In practical electrocardiography (ECG) interpretation, the scarcity of well-annotated data is a common challenge. Transfer learning techniques are valuable in such situations, yet the assessment of transferability has received limited attention. To tackle this issue, we introduce MELEP, which stands for Muti-label Expected Log of Empirical Predictions, a measure designed to estimate the effectiveness of knowledge transfer from a pre-trained model to a downstream multi-label ECG diagnosis task. MELEP is generic, working with new target data with different label sets, and computationally efficient, requiring only a single forward pass through the pre-trained model. To the best of our knowledge, MELEP is the first transferability metric specifically designed for multi-label ECG classification problems. Our experiments show that MELEP can predict the performance of pre-trained convolutional and recurrent deep neural networks, on small and imbalanced ECG data. Specifically, we observed strong correlation coefficients (with absolute values exceeding 0.6 in most cases) between MELEP and the actual average F1 scores of the fine-tuned models. Our work highlights the potential of MELEP to expedite the selection of suitable pre-trained models for ECG diagnosis tasks, saving time and effort that would otherwise be spent on fine-tuning these models.

BACKGROUND: Countries designing a health benefit package (HBP) to support progress towards universal health coverage (UHC) require robust cost-effectiveness evidence. This paper reports on Pakistan\'s approach to assessing the applicability of global cost-effectiveness evidence to country context as part of a HBP design process.
METHODS: A seven-step process was developed and implemented with Disease Control Priority 3 (DCP3) project partners to assess the applicability of global incremental cost-effectiveness ratios (ICERs) to Pakistan. First, the scope of the interventions to be assessed was defined and an independent, interdisciplinary team was formed. Second, the team familiarized itself with intervention descriptions. Third, the team identified studies from the Tufts Medical School Global Health Cost-Effectiveness Analysis (GH-CEA) registry. Fourth, the team applied specific knock-out criteria to match identified studies to local intervention descriptions. Matches were then cross-checked across reviewers and further selection was made where there were multiple ICER matches. Sixth, a quality scoring system was applied to ICER values. Finally, a database was created containing all the ICER results with a justification for each decision, which was made available to decision-makers during HBP deliberation.
RESULTS: We found that less than 50% of the interventions in DCP3 could be supported with evidence of cost-effectiveness applicable to the country context. Out of 78 ICERs identified as applicable to Pakistan from the Tufts GH-CEA registry, only 20 ICERs were exact matches of the DCP3 Pakistan intervention descriptions and 58 were partial matches.
CONCLUSIONS: This paper presents the first attempt globally to use the main public GH-CEA database to estimate cost-effectiveness in the context of HBPs at a country level. This approach is a useful learning for all countries trying to develop essential packages informed by the global database on ICERs, and it will support the design of future evidence and further development of methods.

BACKGROUND: One of the crucial issues related to machine learning potentials is the formation of representative dataset. For multicomponent systems, it is a general methodology to scan the composition range with a certain step. However, there is a lack of information on the compositional transferability of machine learning potentials. In this paper, we extend the knowledge in this area by studying the transferability of deep learning potential over the range of compositions of LiCl-KCl molten mixtures. The training dataset was formed using only the near-eutectic composition of 60% LiCl-40% KCl. Then, we tested the ability of the model to predict physicochemical properties of the melts far from the reference composition. It was found that for the composition range from 0 to 100% of LiCl, the calculated properties concur closely with those of other studies and ab initio calculations. Therefore, the model shows prominent non-intuitive compositional transferability. Moreover, the solid states and solid-liquid coexistence were reproduced. The calculated melting temperatures of LiCl and KCl show the errors of 6.6% and 0.4%, respectively. We argue that such good transferability stems from the local structure configurations that are typical both for pure LiCl and for pure KCl which are implicitly presented in the training dataset because of local fluctuations in composition.
METHODS: To collect the data for the initial dataset, density functional theory was employed. Then, the DeePMD package was used to train a neural network potential. To calculate the properties of the melts, standard equilibrium and non-equilibrium molecular dynamic approaches were utilized.

Because of the naturally limited anaerobic degradability and limited biogas yield of raw sludge (RS), this study aims to increase the biogas production of primary sludge (PS) and waste activated sludge (WAS) by the integration of thermal alkaline process (TAP). PH 11 is confirmed to be the most suitable pH value for the TAP of both sludges. Moreover, with the pretreatment at pH 11 and 160 °C (6 bar) for 30 min, the investigated PSs and WASs achieved an increased biogas production of up to 81 % and 72 %, respectively. The improved net electricity production of WASs after TAP varied between 15-43 % compared to conventional WAS digestion. However, the TAP of PS at pH 11 enhanced the biogas production by 1-81 %, which did not constantly contribute to an improved net electricity production.

An analysis of crash data spanning four years (January 1, 2015, to December 31, 2018) from the State of Washington is conducted to investigate factors influencing injury severity outcomes in large truck-involved crashes. The study utilizes a mixed logit model that accounts for unobserved heterogeneity to capture the variation influenced by other variables. Transferability and temporal stability across the years are assessed using the likelihood ratio test. A wide range of attributes, including driver characteristics, vehicle features, crash-related attributes, roadway conditions, environmental factors, and temporal elements, are considered. Despite a significant temporal instability warranted by the likelihood ratio test across the years, twenty-one parameters consistently exhibit stable effects on injury severity over the years of which thirteen are new. The identified stable parameters included over speeding, following too closely, falling asleep, missing/ faulty airbags, head-on collisions, crashes involving two or more than three vehicles, rear-end collisions, lane width, low-light conditions, sag curves, New Jersey barriers, snowy weather, and morning hours. The temporally stable factors affecting injury severities in large truck crashes are crucial in developing the needed to address these crashes. The findings of this study offer valuable insights for researchers, stakeholders in the trucking industry, and policymakers, empowering them to develop targeted policies that not only improve traffic safety but also alleviate associated economic losses.

Low-resolution coarse-grained (CG) models provide remarkable computational and conceptual advantages for simulating soft materials. In principle, bottom-up CG models can reproduce all structural and thermodynamic properties of atomically detailed models that can be observed at the resolution of the CG model. This review discusses recent progress in developing theory and computational methods for achieving this promise. We first briefly review variational approaches for parameterizing interaction potentials and their relationship to machine learning methods. We then discuss recent approaches for simultaneously improving both the transferability and thermodynamic properties of bottom-up models by rigorously addressing the density and temperature dependence of these potentials. We also briefly discuss exciting progress in modeling high-resolution observables with low-resolution CG models. More generally, we highlight the essential role of the bottom-up framework not only for fundamentally understanding the limitations of prior CG models but also for developing robust computational methods that resolve these limitations in practice.

In recent years, the research on transferable feature-level adversarial attack has become a hot spot due to attacking unknown deep neural networks successfully. But the following problems limit its transferability. Existing feature disruption methods often focus on computing feature weights precisely, while overlooking the noise influence of feature maps, which results in disturbing non-critical features. Meanwhile, geometric augmentation algorithms are used to enhance image diversity but compromise information integrity, which hamper models from capturing comprehensive features. Furthermore, current feature perturbation could not pay attention to the density distribution of object-relevant key features, which mainly concentrate in salient region and fewer in the most distributed background region, and get limited transferability. To tackle these challenges, a feature distribution-aware transferable adversarial attack method, called FDAA, is proposed to implement distinct strategies for different image regions in the paper. A novel Aggregated Feature Map Attack (AFMA) is presented to significantly denoise feature maps, and an input transformation strategy, called Smixup, is introduced to help feature disruption algorithms to capture comprehensive features. Extensive experiments demonstrate that scheme proposed achieves better transferability with an average success rate of 78.6% on adversarially trained models.

To eliminate malaria, all populations must be included. For those who are not reached by the health care system, specific interventions must be tailor-made. An innovative Malakit strategy, based on the distribution of self-diagnosis and self-treatment kits, has been evaluated in the Suriname-French Guiana- Amapá (Brazil) region. The results showed effectiveness and good acceptability. The Malakit intervention is complex and has many components. Its transferability requires adaptation to other populations and regions, while retaining the main features of the intervention. This article provides the keys to adapting, implementing and evaluating it in other contexts facing residual malaria in hard-to-reach and/or mobile populations. The process of transferring this intervention includes: diagnosis of the situation (malaria epidemiology, characteristics of the population affected) to define the relevance of the strategy; determination of the stakeholders and the framework of the intervention (research project or public health intervention); adaptation modalities (adaptation of the kit, training, distribution strategy); the role of community health workers and their need for training and supervision. Finally, evaluation needs are specified in relation to prospects for geographical or temporal extension. Malaria elimination is likely to increasingly involve marginalized people due to climate change and displacement of populations. Evaluation of the transferability and effectiveness of the Malakit strategy in new contexts will be essential to increase and refine the evidence of its value, and to decide whether it could be an additional tool in the arsenal recommended in future WHO guidelines.

The current study aimed to determine if the 3D-printing speed and temperature would impact the transferability of foodborne pathogens from the stainless-steel (SS) food cartridge to the 3D-printed food ink. Staphylococcus aureus and Escherichia coli were inoculated onto the interior surface of the SS food cartridges. Subsequently, a model food ink was extruded with a recommended macronutrient contribution of 55.8, 23.7, and 20.5% of carbohydrates, proteins, and fat, respectively. The impact of 3D-printing temperatures and speeds on transfer rates was analysed using a Two-Way ANOVA. S. aureus was transferred more from the cartridge to the food ink with a population of 3.39, 2.98, and 3.09 log CFU/g compared to 2.03, 2.06, and 2.00 log CFU/g for E. coli at 2000, 3000, and 4000 mm/s printing speed, respectively, at 25 °C. A Kruskal-Wallis Test was employed to investigate the effect of different speeds and temperatures on the transferability of S. aureus and E. coli. Speed was the main factor affecting S. aureus transferability, while temperature (25 and 50 °C) had the greatest impact on E. coli transferability. This research seeks to advance the understanding of 3D-printing parameters in pathogen transferability and help the food industry move towards this technology\'s quick and safe adoption.

BACKGROUND: Although behavioural interventions have been found to help control type 2 diabetes (T2D), it is important to understand how the delivery context can influence implementation and outcomes. The NHS committed to testing a low-calorie diet (LCD) programme designed to support people living with excess weight and T2D to lose weight and improve diabetes outcomes. Understanding what influenced implementation during the programme pilot is important in optimising rollout. This study explored the transferability of the NHS LCD Programme prior to wider adoption.
METHODS: Twenty-five interviews were undertaken with stakeholders involved in implementing the LCD programme in pilot sites (health service leads, referring health professionals and programme deliverers). Interviews with programme participants (people living with T2D) were undertaken within a larger programme of work, exploring what worked, for whom and why, which is reported separately. The conceptual Population-Intervention-Environment-Transfer Model of Transferability (PIET-T) guided study design and data collection. Constructs of the model were also used as a deductive coding frame during data analysis. Key themes were identified which informed recommendations to optimise programme transfer.
RESULTS: Population: Referral strategies in some areas lacked consideration of population characteristics. Many believed that offering a choice of delivery model would promote acceptability and accessibility of the eligible population.
METHODS: Overall, stakeholders had confidence in the LCD programme due to the robust evidence base along with anecdotal evidence, but some felt the complex referral process hindered engagement from GP practices.
METHODS: Stakeholders described barriers to accessing the programme, including language and learning difficulties. Transferability: Multidisciplinary working and effective communication supported successful implementation.
CONCLUSIONS: Referral strategies to reach underrepresented groups should be considered during programme transfer, along with timely data from service providers on access and programme benefits. A choice of delivery models may optimise uptake. Knowledge sharing between sites on good working practices is encouraged, including increasing engagement with key stakeholders.