A 'training of trainers' programme for operational research: increasing capacity remotely

BACKGROUND

Operational research (OR) is a process to improve health system capacity by evaluating interventions to improve health delivery and outcomes. The World Health Organization (WHO) Structured Operational Research Training Initiative (SORT-IT) programme promotes how OR contributes to improved health care delivery and health outcomes. A partnership project between the International Institute of Primary Health Care (IPHCE) in Ethiopia and The University of Queensland (UQ) in Australia modified the SORT-IT programme to deliver a hybrid Training of Trainers programme and improve OR capacity.

OBJECTIVE

This study was performed to develop and evaluate the effectiveness of Train-the Trainers approach in building capability to expand the capacity of the IPHCE to deliver the SORT-IT programme.

METHODS

Recruitment of participants and training were aligned with the principles of the SORT-IT programme. Training was face-to-face for the first session with subsequent training sessions delivered via Zoom over a 13-week period. Participants were required to complete all activities in line with SORT-IT deliverables. Slide decks supporting the SORT-IT training videos were developed and adapted to the Ethiopian context.

RESULTS

Participants had diverse experience from programme directors to research officers. All training sessions were recorded and available for participants to watch and review when required. All participants completed OR protocols to the draft stage. Course evaluation revealed participants found the content and format of the training useful, pertinent, and interesting.

CONCLUSION

A hybrid model (face-to-face and video platform) for OR training was implemented. Managing contextual challenges such as information technology were managed easily by programme staff. Translating course requirements at a management level proved challenging with data collection for the protocols but provided insight into potential future challenges. This OR Training of Trainers course demonstrated that sharing of skills and knowledge can occur through a hybrid delivery model and contribute to developing capacity.

NeuroSeg-II: A deep learning approach for generalized neuron segmentation in two-photon Ca2+ imaging

The development of two-photon microscopy and Ca²⁺ indicators has enabled the recording of multiscale neuronal activities in vivo and thus advanced the understanding of brain functions. However, it is challenging to perform automatic, accurate, and generalized neuron segmentation when processing a large amount of imaging data. Here, we propose a novel deep-learning-based neural network, termed as NeuroSeg-II, to conduct automatic neuron segmentation for in vivo two-photon Ca²⁺ imaging data. This network architecture is based on Mask region-based convolutional neural network (R-CNN) but has enhancements of an attention mechanism and modified feature hierarchy modules. We added an attention mechanism module to focus the computation on neuron regions in imaging data. We also enhanced the feature hierarchy to extract feature information at diverse levels. To incorporate both spatial and temporal information in our data processing, we fused the images from average projection and correlation map extracting the temporal information of active neurons, and the integrated information was expressed as two-dimensional (2D) images. To achieve a generalized neuron segmentation, we conducted a hybrid learning strategy by training our model with imaging data from different labs, including multiscale data with different Ca²⁺ indicators. The results showed that our approach achieved promising segmentation performance across different imaging scales and Ca²⁺ indicators, even including the challenging data of large field-of-view mesoscopic images. By comparing state-of-the-art neuron segmentation methods for two-photon Ca²⁺ imaging data, we showed that our approach achieved the highest accuracy with a publicly available dataset. Thus, NeuroSeg-II enables good segmentation accuracy and a convenient training and testing process.

Radiotherapy teaching during COVID-19: An emergency teaching response

Background

The coronavirus disease 2019 (COVID-19) pandemic resulted in more than six million deaths in the first two years, a third of the estimated number of cancer-related deaths during this time. It directly impacted radiotherapy training in Africa.

Aim

This study evaluated the changes applied to the Access to Care Cape Town Radiotherapy training programme during the pandemic.

Setting

The training platform prior to March 2020 was used as a baseline and compared with the programme status in January 2022, representing the emergency teaching model.

Methods

Five themes were investigated: computer hardware and software changes; e-Learning resources; programme and curriculum changes; challenges experienced and alignment with modern medical education principles.

Results

Reconfiguration of the computer laboratories was required, including additional computer monitors, web cameras and headsets, as well as installation of screen recording and teleconferencing software. The Eclipse^TM radiotherapy treatment planning laboratory was reconfigured for remote student access, with simultaneous monitoring by local assistants. Online learning was augmented by adding the University of Cape Town Vula^TM system as resource, and courses restructured for delivery of short blocks. Five new courses were developed, including collaborations with international training partners, showing good alignment with the principles of modern medical education.

Conclusion

Reconfiguration was performed at a manageable cost but required a high level of information technology support. Connectivity and bandwidth issues remain a challenge, as well as online engagement.

Contribution

Despite these challenges, the virtualisation allowed for continued training between March 2020 and December 2021, with 18 departments attending remote teaching courses.

Neuroevolution Guided Hybrid Spiking Neural Network Training

Neuromorphic computing algorithms based on Spiking Neural Networks (SNNs) are evolving to be a disruptive technology driving machine learning research. The overarching goal of this work is to develop a structured algorithmic framework for SNN training that optimizes unique SNN-specific properties like neuron spiking threshold using neuroevolution as a feedback strategy. We provide extensive results for this hybrid bio-inspired training strategy and show that such a feedback-based learning approach leads to explainable neuromorphic systems that adapt to the specific underlying application. Our analysis reveals 53.8, 28.8, and 28.2% latency improvement for the neuroevolution-based SNN training strategy on CIFAR-10, CIFAR-100, and ImageNet datasets, respectively in contrast to state-of-the-art conversion based approaches. The proposed algorithm can be easily extended to other application domains like image classification in presence of adversarial attacks where 43.2 and 27.9% latency improvements were observed on CIFAR-10 and CIFAR-100 datasets, respectively.

Development of a Hybrid, Interprofessional, Interactive Quality Improvement Curriculum as a Model for Continuing Professional Development

Over the past 20 years, there has been an increased focus on quality improvement (QI) in health care, which is critical in achieving care that is patient-centered, safer, timelier, and more effective, efficient, and equitable. At the center of this movement is QI education, which is known to lead to learning, behavior change, and improved outcomes. However, there is a need for the development and provision of long-duration, interactive, interprofessional training in QI, to allow for in-depth learning and application of learned skills. To this end, we designed a curriculum for an established interprofessional, interactive, web-based QI fellowship for doctorally prepared clinicians. Curricular content is delivered virtually to geographically dispersed learners over a 2-year time span. The didactic curriculum and experiential learning opportunities provide learners with the foundational knowledge and practical skills to engage in-and eventually, lead-QI initiatives around the country. Evaluation of learner satisfaction and cognitive, affective, and skills-based learning has found that this model is an effective method to train geographically distributed learners. A hybrid training structure is used, where learners interact with the material through 3 distinct delivery modes: (1) virtual instruction in QI topics; (2) face-to-face training, mentorship, and the opportunity for practical application of applied knowledge and skills through the completion of QI projects; and (3) opportunities for other types of training, tailored to each learner's Individual Development Plan. This training program model holds value for QI learning in various health care settings, which are interprofessional by nature. These foundational concepts of hybrid learning to distributed learners-wherein an instructor delivers curriculum in small, face-to-face batches, interprofessional learning is supplemented in a virtual, longitudinal manner, and learners are allowed the opportunity to put skills into action for real-world problems in interdisciplinary clinical teams-can be applied in a multitude of settings, with comparatively lower time and cost expenditure than traditional training programs.