Luis Miguel Soria Morillo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Luis Miguel Soria Morillo has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Juan Antonio Alvarez García
Department of Languages and Computer Systems, Universidad de Sevilla, 41012 Sevilla, Spain
20 shared publications - Juan Antonio Ortega
University of Seville
8 shared publications - Luis Gonzalez-Abril
University of Seville
8 shared publications - Jose L. Salazar González
Dpto. de Lenguajes y Sistemas Informáticos, Universidad de Sevilla, Spain
4 shared publications - Juan Jose Vegas Olmos
NVIDIA, Roskilde, Denmark
4 shared publications - Marina Perea-Trigo
Department of Languages and Computer Systems, Universidad de Sevilla, 41012 Sevilla, Spain
4 shared publications
Latest Publications
- Open Access
- 20 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (10) , 5104
LEOPARD: Automated CAD-to-Synthetic Pipeline for 3D-Printed Firearm Detection in Civil Transit Security
The proliferation of 3D-printed firearms poses a growing challenge for civil security, particularly in controlled public environments such as airports, train stations, and other transit hubs. These objects are often manufactured from polymer materials, exhibit high design variability, and are difficult to detect using conventional inspection systems. With over 20,000 weapon designs freely available online, traditional dataset creation methods cannot match the pace of design evolution. To address this challenge, we present LEOPARD, a pipeline designed to support civil security applications by converting CAD (computer-aided design) models of illicit firearm components into large-scale, photorealistic synthetic datasets. The pipeline incorporates procedural geometric variations, material imperfections, and physics-based rendering to realistically model 3D-printed objects as they may appear during security screening. Using this pipeline, we introduce LEOPARD-Zero, a dataset of 75,000 fully annotated synthetic images focused on the detection of illegal 3D-printed firearm components, with potential applications in civil transportation security contexts. Object detection models trained exclusively on our synthetic data achieve high performance on real 3D-printed components, with mAP@50 exceeding 83% and precision reaching up to 91.9%, demonstrating viable performance without requiring extensive real-world data collection. To encourage further research in automated inspection and public safety, we have released LEOPARD-Zero.
- 20 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (10) , 5104
Open AccessLEOPARD: Automated CAD-to-Synthetic Pipeline for 3D-Printed Firearm Detection in Civil Transit Security
The proliferation of 3D-printed firearms poses a growing challenge for civil security, particularly in controlled public environments such as airports, train stations, and other transit hubs. These objects are often manufactured from polymer materials, exhibit high design variability, and are difficult to detect using conventional inspection systems. With over 20,000 weapon designs freely available online, traditional dataset creation methods cannot match the pace of design evolution. To address this challenge, we present LEOPARD, a pipeline designed to support civil security applications by converting CAD (computer-aided design) models of illicit firearm components into large-scale, photorealistic synthetic datasets. The pipeline incorporates procedural geometric variations, material imperfections, and physics-based rendering to realistically model 3D-printed objects as they may appear during security screening. Using this pipeline, we introduce LEOPARD-Zero, a dataset of 75,000 fully annotated synthetic images focused on the detection of illegal 3D-printed firearm components, with potential applications in civil transportation security contexts. Object detection models trained exclusively on our synthetic data achieve high performance on real 3D-printed components, with mAP@50 exceeding 83% and precision reaching up to 91.9%, demonstrating viable performance without requiring extensive real-world data collection. To encourage further research in automated inspection and public safety, we have released LEOPARD-Zero.
- Open Access
- 12 September 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (18) , 8198
Effective Strategies for Enhancing Real-Time Weapons Detection in Industry
Gun violence is a global problem that affects communities and individuals, posing challenges to safety and well-being. The use of autonomous weapons detection systems could significantly improve security worldwide. Despite notable progress in the field of weapons detection closed-circuit television-based systems, several challenges persist, including real-time detection, improved accuracy in detecting small objects, and reducing false positives. This paper, based on our extensive experience in this field and successful private company contracts, presents a detection scheme comprising two modules that enhance the performance of a renowned detector. These modules not only augment the detector’s performance but also have a low negative impact on the inference time. Additionally, a scale-matching technique is utilised to enhance the detection of weapons with a small aspect ratio. The experimental results demonstrate that the scale-matching method enhances the detection of small objects, with an improvement of +13.23 in average precision compared to the non-use of this method. Furthermore, the proposed detection scheme effectively reduces the number of false positives (a 71% reduction in the total number of false positives) of the baseline model, while maintaining a low inference time (34 frames per second on an NVIDIA GeForce RTX-3060 card with a resolution of 720 pixels) in comparison to the baseline model (47 frames per second).
- 12 September 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (18) , 8198
Open AccessEffective Strategies for Enhancing Real-Time Weapons Detection in Industry
Gun violence is a global problem that affects communities and individuals, posing challenges to safety and well-being. The use of autonomous weapons detection systems could significantly improve security worldwide. Despite notable progress in the field of weapons detection closed-circuit television-based systems, several challenges persist, including real-time detection, improved accuracy in detecting small objects, and reducing false positives. This paper, based on our extensive experience in this field and successful private company contracts, presents a detection scheme comprising two modules that enhance the performance of a renowned detector. These modules not only augment the detector’s performance but also have a low negative impact on the inference time. Additionally, a scale-matching technique is utilised to enhance the detection of weapons with a small aspect ratio. The experimental results demonstrate that the scale-matching method enhances the detection of small objects, with an improvement of +13.23 in average precision compared to the non-use of this method. Furthermore, the proposed detection scheme effectively reduces the number of false positives (a 71% reduction in the total number of false positives) of the baseline model, while maintaining a low inference time (34 frames per second on an NVIDIA GeForce RTX-3060 card with a resolution of 720 pixels) in comparison to the baseline model (47 frames per second).
- Open Access
Transformer and Adaptive Threshold Sliding Window for Improving Violence Detection in Videos
This paper presents a comprehensive approach to detect violent events in videos by combining CrimeNet, a Vision Transformer (ViT) model with structured neural learning and adversarial regularization, with an adaptive threshold sliding window model based on the Transformer architecture. CrimeNet demonstrates exceptional performance on all datasets (XD-Violence, UCF-Crime, NTU-CCTV Fights, UBI-Fights, Real Life Violence Situations, MediEval, RWF-2000, Hockey Fights, Violent Flows, Surveillance Camera Fights, and Movies Fight), achieving high AUC ROC and AUC PR values (up to 99% and 100%, respectively). However, the generalization of CrimeNet to cross-dataset experiments posed some problems, resulting in a 20–30% decrease in performance, for instance, training in UCF-Crime and testing in XD-Violence resulted in 70.20% in AUC ROC. The sliding window model with adaptive thresholding effectively solves these problems by automatically adjusting the violence detection threshold, resulting in a substantial improvement in detection accuracy. By applying the sliding window model as post-processing to CrimeNet results, we were able to improve detection accuracy by 10% to 15% in cross-dataset experiments. Future lines of research include improving generalization, addressing data imbalance, exploring multimodal representations, testing in real-world applications, and extending the approach to complex human interactions.
Open AccessTransformer and Adaptive Threshold Sliding Window for Improving Violence Detection in Videos
This paper presents a comprehensive approach to detect violent events in videos by combining CrimeNet, a Vision Transformer (ViT) model with structured neural learning and adversarial regularization, with an adaptive threshold sliding window model based on the Transformer architecture. CrimeNet demonstrates exceptional performance on all datasets (XD-Violence, UCF-Crime, NTU-CCTV Fights, UBI-Fights, Real Life Violence Situations, MediEval, RWF-2000, Hockey Fights, Violent Flows, Surveillance Camera Fights, and Movies Fight), achieving high AUC ROC and AUC PR values (up to 99% and 100%, respectively). However, the generalization of CrimeNet to cross-dataset experiments posed some problems, resulting in a 20–30% decrease in performance, for instance, training in UCF-Crime and testing in XD-Violence resulted in 70.20% in AUC ROC. The sliding window model with adaptive thresholding effectively solves these problems by automatically adjusting the violence detection threshold, resulting in a substantial improvement in detection accuracy. By applying the sliding window model as post-processing to CrimeNet results, we were able to improve detection accuracy by 10% to 15% in cross-dataset experiments. Future lines of research include improving generalization, addressing data imbalance, exploring multimodal representations, testing in real-world applications, and extending the approach to complex human interactions.
- Open Access
- 24 July 2024
- Published by Springer Nature in Universal Access in the Information Society
- Vol. 24 (2) , 1283-1294
Impact of face swapping and data augmentation on sign language recognition
This study addresses the challenge of improving communication between the deaf and hearing community by exploring different sign language recognition (SLR) techniques. Due to privacy issues and the need for validation by interpreters, creating large-scale sign language (SL) datasets can be difficult. The authors address this by presenting a new Spanish isolated sign language recognition dataset, CALSE-1000, consisting of 5000 videos representing 1000 glosses, with various signers and scenarios. The study also proposes using different computer vision techniques, such as face swapping and affine transformations, to augment the SL dataset and improve the accuracy of the model I3D trained using them. The results show that the inclusion of these augmentations during training leads to an improvement in accuracy in top-1 metrics by up to 11.7 points, top-5 by up to 8.8 points and top-10 by up to 9 points. This has great potential to improve the state of the art in other datasets and other models. Furthermore, the analysis confirms the importance of facial expressions in the model by testing with a facial omission dataset and shows how face swapping can be used to include new anonymous signers without the costly and time-consuming process of recording.
- 24 July 2024
- Published by Springer Nature in Universal Access in the Information Society
- Vol. 24 (2) , 1283-1294
Open AccessImpact of face swapping and data augmentation on sign language recognition
This study addresses the challenge of improving communication between the deaf and hearing community by exploring different sign language recognition (SLR) techniques. Due to privacy issues and the need for validation by interpreters, creating large-scale sign language (SL) datasets can be difficult. The authors address this by presenting a new Spanish isolated sign language recognition dataset, CALSE-1000, consisting of 5000 videos representing 1000 glosses, with various signers and scenarios. The study also proposes using different computer vision techniques, such as face swapping and affine transformations, to augment the SL dataset and improve the accuracy of the model I3D trained using them. The results show that the inclusion of these augmentations during training leads to an improvement in accuracy in top-1 metrics by up to 11.7 points, top-5 by up to 8.8 points and top-10 by up to 9 points. This has great potential to improve the state of the art in other datasets and other models. Furthermore, the analysis confirms the importance of facial expressions in the model by testing with a facial omission dataset and shows how face swapping can be used to include new anonymous signers without the costly and time-consuming process of recording.
- Open Access
Energy-Efficient Edge and Cloud Image Classification with Multi-Reservoir Echo State Network and Data Processing Units
In an era dominated by Internet of Things (IoT) devices, software-as-a-service (SaaS) platforms, and rapid advances in cloud and edge computing, the demand for efficient and lightweight models suitable for resource-constrained devices such as data processing units (DPUs) has surged. Traditional deep learning models, such as convolutional neural networks (CNNs), pose significant computational and memory challenges, limiting their use in resource-constrained environments. Echo State Networks (ESNs), based on reservoir computing principles, offer a promising alternative with reduced computational complexity and shorter training times. This study explores the applicability of ESN-based architectures in image classification and weather forecasting tasks, using benchmarks such as the MNIST, FashionMnist, and CloudCast datasets. Through comprehensive evaluations, the Multi-Reservoir ESN (MRESN) architecture emerges as a standout performer, demonstrating its potential for deployment on DPUs or home stations. In exploiting the dynamic adaptability of MRESN to changing input signals, such as weather forecasts, continuous on-device training becomes feasible, eliminating the need for static pre-trained models. Our results highlight the importance of lightweight models such as MRESN in cloud and edge computing applications where efficiency and sustainability are paramount. This study contributes to the advancement of efficient computing practices by providing novel insights into the performance and versatility of MRESN architectures. By facilitating the adoption of lightweight models in resource-constrained environments, our research provides a viable alternative for improved efficiency and scalability in modern computing paradigms.
Open AccessEnergy-Efficient Edge and Cloud Image Classification with Multi-Reservoir Echo State Network and Data Processing Units
In an era dominated by Internet of Things (IoT) devices, software-as-a-service (SaaS) platforms, and rapid advances in cloud and edge computing, the demand for efficient and lightweight models suitable for resource-constrained devices such as data processing units (DPUs) has surged. Traditional deep learning models, such as convolutional neural networks (CNNs), pose significant computational and memory challenges, limiting their use in resource-constrained environments. Echo State Networks (ESNs), based on reservoir computing principles, offer a promising alternative with reduced computational complexity and shorter training times. This study explores the applicability of ESN-based architectures in image classification and weather forecasting tasks, using benchmarks such as the MNIST, FashionMnist, and CloudCast datasets. Through comprehensive evaluations, the Multi-Reservoir ESN (MRESN) architecture emerges as a standout performer, demonstrating its potential for deployment on DPUs or home stations. In exploiting the dynamic adaptability of MRESN to changing input signals, such as weather forecasts, continuous on-device training becomes feasible, eliminating the need for static pre-trained models. Our results highlight the importance of lightweight models such as MRESN in cloud and edge computing applications where efficiency and sustainability are paramount. This study contributes to the advancement of efficient computing practices by providing novel insights into the performance and versatility of MRESN architectures. By facilitating the adoption of lightweight models in resource-constrained environments, our research provides a viable alternative for improved efficiency and scalability in modern computing paradigms.
- Open Access
- 18 April 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (20) , 11901-11918
Exploring deep echo state networks for image classification: a multi-reservoir approach
Echo state networks (ESNs) belong to the class of recurrent neural networks and have demonstrated robust performance in time series prediction tasks. In this study, we investigate the capability of different ESN architectures to capture spatial relationships in images without transforming them into temporal sequences. We begin with three pre-existing ESN-based architectures and enhance their design by incorporating multiple output layers, customising them for a classification task. Our investigation involves an examination of the behaviour of these modified networks, coupled with a comprehensive performance comparison against the baseline vanilla ESN architecture. Our experiments on the MNIST data set reveal that a network with multiple independent reservoirs working in parallel outperforms other ESN-based architectures for this task, achieving a classification accuracy of 98.43%. This improvement on the classical ESN architecture is accompanied by reduced training times. While the accuracy of ESN-based architectures lags behind that of convolutional neural network-based architectures, the significantly lower training times of ESNs with multiple reservoirs operating in parallel make them a compelling choice for learning spatial relationships in scenarios prioritising energy efficiency and rapid training. This multi-reservoir ESN architecture overcomes standard ESN limitations regarding memory requirements and training times for large networks, providing more accurate predictions than other ESN-based models. These findings contribute to a deeper understanding of the potential of ESNs as a tool for image classification.
- 18 April 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (20) , 11901-11918
Open AccessExploring deep echo state networks for image classification: a multi-reservoir approach
Echo state networks (ESNs) belong to the class of recurrent neural networks and have demonstrated robust performance in time series prediction tasks. In this study, we investigate the capability of different ESN architectures to capture spatial relationships in images without transforming them into temporal sequences. We begin with three pre-existing ESN-based architectures and enhance their design by incorporating multiple output layers, customising them for a classification task. Our investigation involves an examination of the behaviour of these modified networks, coupled with a comprehensive performance comparison against the baseline vanilla ESN architecture. Our experiments on the MNIST data set reveal that a network with multiple independent reservoirs working in parallel outperforms other ESN-based architectures for this task, achieving a classification accuracy of 98.43%. This improvement on the classical ESN architecture is accompanied by reduced training times. While the accuracy of ESN-based architectures lags behind that of convolutional neural network-based architectures, the significantly lower training times of ESNs with multiple reservoirs operating in parallel make them a compelling choice for learning spatial relationships in scenarios prioritising energy efficiency and rapid training. This multi-reservoir ESN architecture overcomes standard ESN limitations regarding memory requirements and training times for large networks, providing more accurate predictions than other ESN-based models. These findings contribute to a deeper understanding of the potential of ESNs as a tool for image classification.
- Open Access
Synthetic Corpus Generation for Deep Learning-Based Translation of Spanish Sign Language
Sign language serves as the primary mode of communication for the deaf community. With technological advancements, it is crucial to develop systems capable of enhancing communication between deaf and hearing individuals. This paper reviews recent state-of-the-art methods in sign language recognition, translation, and production. Additionally, we introduce a rule-based system, called ruLSE, for generating synthetic datasets in Spanish Sign Language. To check the usefulness of these datasets, we conduct experiments with two state-of-the-art models based on Transformers, MarianMT and Transformer-STMC. In general, we observe that the former achieves better results (+3.7 points in the BLEU-4 metric) although the latter is up to four times faster. Furthermore, the use of pre-trained word embeddings in Spanish enhances results. The rule-based system demonstrates superior performance and efficiency compared to Transformer models in Sign Language Production tasks. Lastly, we contribute to the state of the art by releasing the generated synthetic dataset in Spanish named synLSE.
Open AccessSynthetic Corpus Generation for Deep Learning-Based Translation of Spanish Sign Language
Sign language serves as the primary mode of communication for the deaf community. With technological advancements, it is crucial to develop systems capable of enhancing communication between deaf and hearing individuals. This paper reviews recent state-of-the-art methods in sign language recognition, translation, and production. Additionally, we introduce a rule-based system, called ruLSE, for generating synthetic datasets in Spanish Sign Language. To check the usefulness of these datasets, we conduct experiments with two state-of-the-art models based on Transformers, MarianMT and Transformer-STMC. In general, we observe that the former achieves better results (+3.7 points in the BLEU-4 metric) although the latter is up to four times faster. Furthermore, the use of pre-trained word embeddings in Spanish enhances results. The rule-based system demonstrates superior performance and efficiency compared to Transformer models in Sign Language Production tasks. Lastly, we contribute to the state of the art by releasing the generated synthetic dataset in Spanish named synLSE.
- Open Access
- 14 November 2023
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 12 (1) , e48925
Drug Repurposing for Cancers With Limited Survival: Protocol for a Retrospective Cohort Study
Background: Only 5% of the molecules tested in oncology phase 1 trials reach the market after an average of 7.5 years of waiting and at a cost of tens of millions of dollars. To reduce the cost and shorten the time of discovery of new treatments, “drug repurposing” (research with molecules already approved for another indication) and the use of secondary data (not collected for the purpose of research) have been proposed. Due to advances in informatics in clinical care, secondary data can, in some cases, be of equal quality to primary data generated through prospective studies. Objective: The objective of this study is to identify drugs currently marketed for other indications that may have an effect on the prognosis of patients with cancer. Methods: We plan to monitor a cohort of patients with high-lethality cancers treated in the public health system of Catalonia between 2006 and 2012, retrospectively, for survival for 5 years after diagnosis or until death. A control cohort, comprising people without cancer, will also be retrospectively monitored for 5 years. The following study variables will be extracted from different population databases: type of cancer (patients with cancer cohort), date and cause of death, pharmacological treatment, sex, age, and place of residence. During the first stage of statistical analysis of the patients with cancer cohort, the drugs consumed by the long-term survivors (alive at 5 years) will be compared with those consumed by nonsurvivors. In the second stage, the survival associated with the consumption of each relevant drug will be analyzed. For the analyses, groups will be matched for potentially confounding variables, and multivariate analyses will be performed to adjust for residual confounding variables if necessary. The control cohort will be used to verify whether the associations found are exclusive to patients with cancer or whether they also occur in patients without cancer. Results: We anticipate discovering multiple significant associations between commonly used drugs and the survival outcomes of patients with cancer. We expect to publish the initial results in the first half of 2024. Conclusions: This retrospective study may identify several commonly used drugs as candidates for repurposing in the treatment of various cancers. All analyses are considered exploratory; therefore, the results will have to be confirmed in subsequent clinical trials. However, the results of this study may accelerate drug discovery in oncology. International Registered Report Identifier (IRRID): DERR1-10.2196/48925
- 14 November 2023
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 12 (1) , e48925
Open AccessDrug Repurposing for Cancers With Limited Survival: Protocol for a Retrospective Cohort Study
Background: Only 5% of the molecules tested in oncology phase 1 trials reach the market after an average of 7.5 years of waiting and at a cost of tens of millions of dollars. To reduce the cost and shorten the time of discovery of new treatments, “drug repurposing” (research with molecules already approved for another indication) and the use of secondary data (not collected for the purpose of research) have been proposed. Due to advances in informatics in clinical care, secondary data can, in some cases, be of equal quality to primary data generated through prospective studies. Objective: The objective of this study is to identify drugs currently marketed for other indications that may have an effect on the prognosis of patients with cancer. Methods: We plan to monitor a cohort of patients with high-lethality cancers treated in the public health system of Catalonia between 2006 and 2012, retrospectively, for survival for 5 years after diagnosis or until death. A control cohort, comprising people without cancer, will also be retrospectively monitored for 5 years. The following study variables will be extracted from different population databases: type of cancer (patients with cancer cohort), date and cause of death, pharmacological treatment, sex, age, and place of residence. During the first stage of statistical analysis of the patients with cancer cohort, the drugs consumed by the long-term survivors (alive at 5 years) will be compared with those consumed by nonsurvivors. In the second stage, the survival associated with the consumption of each relevant drug will be analyzed. For the analyses, groups will be matched for potentially confounding variables, and multivariate analyses will be performed to adjust for residual confounding variables if necessary. The control cohort will be used to verify whether the associations found are exclusive to patients with cancer or whether they also occur in patients without cancer. Results: We anticipate discovering multiple significant associations between commonly used drugs and the survival outcomes of patients with cancer. We expect to publish the initial results in the first half of 2024. Conclusions: This retrospective study may identify several commonly used drugs as candidates for repurposing in the treatment of various cancers. All analyses are considered exploratory; therefore, the results will have to be confirmed in subsequent clinical trials. However, the results of this study may accelerate drug discovery in oncology. International Registered Report Identifier (IRRID): DERR1-10.2196/48925
- Open Access
- 5 October 2023
- Published by Taylor & Francis in Disability and Rehabilitation: Assistive Technology
- Vol. 19 (5) , 2095-2112
Two decades of assistive technologies to empower people with disability: a systematic mapping study
Information and Communication Technologies have transformed our lives in different social areas, facilitating interpersonal relationships thanks to technological tools. In the specific case of people with disabilities, Assistive Technologies (ATs) break down barriers and increase opportunities to become active members of society with equal opportunities. This paper presents a systematic mapping study that analyzes the current state-of-the-art of ATs proposed in the literature to support the empowering of people with disability. Specifically, this paper focuses on (1) describing a global vision of the scientific literature published in the last 20 years about ATs in the computer science field and (2) identifying research needs, gaps, and trends. For this purpose, an in-depth analysis of 389 primary studies is presented. The information obtained from the mapping process is also constrained. Concretely, 35 ATs versus 22 disabilities are compared, obtaining striking peaks for some disabilities described in the discussion. Finally, the findings show that several areas have been covered only lightly, revealing interesting future directions and challenges for junior researchers.
- 5 October 2023
- Published by Taylor & Francis in Disability and Rehabilitation: Assistive Technology
- Vol. 19 (5) , 2095-2112
Open AccessTwo decades of assistive technologies to empower people with disability: a systematic mapping study
Information and Communication Technologies have transformed our lives in different social areas, facilitating interpersonal relationships thanks to technological tools. In the specific case of people with disabilities, Assistive Technologies (ATs) break down barriers and increase opportunities to become active members of society with equal opportunities. This paper presents a systematic mapping study that analyzes the current state-of-the-art of ATs proposed in the literature to support the empowering of people with disability. Specifically, this paper focuses on (1) describing a global vision of the scientific literature published in the last 20 years about ATs in the computer science field and (2) identifying research needs, gaps, and trends. For this purpose, an in-depth analysis of 389 primary studies is presented. The information obtained from the mapping process is also constrained. Concretely, 35 ATs versus 22 disabilities are compared, obtaining striking peaks for some disabilities described in the discussion. Finally, the findings show that several areas have been covered only lightly, revealing interesting future directions and challenges for junior researchers.
- Open Access
- 12 May 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Drug Repurposing for Cancers With Limited Survival: Protocol for a Retrospective Cohort Study (Preprint)
BACKGROUND Only 5% of the molecules tested in oncology phase 1 trials reach the market after an average of 7.5 years of waiting and at a cost of tens of millions of dollars. To reduce the cost and shorten the time of discovery of new treatments, “drug repurposing” (research with molecules already approved for another indication) and the use of secondary data (not collected for the purpose of research) have been proposed. Due to advances in informatics in clinical care, secondary data can, in some cases, be of equal quality to primary data generated through prospective studies. OBJECTIVE The objective of this study is to identify drugs currently marketed for other indications that may have an effect on the prognosis of patients with cancer. METHODS We plan to monitor a cohort of patients with high-lethality cancers treated in the public health system of Catalonia between 2006 and 2012, retrospectively, for survival for 5 years after diagnosis or until death. A control cohort, comprising people without cancer, will also be retrospectively monitored for 5 years. The following study variables will be extracted from different population databases: type of cancer (patients with cancer cohort), date and cause of death, pharmacological treatment, sex, age, and place of residence. During the first stage of statistical analysis of the patients with cancer cohort, the drugs consumed by the long-term survivors (alive at 5 years) will be compared with those consumed by nonsurvivors. In the second stage, the survival associated with the consumption of each relevant drug will be analyzed. For the analyses, groups will be matched for potentially confounding variables, and multivariate analyses will be performed to adjust for residual confounding variables if necessary. The control cohort will be used to verify whether the associations found are exclusive to patients with cancer or whether they also occur in patients without cancer. RESULTS We anticipate discovering multiple significant associations between commonly used drugs and the survival outcomes of patients with cancer. We expect to publish the initial results in the first half of 2024. CONCLUSIONS This retrospective study may identify several commonly used drugs as candidates for repurposing in the treatment of various cancers. All analyses are considered exploratory; therefore, the results will have to be confirmed in subsequent clinical trials. However, the results of this study may accelerate drug discovery in oncology. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/48925
- 12 May 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessDrug Repurposing for Cancers With Limited Survival: Protocol for a Retrospective Cohort Study (Preprint)
BACKGROUND Only 5% of the molecules tested in oncology phase 1 trials reach the market after an average of 7.5 years of waiting and at a cost of tens of millions of dollars. To reduce the cost and shorten the time of discovery of new treatments, “drug repurposing” (research with molecules already approved for another indication) and the use of secondary data (not collected for the purpose of research) have been proposed. Due to advances in informatics in clinical care, secondary data can, in some cases, be of equal quality to primary data generated through prospective studies. OBJECTIVE The objective of this study is to identify drugs currently marketed for other indications that may have an effect on the prognosis of patients with cancer. METHODS We plan to monitor a cohort of patients with high-lethality cancers treated in the public health system of Catalonia between 2006 and 2012, retrospectively, for survival for 5 years after diagnosis or until death. A control cohort, comprising people without cancer, will also be retrospectively monitored for 5 years. The following study variables will be extracted from different population databases: type of cancer (patients with cancer cohort), date and cause of death, pharmacological treatment, sex, age, and place of residence. During the first stage of statistical analysis of the patients with cancer cohort, the drugs consumed by the long-term survivors (alive at 5 years) will be compared with those consumed by nonsurvivors. In the second stage, the survival associated with the consumption of each relevant drug will be analyzed. For the analyses, groups will be matched for potentially confounding variables, and multivariate analyses will be performed to adjust for residual confounding variables if necessary. The control cohort will be used to verify whether the associations found are exclusive to patients with cancer or whether they also occur in patients without cancer. RESULTS We anticipate discovering multiple significant associations between commonly used drugs and the survival outcomes of patients with cancer. We expect to publish the initial results in the first half of 2024. CONCLUSIONS This retrospective study may identify several commonly used drugs as candidates for repurposing in the treatment of various cancers. All analyses are considered exploratory; therefore, the results will have to be confirmed in subsequent clinical trials. However, the results of this study may accelerate drug discovery in oncology. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/48925