Search

In anticipation of potential future pandemics, we examined the challenges and opportunities presented by the COVID-19 outbreak. This analysis highlights how artificial intelligence (AI) and predictive models can support both patients and clinicians in managing subsequent infectious diseases, and how legislators and policymakers could support these efforts, to bring learning healthcare system (LHS) from guidelines to real-world implementation. This report chronicles the trajectory of the COVID-19 pandemic, emphasizing the diverse data sets generated throughout its course. We propose strategies for harnessing this data via AI and predictive modelling to enhance the functioning of LHS. The challenges faced by patients and healthcare systems around the world during this unprecedented crisis could have been mitigated with an informed and timely adoption of the three pillars of the LHS: Knowledge, Data and Practice. By harnessing AI and predictive analytics, we can develop tools that not only detect potential pandemic-prone diseases early on but also assist in patient management, provide decision support, offer treatment recommendations, deliver patient outcome triage, predict post-recovery long-term disease impacts, monitor viral mutations and variant emergence, and assess vaccine and treatment efficacy in real-time. A patient-centric approach remains paramount, ensuring patients are both informed and actively involved in disease mitigation strategies.

ABSTRACTLand cover and land use have established effects on hazard and exposure to vector-borne diseases. While our understanding of the proximate and distant causes and consequences of land use decisions has evolved, the focus on the proximate effects of landscape on disease ecology remains dominant. We argue that land use governance, viewed through a land system lens, affects tick-borne disease risk. Governance affects land use trajectories and potentially shapes landscapes favourable to ticks or increases contact with ticks by structuring human-land interactions. We illustrate the role of land use legacies, trade-offs in land-use decisions, and social inequities in access to land resources, information and decision-making, with three cases: Kyasanur Forest disease in India, Lyme disease in the Outer Hebrides (Scotland), and tick acaricide resistance in cattle in Ecuador. Land use governance is key to managing the risk of tick-borne diseases, by affecting the hazard and exposure. We propose that land use governance should consider unintended consequences on infectious disease risk.

Effective long-term management of invasive non-native species (INNS) in South America is a pressing yet complex task. Critically, the environmental, historical, cultural, and economic idiosyncrasies of the region call for the inclusion of a plurality of views from those sectors of society receiving the negative and positive impacts of INNS. This is a multifaceted, and often daunting, task that can be aided by an early identification of stakeholders – those affected by or with an interest in INNS and their management – accompanied by targeted stakeholder engagement. Here, we report the procedures and results of a stakeholder mapping activity aimed at identifying stakeholders and designing engagement strategies. Using expert knowledge procedures, we compiled comprehensive lists of stakeholders for six case-studies in South America: (i) invasive grasses (Urochloa spp.) in Brazil; (ii) glossy privet (Ligustrum lucidum) in Argentina; (iii) lodgepole and Monterey pines (Pinus contorta and P. radiata) in Argentina; (iv) American mink (Neogale vison) in Argentina and Chile; (v) lodgepole and Monterey pines in Chile; and (vi) German yellow-jacket (Vespula germanica) in Chile. Overall, we identified 250 stakeholders, which, based on their interest and influence, were classified into “context settlers” (2%), “key players” (47%), “crowd” (5%), and “subjects” (49%). We outlined strategies to engage with each of these four groups and for each of our six case-studies. Across case studies, communication with stakeholders was the most common engagement strategy proposed (27%; 19 of 70 strategies), followed by active involvement of stakeholders in INNS research and management (23%). Our results highlight the importance of considering power imbalances, as those stakeholders more likely to benefit from INNS were assessed to have more influence over INNS management relative to local and indigenous communities. Our work illustrates how to identify stakeholders in a rigorous and rapid manner, which should be complemented with the involvement of the stakeholders themselves.

IntroductionMagnetic resonance imaging (MRI) is crucial for diagnosing and monitoring of multiple sclerosis (MS) as it is used to assess lesions in the brain and spinal cord. However, in real-world clinical settings, MRI scans are often acquired with thick slices, limiting their utility for automated quantitative analyses. This work presents a single-image super-resolution (SR) reconstruction framework that leverages SR convolutional neural networks (CNN) to enhance the through-plane resolution of structural MRI in people with MS (PwMS).MethodsOur strategy involves the supervised fine-tuning of CNN architectures, guided by a content loss function that promotes perceptual quality, as well as reconstruction accuracy, to recover high-level image features.ResultsExtensive evaluation with MRI data of PwMS shows that our SR strategy leads to more accurate MRI reconstructions than competing methods. Furthermore, it improves lesion segmentation on low-resolution MRI, approaching the performance achievable with high-resolution images.DiscussionResults demonstrate the potential of our SR framework to facilitate the use of low-resolution retrospective MRI from real-world clinical settings to investigate quantitative image-based biomarkers of MS.

Abstract Background Clostridium spp. has demonstrated therapeutic potential in cancer treatment through intravenous or intratumoral administration. This approach has expanded to include non-pathogenic clostridia for the treatment of various diseases, underscoring the innovative concept of oral-spore vaccination using clostridia. Recent advancements in the field of synthetic biology have significantly enhanced the development of Clostridium-based bio-therapeutics. These advancements are particularly notable in the areas of efficient protein overexpression and secretion, which are crucial for the feasibility of oral vaccination strategies. Here, we present two examples of genetically engineered Clostridium candidates: one as an oral cancer vaccine and the other as an antiviral oral vaccine against SARS-CoV-2. Results Using five validated promoters and a signal peptide derived from Clostridium sporogenes, a series of full-length NY-ESO-1/CTAG1, a promising cancer vaccine candidate, expression vectors were constructed and transformed into C. sporogenes and Clostridium butyricum. Western blotting analysis confirmed efficient expression and secretion of NY-ESO-1 in clostridia, with specific promoters leading to enhanced detection signals. Additionally, the fusion of a reported bacterial adjuvant to NY-ESO-1 for improved immune recognition led to the cloning difficulties in E. coli. The use of an AUU start codon successfully mitigated potential toxicity issues in E. coli, enabling the secretion of recombinant proteins in C. sporogenes and C. butyricum. We further demonstrate the successful replacement of PyrE loci with high-expression cassettes carrying NY-ESO-1 and adjuvant-fused NY-ESO-1, achieving plasmid-free clostridia capable of secreting the antigens. Lastly, the study successfully extends its multiplex genetic manipulations to engineer clostridia for the secretion of SARS-CoV-2-related Spike_S1 antigens. Conclusions This study successfully demonstrated that C. butyricum and C. sporogenes can produce the two recombinant antigen proteins (NY-ESO-1 and SARS-CoV-2-related Spike_S1 antigens) through genetic manipulations, utilizing the AUU start codon. This approach overcomes challenges in cloning difficult proteins in E. coli. These findings underscore the feasibility of harnessing commensal clostridia for antigen protein secretion, emphasizing the applicability of non-canonical translation initiation across diverse species with broad implications for medical or industrial biotechnology.

Abstract Here, we establish a CT-radiomics based method for application in invasive, orthotopic rodent brain tumour models. Twenty four NOD/SCID mice were implanted with U87R-Luc2 GBM cells and longitudinally imaged via contrast enhanced (CE-CT) imaging. Pyradiomics was employed to extract CT-radiomic features from the tumour-implanted hemisphere and non-tumour-implanted hemisphere of acquired CT-scans. Inter-correlated features were removed (Spearman correlation > 0.85) and remaining features underwent predictive analysis (recursive feature elimination or Boruta algorithm). An area under the curve of the receiver operating characteristic curve was implemented to evaluate radiomic features for their capacity to predict defined outcomes. Firstly, we identified a subset of radiomic features which distinguish the tumour-implanted hemisphere and non- tumour-implanted hemisphere (i.e, tumour presence from normal tissue). Secondly, we successfully translate preclinical CT-radiomic pipelines to GBM patient CT scans (n = 10), identifying similar trends in tumour-specific feature intensities (E.g. ‘glszm Zone Entropy’), thereby suggesting a mouse-to-human species conservation (a conservation of radiomic features across species). Thirdly, comparison of features across timepoints identify features which support preclinical tumour detection earlier than is possible by visual assessment of CT scans. This work establishes robust, preclinical CT-radiomic pipelines and describes the application of CE-CT for in-depth orthotopic brain tumour monitoring. Overall we provide evidence for the role of pre-clinical ‘discovery’ radiomics in the neuro-oncology space.

Abstract The modification of landscapes is increasing the interface between humans and wildlife, while conflicts concerning predator impacts on human activities persist. Some previously persecuted but now protected predator species are experiencing recovery and range expansion. Tolerance is considered essential for achieving coexistence between humans and wildlife; however, its conceptualisation remains unresolved. Little is known about tolerance in the context of recovering predators, particularly which drivers are relevant to all or specific species and human interests. Using an online questionnaire survey shared with members of organisations with interests in rural land‐based activities, we collected data on interests and beliefs, and attitudes, perceptions, experience and management preferences for six recovering vertebrate predators in the United Kingdom (n = 819). We created a species tolerance score representing the management choices of the respondents in different conflict scenarios, which differed in the degree of impact on the predator population. Our species tolerance score was characterised by a complex combination of the interests and beliefs of the respondents about wildlife management, perceptions and experience of that species (perceived benefits, population trend, positive and negative experience, indirect negative experience) and negative experience of other recovering predators. We found a tolerance gradient between interest groups with notable overlap between groups with primary interests in wildlife conservation, shooting, farming and fishing. Although higher perceived benefits consistently corresponded to higher tolerance, having a negative experience of the species dampened the effect of perceived benefits on tolerance. When both negative personal and indirect experiences were reported, tolerance was dramatically reduced. The classification of species from least to most tolerated was consistent between interest groups. The application of our species tolerance score as the normative dimension (i.e. acceptability) in Brenner and Metcalf's (2020) Social Tolerance of Wildlife Framework highlights that tolerance (negative attitude—high acceptability) is potentially rare and more positive attitudes must be achieved before acceptance of the impacts of species can increase. Our findings highlight that considering only primary interests may hinder debates concerning recovering predators. Strategies to reduce negative experiences or change how they are perceived could significantly increase tolerance in combination with increasing positive experiences. Read the free Plain Language Summary for this article on the Journal blog.

ObjectiveColorectal cancer (CRC) is one of the most prevalent cancers worldwide. A considerable percentage of patients who undergo surgery with curative intent will experience cancer recurrence. Early identification of individuals with a higher risk of recurrence is crucial for healthcare professionals to intervene promptly and devise appropriate treatment strategies. In this study, we developed prognostic models for CRC recurrence using machine learning models on a limited number of CEA measurements.MethodA dataset of 1927 patients diagnosed with Stage I-III CRC and referred to Zuyderland Hospital for surgery between 2008 and 2016 was utilized. Machine learning models were trained using this comprehensive dataset, which included demographic details, clinicopathological factors, and serial measurements of Carcinoembryonic Antigen (CEA). In this study, the predictive performance of these models was assessed, and the key prognostic factors influencing colorectal cancer (CRC) recurrence were pinpointedResultAmong the evaluated models, the gradient boosting classifier demonstrated superior performance, achieving an Area Under the Curve (AUC) score of 0.81 and a balanced accuracy rate of 0.73. Recurrence prediction was shown to be feasible with an AUC of 0.71 when using only five post-operative CEA measurements. Furthermore, key factors influencing recurrence were identified and elucidated.ConclusionThis study shows the transformative role of machine learning in recurrence prediction for CRC, particularly by investigating the minimum number of CEA measurements required for effective recurrence prediction. This approach not only contributes to the optimization of clinical workflows but also facilitates the development of more effective, individualized treatment plans, thereby laying the groundwork for future advancements in this area. Future directions involve validating these models in larger and more diverse cohorts. Building on these efforts, our ultimate goal is to develop a risk-based follow-up strategy that can improve patient outcomes and enhance healthcare efficiency.

The aim of this study was to develop and evaluate a proof-of-concept open-source individualized Patient Decision Aid (iPDA) with a group of patients, physicians, and computer scientists. The iPDA was developed based on the International Patient Decision Aid Standards (IPDAS). A previously published questionnaire was adapted and used to test the user-friendliness and content of the iPDA. The questionnaire contained 40 multiple-choice questions, and answers were given on a 5-point Likert Scale (1–5) ranging from “strongly disagree” to “strongly agree.” In addition to the questionnaire, semi-structured interviews were conducted with patients. We performed a descriptive analysis of the responses. The iPDA was evaluated by 28 computer scientists, 21 physicians, and 13 patients. The results demonstrate that the iPDA was found valuable by 92% (patients), 96% (computer scientists), and 86% (physicians), while the treatment information was judged useful by 92%, 96%, and 95%, respectively. Additionally, the tool was thought to be motivating for patients to actively engage in their treatment by 92%, 93%, and 91% of the above respondents groups. More multimedia components and less text were suggested by the respondents as ways to improve the tool and user interface. In conclusion, we successfully developed and tested an iPDA for patients with stage I–II Non-Small Cell Lung Cancer (NSCLC).

Global warming has already substantially altered the Arctic cryosphere. Due to the Arctic warming amplification, the temperature is increasing more strongly, leading to pervasive changes in this area. Recent years were notably marked by melt records over the Greenland Ice Sheet, while other regions such as Svalbard seem to remain less influenced. This raises the question of the current state of the Greenland Ice Sheet and the various ice caps in the Arctic for which few studies are available. Here, we run the regional climate model (RCM) Modèle Atmosphérique Régional (MAR) at a resolution of 6 km over four different domains covering all Arctic land ice to produce a unified surface mass balance product from 1950 to the present day. We also compare our results to large-scale indices to better understand the heterogeneity of the evolutions across the Arctic and their links to recent climate change. We find a sharp decrease of surface mass balance (SMB) over the western Arctic (Canada and Greenland) in relationship with the atmospheric blocking situations that have become more frequent in summer, resulting in a 41 % increase of the melt rate since 1950. This increase is not seen over the Russian Arctic permanent ice areas, where melt rates have increased by only 3 % on average, illustrating a heterogeneity in the Arctic SMB response to global warming.

Many organisms live in fragmented populations, which has profound consequences on the dynamics of associated parasites. Metapopulation theory offers a canonical framework for predicting the effects of fragmentation on spatiotemporal host–parasite dynamics. However, empirical studies of parasites in classical metapopulations remain rare, particularly for vector-borne parasites. Here, we quantify spatiotemporal patterns and possible drivers of infection probability for several ectoparasites (fleas, Ixodes trianguliceps and Ixodes ricinus) and vector-borne microparasites (Babesia microti, Bartonella spp., Hepatozoon spp.) in a classically functioning metapopulation of water vole hosts. Results suggest that the relative importance of vector or host dynamics on microparasite infection probabilities is related to parasite life-histories. Bartonella, a microparasite with a fast life-history, was positively associated with both host and vector abundances at several spatial and temporal scales. In contrast, B. microti, a tick-borne parasite with a slow life-history, was only associated with vector dynamics. Further, we provide evidence that life-history shaped parasite dynamics, including occupancy and colonization rates, in the metapopulation. Lastly, our findings were consistent with the hypothesis that landscape connectivity was determined by distance-based dispersal of the focal hosts. We provide essential empirical evidence that contributes to the development of a comprehensive theory of metapopulation processes of vector-borne parasites.

IntroductionThere is a cumulative risk of 20-40% of developing brain metastases (BM) in solid cancers. Stereotactic radiotherapy (SRT) enables the application of high focal doses of radiation to a volume and is often used for BM treatment. However, SRT can cause adverse radiation effects (ARE), such as radiation necrosis, which sometimes cause irreversible damage to the brain. It is therefore of clinical interest to identify patients at a high risk of developing ARE. We hypothesized that models trained with radiomics features, deep learning (DL) features, and patient characteristics or their combination can predict ARE risk in patients with BM before SRT.MethodsGadolinium-enhanced T1-weighted MRIs and characteristics from patients treated with SRT for BM were collected for a training and testing cohort (N = 1,404) and a validation cohort (N = 237) from a separate institute. From each lesion in the training set, radiomics features were extracted and used to train an extreme gradient boosting (XGBoost) model. A DL model was trained on the same cohort to make a separate prediction and to extract the last layer of features. Different models using XGBoost were built using only radiomics features, DL features, and patient characteristics or a combination of them. Evaluation was performed using the area under the curve (AUC) of the receiver operating characteristic curve on the external dataset. Predictions for individual lesions and per patient developing ARE were investigated.ResultsThe best-performing XGBoost model on a lesion level was trained on a combination of radiomics features and DL features (AUC of 0.71 and recall of 0.80). On a patient level, a combination of radiomics features, DL features, and patient characteristics obtained the best performance (AUC of 0.72 and recall of 0.84). The DL model achieved an AUC of 0.64 and recall of 0.85 per lesion and an AUC of 0.70 and recall of 0.60 per patient.ConclusionMachine learning models built on radiomics features and DL features extracted from BM combined with patient characteristics show potential to predict ARE at the patient and lesion levels. These models could be used in clinical decision making, informing patients on their risk of ARE and allowing physicians to opt for different therapies.

ABSTRACT Clostridium species have gained attention in industrial and medical applications, and the development of genetic tools has enabled the advancement of the CRISPR-Cas systems for these bacteria. Compared to the primarily used Cas9 from Streptococcus pyogenes, the utilization of Cas12a (previously known as Cpf1) proteins remains incomplete in clostridia, although they exhibit potential advantages, including T-rich recognition for Clostridium genomes and lower toxicity. In this study, we expanded the CRISPR-Cas tools in clostridia by establishing a CRISPR-Cas12a system with two different cas12a genes (Ascas12a from Acidaminococcus and Fncas12a from Francisella novicida). The optimized tetracycline-inducible systems were initially determined by the glucuronidase reporter and were used to drive expression of the cas12a genes and crRNAs. Our results demonstrate that the CRISPR-FnCas12a system offers flexible target selection in clostridia, and a specific folding pattern of the precursor crRNA is important to enable high mutation generation efficiency. By using sacB (encoding levansucrase) as a negative marker for plasmid curing and determining the optimal size of the donor DNA template for gene integration in the CRISPR-FnCas12a system, we achieved highly efficient and rapid genome modification, exemplified by the successful engineering of clostridia (Clostridium butyricum and Clostridium sporogenes) to produce near-infrared fluorescence from biliverdin and hemin. IMPORTANCE Continued efforts in developing the CRISPR-Cas systems will further enhance our understanding and utilization of Clostridium species. This study demonstrates the development and application of a genome-engineering tool in two Clostridium strains, Clostridium butyricum and Clostridium sporogenes, which have promising potential as probiotics and oncolytic agents. Particular attention was given to the folding of precursor crRNA and the role of this process in off-target DNA cleavage by Cas12a. The results provide the guidelines necessary for efficient genome engineering using this system in clostridia. Our findings not only expand our fundamental understanding of genome-engineering tools in clostridia but also improve this technology to allow use of its full potential in a plethora of biotechnological applications.

A Correction to this paper has been published: https://doi.org/10.1038/s41467-021-22418-3

PurposeNatural American Spirit (NAS) cigarettes, which have recently grown in popularity, are marketed as eco-friendly and natural. The present study examined whether NAS's on-the-pack messaging influences adolescents' health perceptions of the brand.MethodsIn a mixed-factor design, adolescent participants (N = 1,003, ages 13-17, 75% female) were randomized to one of the six exposure conditions. All viewed images of an NAS and a Pall Mall (comparison brand) cigarette pack, but differed in pack color (blue, green, or gold/orange) and brand viewed first. Perceptions of pack logos, addictiveness, harms to the smoker, others, and the environment were assessed directly after viewing pack images for each brand.ResultsAdolescents who perceived NAS as more pro-environment tended to perceive NAS cigarettes to be less addictive, r = -.19, p < .01. NAS cigarettes also were perceived as less addictive and better for the environment than Pall Mall. Most (90%) participants provided nature-friendly words (e.g., environment, recycle) when asked to describe logos on the NAS packs. In adjusted models, relative to Pall Mall, NAS was perceived as healthier for smokers, healthier for smokers' family and friends, and safer for the environment. Findings did not differ by pack color and ever tobacco use.ConclusionsAdolescents perceived a health advantage for NAS cigarettes with its on-the-pack, eco-friendly and pro-health marketing. The findings are consistent with prior research with adults. Given the accumulating evidence of consumer misperceptions, eco-friendly messaging on cigarettes is a public health concern that warrants further consideration for regulatory intervention.

Abstract Background Current frequent follow-up after treatment for breast cancer does not meet its intended aims, but does depend on expensive and scarce specialized knowledge for routine history taking and physical examinations. The study described in this paper compared patient satisfaction with a reduced follow-up strategy, i.e. nurse-led telephone follow-up, to satisfaction with traditional hospital follow-up. Methods Patient satisfaction was assessed among patients (n = 299) who were participants of a randomized controlled trial investigating the cost-effectiveness of several follow-up strategies in the first year after treatment for breast cancer. Data on patient satisfaction were collected at baseline, three, six and 12 months after treatment, using the Dutch version of Ware's Patient Satisfaction Questionnaire III (PSQ III). In addition to general satisfaction, the PSQ III reports on satisfaction scores for technical competence, interpersonal aspects, and access of care. Regression analysis was used to predict satisfaction scores from whether or not nurse-led telephone follow-up was received. Results Nurse-led telephone follow-up had no statistically significant influence on general patient satisfaction (p = 0.379), satisfaction with technical competence (p = 0.249), and satisfaction with interpersonal aspects (p = 0.662). Regarding access of care, patient satisfaction scores were significantly higher for patients receiving telephone follow-up (p = 0.015). However, a mean difference at 12 months of 3.1 points was judged to be not clinically relevant. Conclusions No meaningful differences were found in satisfaction scores between nurse-led telephone and hospital follow-up in the first year after breast cancer treatment. With high satisfaction scores and the potential to substantially reduce clinic visits, nurse-led telephone follow-up may be an acceptable alternative to traditional hospital follow-up. Trial registration number ISRCTN 74071417.

Abstract The paper deals with the evaluation of the performance of an existing and previously validated CT based radiomic signature, developed in oropharyngeal cancer to predict human papillomavirus (HPV) status, in the context of anal cancer. For the validation in anal cancer, a dataset of 59 patients coming from two different centers was collected. The primary endpoint was HPV status according to p16 immunohistochemistry. Predefined statistical tests were performed to evaluate the performance of the model. The AUC obtained here in anal cancer is 0.68 [95% CI (0.32–1.00)] with F1 score of 0.78. This signature is TRIPOD level 4 (57%) with an RQS of 61%. This study provides proof of concept that this radiomic signature has the potential to identify a clinically relevant molecular phenotype (i.e., the HPV-ness) across multiple cancers and demonstrates potential for this radiomic signature as a CT imaging biomarker of p16 status.

Abstract Rodent pests can have major social, economic, and environmental impacts. Their management, therefore, represents a complex socio‐ecological problem involving a network of stakeholders from across different sectors, with diverging and sometimes competing interests. Failure to incorporate stakeholder interests can result in ineffective or unsustainable management programmes, with unintended negative consequences for people and nature. Participatory approaches to decision‐making have been proposed as suitable strategies to tackle complex problems, yet, these processes are often considered too difficult, costly, or time‐consuming to implement. To facilitate a participatory approach to rodent control in Madagascar, we identified and mapped key stakeholders and developed a multisector framework for guiding rodent management programmes based on current literature and expert recommendations. We then carried out interviews and focus groups with stakeholders and end‐users to validate the final framework. The final framework unifies stakeholder interests around the dimensions of People, Resources, Knowledge and Power. Combined application of the stakeholder map and framework provides decision‐makers with the tools to identify stakeholder interests; to explore areas of conflict, as well as areas of agreement; and to ensure that these are addressed within the design of control programmes. As an assessment tool, the framework can also be used to evaluate the responsiveness of programmes to the needs of different stakeholders and assess whether objectives are being reached. We recommend the application of the stakeholder map and framework to encourage and strengthen participatory approaches aimed at rodent pest control. Due to the inclusive and interdisciplinary nature of the framework, it can be applied to address numerous complex social, environmental, and economic issues across scales, sectors, and systems. Read the free Plain Language Summary for this article on the Journal blog.

Abstract Background/aim The EQ-5D is a generic health-related quality of life (HRQoL) measure that is used for the purpose of economic evaluations of health interventions. Therefore, it has to be responsive to meaningful changes in health in the patient population under investigation. The aim of this study was to investigate the responsiveness of the EQ-5D in breast cancer patients in their first year after treatment. Methods The subscale global health of the disease-specific HRQoL measure EORTC QLQ-C30 was used as a reference instrument to determine meaningful changes in health and identify subgroups of patients: patients reporting a moderate-large deterioration, small deterioration, a small improvement, moderate-large improvement, or no change in health status. Responsiveness was evaluated by calculating standardized response means (SRMs) in the five subgroups of patients and performing analysis of variance procedures. The two HRQoL measures were filled out two weeks and one year after finalizing curative treatment for breast cancer (n = 192). Results The EQ-5D was able to capture both improvements and deteriorations in HRQoL. SRMs of the EQ VAS and EQ-5D Index were close to zero in the subgroup reporting no change and increased and decreased adequately in the subgroups reporting small and moderate changes. Additional analysis of variance procedures showed that the EQ-5D was able to differentiate between subgroups of patients with no change and moderate-large deterioration or improvement in health. Conclusion The EQ-5D seems an appropriate measure for the purpose of economic evaluations of health intervention in breast cancer patients after treatment. Trial registration Current Controlled Trials ISRCTN74071417.

Abstract Background After curative treatment for breast cancer women frequently attend scheduled follow-up examinations. Usually the follow-up is most frequent in the first 2–3 years (2–4 times a year); thereafter the frequency is reduced to once a year in most countries. Its main aim is to detect local disease recurrence, or a second primary breast cancer, but also to provide information and psychosocial support. However, the cost-effectiveness of these frequent visits is under much debate, leading to a search for less intensive and more cost-effective follow-up strategies. In this paper the design of the MaCare trial is described. This trial compares the cost-effectiveness of four follow-up strategies for curatively treated breast cancer patients. We investigate the costs and effects of nurse-led telephone follow-up and a short educational group programme. Methods/design The MaCare trial is a multi centre randomised clinical trial in which 320 breast cancer patients are randomised into four follow-up strategies, focussed on the first 18 months after treatment: 1) standard follow-up; 2) nurse-led telephone follow-up; 3) arm 1 with the educational group programme; 4) arm 2 with the educational group programme. Data is collected at baseline and 3, 6, 12 and 18 months after treatment. The primary endpoint of the trial is cancer-specific quality of life as measured by the global health/QoL scale of the EORTC QLQ-C30. Secondary outcomes are perceived feelings of control, anxiety, patients' satisfaction with follow-up and costs. A cost-effectiveness analysis will be performed from a societal perspective. Discussion Reduced follow-up strategies for breast cancer have not yet been widely applied in clinical practice. Improvement of psychosocial support and information to patients could lead to a better acceptance of reduced follow-up. The MaCare trial combines a reduced follow-up strategy with additional psychosocial support. Less frequent follow-up can reduce the burden on medical specialists and costs. The educational group programme can improve QoL of patients, but also less frequent follow-up can improve QoL by reducing the anxiety experienced for each follow-up visit. Results of the trial will provide knowledge on both costs and psychosocial aspects regarding follow-up and are expected in 2009.

Purpose. This multicenter retrospective study aims to identify reliable clinical and radiomic features to build machine learning models that predict progression-free survival (PFS) and overall survival (OS) in pancreatic ductal adenocarcinoma (PDAC) patients. Methods. Between 2010 and 2020 pre-treatment contrast-enhanced CT scans of 287 pathology-confirmed PDAC patients from two sites of the Hopital Universitaire de Bruxelles (HUB) and from 47 hospitals within the HUB network were retrospectively analysed. Demographic, clinical, and survival data were also collected. Gross tumour volume (GTV) and non-tumoral pancreas (RPV) were semi-manually segmented and radiomics features were extracted. Patients from two HUB sites comprised the training dataset, while those from the remaining 47 hospitals of the HUB network constituted the testing dataset. A three-step method was used for feature selection. Based on the GradientBoostingSurvivalAnalysis classifier, different machine learning models were trained and tested to predict OS and PFS. Model performances were assessed using the C-index and Kaplan–Meier curves. SHAP analysis was applied to allow for post hoc interpretability. Results. A total of 107 radiomics features were extracted from each of the GTV and RPV. Fourteen subgroups of features were selected: clinical, GTV, RPV, clinical & GTV, clinical & GTV & RPV, GTV-volume and RPV-volume both for OS and PFS. Subsequently, 14 Gradient Boosting Survival Analysis models were trained and tested. In the testing dataset, the clinical & GTV model demonstrated the highest performance for OS (C-index: 0.72) among all other models, while for PFS, the clinical model exhibited a superior performance (C-index: 0.70). Conclusions. An integrated approach, combining clinical and radiomics features, excels in predicting OS, whereas clinical features demonstrate strong performance in PFS prediction.