensitivity and specificity with 95% confidence intervals (CIs) for each cut-off and the area under the curve. RESULTS: Compared to the BREMs fitted to the full IPD data, the Steinhauser et al., Jones et al., and Hoyer and Kuss models fitted to the published data produced similar receiver operating characteristic curves; though, the Hoyer and Kuss model had lower area under the curve, mainly due to estimating slightly lower sensitivity at lower cut-offs. When fitting the three multiple cut-off models to the full IPD data, a similar pattern of results was observed. Importantly, all models had similar 95% CIs for sensitivity and specificity, and the CI width increased with cut-off levels for sensitivity and decreased with an increasing cut-off for specificity, even the BREMs which treat each cut-off separately. CONCLUSIONS: Multiple cut-off models appear to be the favorable methods when only published data are available. While collecting IPD is expensive and time consuming, IPD can facilitate subgroup analyses that cannot be conducted with published data only.

The Determination of Diabetes Utilities, Costs, and Effects Model: A Cost-Utility Tool Using Patient-Level Microsimulation to Evaluate Sensor-Based Glucose Monitoring Systems in Type 1 and Type 2 Diabetes: Comparative Validation.

OBJECTIVES: To assess the accuracy and validity of the Determination of Diabetes Utilities, Costs, and Effects (DEDUCE) model, a Microsoft-Excel-based tool for evaluating diabetes interventions for type 1 and type 2 diabetes. METHODS: The DEDUCE model is a patient-level microsimulation, with complications predicted based on the Sheffield and Risk Equations for Complications Of type 2 diabetes models for type 1 and type 2 diabetes, respectively. For this tool to be useful, it must be validated to ensure that its complication predictions are accurate. Internal, external, and cross-validation was assessed by populating the DEDUCE model with the baseline characteristics and treatment effects reported in clinical trials used in the Fourth, Fifth, and Ninth Mount Hood Diabetes Challenges. Results from the DEDUCE model were evaluated against clinical results and previously validated models via mean absolute percentage error or percentage error. RESULTS: The DEDUCE model performed favorably, predicting key outcomes, including cardiovascular disease in type 1 diabetes and all-cause mortality in type 2 diabetes. The model performed well against other models. In the Mount Hood 9 Challenge comparison, error was below the mean reported from comparator models for several outcomes, particularly for hazard ratios. CONCLUSIONS: The DEDUCE model predicts diabetes-related complications from trials and studies well when compared with previously validated models. The model may serve as a useful tool for evaluating the cost-effectiveness of diabetes technologies.

Different ways of evolving tool-using brains in teleosts and amniotes.

In mammals and birds, tool-using species are characterized by their relatively large telencephalon containing a higher proportion of total brain neurons compared to other species. Some teleost species in the wrasse family have evolved tool-using abilities. In this study, we compared the brains of tool-using wrasses with various teleost species. We show that in the tool-using wrasses, the telencephalon and the ventral part of the forebrain and midbrain are significantly enlarged compared to other teleost species but do not contain a larger proportion of cells. Instead, this size difference is due to large fiber tracts connecting the dorsal part of the telencephalon (pallium) to the inferior lobe, a ventral mesencephalic structure absent in amniotes. The high degree of connectivity between these structures in tool-using wrasses suggests that the inferior lobe could contribute to higher-order cognitive functions. We conclude that the evolution of non-telencephalic structures might have been key in the emergence of these cognitive functions in teleosts.

Male-biased stone tool use by wild white-faced capuchins (Cebus capucinus imitator).

Tool-using primates often show sex differences in both the frequency and efficiency of tool use. In species with sex-biased dispersal, such within-group variation likely shapes patterns of cultural transmission of tool-use traditions between groups. On the Panamanian islands of Jicarón and Coiba, a population of white-faced capuchins (Cebus capucinus imitator)-some of which engage in habitual stone tool use-provide an opportunity to test hypotheses about why such sex-biases arise. On Jicarón, we have only observed males engaging in stone tool use, whereas on Coiba, both sexes are known to use tools. Using 5 years of camera trap data, we provide evidence that this variation likely reflects a sex difference in tool use rather than a sampling artifact, and then test hypotheses about the factors driving this pattern. Differences in physical ability or risk-aversion, and competition over access to anvils do not account for the sex-differences in tool-use we observe. Our data show that adult females are physically capable of stone tool use: adult females on Coiba and juveniles on Jicarón smaller than adult females regularly engage in tool use. Females also have ample opportunity to use tools: the sexes are equally terrestrial, and competition over anvils is low. Finally, females rarely scrounge on left-over food items either during or after tool-using events, suggesting they are not being provisioned by males. Although it remains unclear why adult white-faced capuchin females on Jicarón do not use stone-tools, our results illustrate that such sex biases in socially learned behaviors can arise even in the absence of obvious physical, environmental, and social constraints. This suggests that a much more nuanced understanding of the differences in social structure, diet, and dispersal patterns are needed to explain why sex-biases in tool use arise in some populations but not in others.

Mapping nut-cracking in a new population of wild capuchin monkeys (Sapajus libidinosus) at Ubajara National Park, Brazil.

Populations of bearded capuchin monkeys (Sapajus libidinosus) vary in their tool use behaviors, with some of this divergence regarded as culturally determined. The use of stone tools, primarily to crack open encased foods, is widespread among bearded capuchins living in dry habitats (Caatinga and Cerrado). Significant diversity in targets, processed foods, material, and size of tools is observed across populations. However, so far, only a few sites have been systematically studied, and we are still distant from a representative picture of the range of variation in capuchins' culture. In this study, we did a systematic assessment of stone tool use sites in the Ubajara National Park (UNP), in the Caatinga region of Ceará, Brazil, recording and measuring stone tools, processed foods, and available lithic resources as part of an extensive comparative research, the CapCult project. We found indirect and direct evidence that capuchin monkeys at UNP customarily use hammerstones and anvils to process at least two species of palm nuts, macauba (Acrocomia aculeata) and the harder babaçu (Attalea speciosa). Most of the anvils were rock surfaces and had leftovers of only one palm nut species. The hammerstones used to process both palm nuts were not significantly different in weight, although the ones used for Ac. aculeata were longer. We found a higher frequency of nut-cracking sites in the drier lowland area of the park, reflecting differences in the density of the most common palm species, Ac. aculeata, and availability of raw stone material. The stone tool use observed in UNP is within the scope of previously reported in savannah capuchin populations. Our study widens the knowledge of stone tool-use diversity in wild capuchin monkeys, which could contribute to shaping conservation policy, including cultural traits.

Relationship Between Patient Portal Tool Use and Medication Adherence and Viral Load Among Patients Living with HIV.

BACKGROUND: Patient portals play an increasingly critical role in engaging patients in their health care. They have the potential to significantly impact the health of those living with chronic diseases, such as HIV, for whom consistent care engagement is both critical and complex. OBJECTIVE: The primary aim was to examine the longitudinal relationships between individual portal tool use and health-related outcomes in patients living with HIV. DESIGN: Retrospective cohort study using electronic health record data to examine the relationship between patient portal tool use and key HIV-specific, health-related outcomes in patients engaged in care in the Veterans Health Administration (VA) through the application of marginal structural models. PARTICIPANTS: A national sample of patients living with HIV (PLWH) active in VA care who were registered to use the VA's patient portal, My HealtheVet (MHV; n = 18,390) between 10/1/2012 and 4/1/2017. MAIN MEASURES: The MHV tools examined were prescription refill (including prescription refill of an antiretroviral (ART) medication and any medication), secure messaging, view appointments, and view labs. Primary outcomes were viral load test receipt, viral load suppression, and ART medication adherence (measured as proportion of days covered). KEY RESULTS: The use of prescription refill for any medication or for ART was positively associated with ART adherence. Secure messaging was positively associated with ART adherence but not with viral load test receipt or viral load suppression. The use of view appointments was positively associated with ART adherence and viral load test receipt but not viral load suppression. The use of view labs was positively associated with viral load suppression but not ART adherence or viral load test receipt. CONCLUSIONS: These findings highlight the valuable role patient portals may play in improving health-related outcomes among PLWH and have implications for patients living with other types of chronic disease.

MLDSPP: Bacterial Promoter Prediction Tool Using DNA Structural Properties with Machine Learning and Explainable AI.

Bacterial promoters play a crucial role in gene expression by serving as docking sites for the transcription initiation machinery. However, accurately identifying promoter regions in bacterial genomes remains a challenge due to their diverse architecture and variations. In this study, we propose MLDSPP (Machine Learning and Duplex Stability based Promoter prediction in Prokaryotes), a machine learning-based promoter prediction tool, to comprehensively screen bacterial promoter regions in 12 diverse genomes. We leveraged biologically relevant and informative DNA structural properties, such as DNA duplex stability and base stacking, and state-of-the-art machine learning (ML) strategies to gain insights into promoter characteristics. We evaluated several machine learning models, including Support Vector Machines, Random Forests, and XGBoost, and assessed their performance using accuracy, precision, recall, specificity, F1 score, and MCC metrics. Our findings reveal that XGBoost outperformed other models and current state-of-the-art promoter prediction tools, namely Sigma70pred and iPromoter2L, achieving F1-scores >95% in most systems. Significantly, the use of one-hot encoding for representing nucleotide sequences complements these structural features, enhancing our XGBoost model's predictive capabilities. To address the challenge of model interpretability, we incorporated explainable AI techniques using Shapley values. This enhancement allows for a better understanding and interpretation of the predictions of our model. In conclusion, our study presents MLDSPP as a novel, generic tool for predicting promoter regions in bacteria, utilizing original downstream sequences as nonpromoter controls. This tool has the potential to significantly advance the field of bacterial genomics and contribute to our understanding of gene regulation in diverse bacterial systems.

Influence of COVID-19 on the emergence of stone-tool use behavior in a population of common long-tailed macaques (Macaca fascicularis fascicularis) in Thailand.

Stone tool use is a rare behavior across nonhuman primates. Here we report the first population of common long-tailed macaques (Macaca fascicularis fascicularis) who customarily used stone tools to open rock oysters (Saccostrea forskali) on a small island along the Thai Gulf in Koh Ped (KPE), eastern Thailand. We observed this population several times during the past 10 years, but no stone-tool use behavior was observed until our survey during the coronavirus disease 2019 (COVID-19) pandemic in July 2022. KPE is located in Pattaya City, a hotspot for tourism in Thailand. Tourists in this area frequently provided large amounts of food for the monkeys on KPE. During the COVID-19 curfew, however, tourists were not allowed to access the island, and monkeys began to face food scarcity. During this time, we observed stone-tool use behavior for the first time on KPE. Based on our observations, the first tool manipulation was similar to stone throwing (a known precursor of stone tool use). From our observations in March 2023, we found 17 subadult/adult animals performing the behavior, 15 of 17 were males and mostly solitary while performing the behavior. The M. f. fascicularis subspecies was confirmed by distribution, morphological characteristics, and mtDNA and SRY gene sequences. Taken together, we proposed that the stone tool use behavior in the KPE common long-tailed macaques emerged due to the COVID-19 food scarcity. Since traveling is no longer restricted many tourists have started coming back to the island, and there is a high risk for this stone tool-use behavior to disappear within this population of long-tailed macaques.

Primate archaeology 3.0.

The new field of primate archaeology investigates the technological behavior and material record of nonhuman primates, providing valuable comparative data on our understanding of human technological evolution. Yet, paralleling hominin archaeology, the field is largely biased toward the analysis of lithic artifacts. While valuable comparative data have been gained through an examination of extant nonhuman primate tool use and its archaeological record, focusing on this one single aspect provides limited insights. It is therefore necessary to explore to what extent other non-technological activities, such as non-tool aided feeding, traveling, social behaviors or ritual displays, leave traces that could be detected in the archaeological record. Here we propose four new areas of investigation which we believe have been largely overlooked by primate archaeology and that are crucial to uncovering the full archaeological potential of the primate behavioral repertoire, including that of our own: (1) Plant technology; (2) Archaeology beyond technology; (3) Landscape archaeology; and (4) Primate cultural heritage. We discuss each theme in the context of the latest developments and challenges, as well as propose future directions. Developing a more "inclusive" primate archaeology will not only benefit the study of primate evolution in its own right but will aid conservation efforts by increasing our understanding of changes in primate-environment interactions over time.

A data-driven computational methodology towards a pre-hospital Acute Ischaemic Stroke screening tool using haemodynamics waveforms.

BACKGROUND AND OBJECTIVE: Acute Ischaemic Stroke (AIS), a significant global health concern, results from occlusions in cerebral arteries, causing irreversible brain damage. Different type of treatments exist depending on the size and location of the occlusion. Challenges persist in achieving faster diagnosis and treatment, which needs to happen in the first hours after the onset of symptoms to maximize the chances of patient recovery. The current diagnostic pipeline, i.e. "drip and ship", involves diagnostic via advanced imaging tools, only available in large clinical facilities, which poses important delays. This study investigates the feasibility of developing a machine learning model to diagnose and locate occluding blood clots from velocity waveforms, which can be easily be obtained with portable devices such as Doppler Ultrasound. The goal is to explore this approach as a cost-effective and time-efficient alternative to advanced imaging techniques typically available only in large hospitals. METHODS: Simulated haemodynamic data is used to conduct blood flow simulations representing healthy and different AIS scenarios using a population-based database. A Machine Learning classification model is trained to solve the inverse problem, this is, detect and locate a potentially occluding thrombus from measured waveforms. The classification process involves two steps. First, the region where the thrombus is located is classified into nine groups, including healthy, left or right large vessel occlusion, left or right anterior cerebral artery, and left or right posterior cerebral artery. In a second step, the bifurcation generation of the thrombus location is classified as small, medium, or large vessel occlusion. RESULTS: The proposed methodology is evaluated for data without noise, achieving a true prediction rate exceeding 95% for both classification steps mentioned above. The inclusion of up to 20% noise reduces the true prediction rate to 80% for region detection and 70% for bifurcation generation detection. CONCLUSIONS: This study demonstrates the potential effectiveness and efficiency of using haemodynamic data and machine learning to detect and locate occluding thrombi in AIS patients. Although the geometric and topological data used in this study are idealized, the results suggest that this approach could be applicable in real-world situations with appropriate adjustments. Source code is available in https://github.com/ahmetsenemse/Acute-Ischaemic-Stroke-screening-tool-.

Evaluating the OH-EpiCap tool using the Danish integrated surveillance program for AMU and AMR as a case study.

Antimicrobial resistance (AMR) is considered a One Health (OH) challenge, ideally demanding concerted efforts from the animal, human and environmental side. DANMAP, the Danish Integrated Antimicrobial Resistance Monitoring and Research Program, is monitoring AMR and antimicrobial use in animals and humans. OH-EpiCap is an evaluation tool, developed to address essential elements in OH surveillance systems, such as the dimensions of the organization, operational activities and the impact of the surveillance activities. We aimed to evaluate DANMAP using OH-EpiCap and hereby assessed the suitability of OH-EpiCap to evaluate integrated AMR surveillance systems. During the evaluation, the strengths and weaknesses of DANMAP concerning the "OH-ness" of the program were discussed. Furthermore, possible adaptations of the standard operating procedures and governance structure were addressed. Attention was paid to the ability and easiness of DANMAP to cope with current and future challenges connected to integrated AMR surveillance. It was concluded that DANMAP has a strong OH approach covering relevant aspects for humans and animals, whereas environmental aspects are missing. OH-EpiCap proved to be straightforward to use and provided valuable insights. The authors recommend OH-EpiCap to be used by health authorities and stakeholders. It is not suitable for the technical evaluation of a surveillance program.

Dunking rusk: innovative food soaking behaviour in Goffin's cockatoos (Cacatua goffiniana).

Foraging innovations in animals involving the processing of resources that are already edible in an unprocessed state, yet of improved quality in a processed state, are rare but important to study the evolution of food preparation. Here, we present the first scientific report of food dunking behaviours in parrots by Goffin's cockatoos, a model species for innovative problem solving. Observations during lunch showed seven out of 18 cockatoos placing their food into water and soaking it prior to consumption. This was largely done with dry rusk which was eaten almost exclusively when dunked. Furthermore, their transport effort and waiting times before retrieving food from the water indicate their willingness to invest considerable time to prepare a soaked rusk piece of a higher texture quality. Our present results suggest that the function of this behaviour is to soak the food. Because only some individuals dunked food and dunking has not been observed in the wild, we believe this to be a spontaneous foraging innovation either by one or multiple individuals.

Development of LuxIA, a Cloud-Based AI Diabetic Retinopathy Screening Tool Using a Single Color Fundus Image.

Purpose: Diabetic retinopathy (DR) is the leading cause of vision impairment in working-age adults. Automated screening can increase DR detection at early stages at relatively low costs. We developed and evaluated a cloud-based screening tool that uses artificial intelligence (AI), the LuxIA algorithm, to detect DR from a single fundus image. Methods: Color fundus images that were previously graded by expert readers were collected from the Canarian Health Service (Retisalud) and used to train LuxIA, a deep-learning-based algorithm for the detection of more than mild DR. The algorithm was deployed in the Discovery cloud platform to evaluate each test set. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve were computed using a bootstrapping method to evaluate the algorithm performance and compared through different publicly available datasets. A usability test was performed to assess the integration into a clinical tool. Results: Three separate datasets, Messidor-2, APTOS, and a holdout set from Retisalud were evaluated. Mean sensitivity and specificity with 95% confidence intervals (CIs) reached for these three datasets were 0.901 (0.901-0.902) and 0.955 (0.955-0.956), 0.995 (0.995-0.995) and 0.821 (0.821-0.823), and 0.911 (0.907-0.912) and 0.880 (0.879-0.880), respectively. The usability test confirmed the successful integration of LuxIA into Discovery. Conclusions: Clinical data were used to train the deep-learning-based algorithm LuxIA to an expert-level performance. The whole process (image uploading and analysis) was integrated into the cloud-based platform Discovery, allowing more patients to have access to expert-level screening tools. Translational Relevance: Using the cloud-based LuxIA tool as part of a screening program may give diabetic patients greater access to specialist-level decisions, without the need for consultation.

American crows that excel at tool use activate neural circuits distinct from less talented individuals.

Tools enable animals to exploit and command new resources. However, the neural circuits underpinning tool use and how neural activity varies with an animal's tool proficiency, are only known for humans and some other primates. We use 18F-fluorodeoxyglucose positron emission tomography to image the brain activity of naïve vs trained American crows (Corvus brachyrhynchos) when presented with a task requiring the use of stone tools. As in humans, talent affects the neural circuits activated by crows as they prepare to execute the task. Naïve and less proficient crows use neural circuits associated with sensory- and higher-order processing centers (the mesopallium and nidopallium), while highly proficient individuals increase activity in circuits associated with motor learning and tactile control (hippocampus, tegmentum, nucleus basorostralis, and cerebellum). Greater proficiency is found primarily in adult female crows and may reflect their need to use more cognitively complex strategies, like tool use, to obtain food.

Technical note: A collision prediction tool using Blender.

Non-coplanar radiotherapy treatment techniques on C-arm linear accelerators have the potential to reduce dose to organs-at-risk in comparison with coplanar treatment techniques. Accurately predicting possible collisions between gantry, table and patient during treatment planning is needed to ensure patient safety. We offer a freely available collision prediction tool using Blender, a free and open-source 3D computer graphics software toolset. A geometric model of a C-arm linear accelerator including a library of patient models is created inside Blender. Based on the model, collision predictions can be used both to calculate collision-free zones and to check treatment plans for collisions. The tool is validated for two setups, once with and once without a full body phantom with the same table position. For this, each gantry-table angle combination with a 2° resolution is manually checked for collision interlocks at a TrueBeam system and compared to simulated collision predictions. For the collision check of a treatment plan, the tool outputs the minimal distance between the gantry, table and patient model and a video of the movement of the gantry and table, which is demonstrated for one use case. A graphical user interface allows user-friendly input of the table and patient specification for the collision prediction tool. The validation resulted in a true positive rate of 100%, which is the rate between the number of correctly predicted collision gantry-table combinations and the number of all measured collision gantry-table combinations, and a true negative rate of 89%, which is the ratio between the number of correctly predicted collision-free combinations and the number of all measured collision-free combinations. A collision prediction tool is successfully created and able to produce maps of collision-free zones and to test treatment plans for collisions including visualisation of the gantry and table movement.