In the CSC, we regularly collect various resources to which we regularly reference and recommend
to our internal and external collaborators as part of our work. Click on the sections in the
left-hand sidebar to learn more.
These resources are updated as and when necessary, so we recommend both keeping an eye on this
page, as well as reach out to us if you need any further
information and/or would like to propose future additions.
| Resource | Description |
|---|---|
| Pycharm Professional Edition | Integrated Development Environment of choice for the CSC team. Log in to Jetbrains using your KCL login details on https://www.jetbrains.com/community/education/#students |
| Free-for.dev | This is a list of software (SaaS, PaaS, IaaS, etc.) and other offerings that have free tiers for developers. The scope of this particular list is limited to things that infrastructure developers (System Administrator, DevOps Practitioners, etc.) are likely to find useful. |
| GitHub Student Developer Pack | Free access to the best developer tools in one place so they can learn by doing. |
| NHS Python Community | Lead by enthusiasts and advocates, the NHS Python Community for Healthcare is an open community of practice that champions the use of the python programming language and open code in the NHS and healthcare sector |
| devdocs | DevDocs combines multiple API documentations in a fast, organized, and searchable interface. |
| Datacamp | Comprehensive online learning for data scientists |
| SankeyMATIC | Free web tool for creating Sankey diagrams, no specialist knowledge needed |
| Diagrams | Diagram as Code allows you to track the architecture diagram changes in any version control system. |
| autosklearn | auto-sklearn frees a machine learning user from algorithm selection and hyperparameter tuning. It leverages recent advantages in Bayesian optimization, meta-learning and ensemble construction |
| Open source imaging data sets | A collection of open source imaging data sets. |
| Open Access Medical Image Repositories | Sites that list and/or host multiple collections of data |
| System Design Primer | An organized collection of resources to help you learn how to build systems at scale |
| Jupyter Book | Make publication ready books from Jupyter notebooks and markdown files |
| Resource | Description |
|---|---|
| NHS Fellowship in Clinical AI, Clinical AI Curriculum | Developed by the faculty of the NHS Fellowship in Clinical AI, this document specifies the content and outlines the delivery of the knowledge and skills to adopt AI safely and effectively in clinical workflows. |
| NHS AI and Digital Regulations Service for health and social care | Developed by NICE, the MHRA, the CQC, and the HRA for both adopters of AI in healthcare and developers. |
| KCL Innovation Scholars- AI modules | These three e-learning modules are aimed at those interested in evidence-based medicine, extracting knowledge from large-scale data and applying AI to improve patient care. |
| NHS Digital Academy AI Learning Hub | NHS Digital Academy's collection of curated learning resources, mapped to their an Artificial Intelligence (AI) capability framework. |
| Turing Institute, Clinical AI interest group | The Clinical AI interest group seeks to bring together health professionals from diverse healthcare fields and data scientists who have a shared interest in clinical AI and to foster this network through interactive events on up-to-date developments in the field and cultivate innovative research projects. |
| Topol Digital Fellowships | The Topol Digital Fellowship provides health and social care professionals with time, support and training to lead digital health transformations and innovations in their organisations. |
| Scientist Training Programme | The Scientist Training Programme (STP) is a three-year programme of work-based learning, supported by a University accredited master's degree. |
| Van Der Schaar lab- Revolutionizing healthcare clinician engagement sessions | A series of engagement sessions for clinicians and medical students, aiming to share ideas and discuss topics that will define the future of machine learning in healthcare. |
| Digital, Artificial Intelligence and Robotics (DART-Ed) programme | The Digital, Artificial Intelligence and Robotics Technologies in Education (DART-Ed) programme is delivered by Health Education England (HEE) and explores the educational needs of the health and care workforce to enable use of Artificial Intelligence (AI) and Robotic technologies to improve healthcare. |
| Open Grants | An increasing number of researchers are sharing their grant proposals openly. They do this to open up science so that all stages of the process can benefit from better interaction and communication and to provide examples for early career scientists writing grants. This is a list of some of these proposals to help you find them. |
| Resource | Description |
|---|---|
| The Cancer Imaging Archive (TCIA) | The Cancer Imaging Archive (TCIA) is a service which de-identifies and hosts a large archive of medical images of cancer accessible for public download. |
| NHS Data Model and Dictionary | The NHS Data Model and Dictionary provides a reference point for approved Information Standards Notices to support health care activities within the NHS in England. It has been developed for everyone who is actively involved in the collection of data and the management of information in the NHS. |
| DeployStack | DeployStack is a list of the best, hand picked tools and services that you might need when launching a website. Note that this project is no longer actively maintained. |
| FastAPI | FastAPI is a modern, fast (high-performance), web framework for building APIs with Python 3.6+ based on standard Python type hints. |
| gazelle - eHealth test framework for interoperability | Contains technical resources for implementers of IHE profiles, including those preparing for IHE Connectathons. |
| Digital Health & Care Innovation Centre | Simulation refers to funded projects where we work with developers to integrate their products and services within these new types of architecture |
| Resource | Description |
|---|---|
| British Standards Institute | The BSI publish standards relevant to our work in medical devices. Use KCL institutional login for access. |
| Best-practice guidance for the in-house manufacture of medical devices and non-medical devices, including software in both cases, for use within the same health institution | This guidance document has been developed to provide scientific, engineering, technical, clinical and risk management staff with guidance on the regulatory issues and best-practice involved in the manufacture, management and use of these devices |
| Artificial intelligence in healthcare - Applications, risks, and ethical and | The report identifies and clarifies the main clinical, social and ethical risks posed by AI in healthcare, more specifically the potential errors and patient harm; risk of bias and increased health inequalities; lack of transparency and trust; and vulnerability to hacking and data privacy breaches. |
| Resource | Description |
|---|---|
| Emerging Architectures for Modern Data Infrastructure | This reads provides with an updated set of data infrastructure architectures. Data infrastructures architectures provide a framework for how IT infrastructure supports data. The goal of any data architecture is to show how data is acquired, transported, stored, queried, and secured. |
| The Model Performance Mismatch Problem (and what to do about it) | This read gives an overview of what to do when you get a very promising performance when evaluating the model on the training dataset but poor performance when evaluating the model on the test set. |
| Simple Python Package to Extract Deep Learning Features | This read explains how to use a Python package called image_features that can be used to perform computer vision problems such as to extract features using imagenet trained deep learning models. |
| Awesome Production Machine Learning | This repository contains a curated list of awesome open source libraries that will help you deploy, monitor, version, scale and secure your production machine learning. |
| Playbook for Threat Modeling Medical Devices | This read provides a description of threat modeling and why it has become a recognized cybersecurity best practice. Threat modeling is analyzing representations of a system to highlight concerns about security and privacy characteristics. |
| Regulatory Frameworks for Development and Evaluation of Artificial Intelligence–Based Diagnostic Imaging Algorithms | This read delves into how AI algorithms' safety and effectiveness must be ensured in order for these to be trusted. This articles talks about the major regulatory frameworks for software as a medical device application, identifies major gaps, and propose additional strategies to improve the development and evaluation of diagnostic AI algorithms. |
| Presenting Machine Learning Model Information to Clinical end Users with Model Facts Labels | This paper talks about the risks of translating a machine learning model into clinical care and provides the “Model Facts” label, which aims to ensure that clinicians actually know how, when, how not, and when not to incorporate model output into clinical decisions. |
| To buy or Not to Buy - Evaluating Commercial AI Solutions in Radiology (the ECLAIR guidelines) | This article lays out a practical framework that will help stakeholders evaluate commercial AI solutions in radiology to allow them to make an informed decision on whether to buy the AI or not. |
| Open Source in Government, Creating the Conditions for Success. | This book talks about the advantages of using open-source software. |
| How Do We Get the Best Out of Automation and AI in Health Care? | This report explores the opportunities for automation and AI in health care and the challenges of deploying them in practice. |
| Deep Learning Interviews | This book will prepare you for deep learning job interviews by guiding you through hundreds of fully solved questions. |
| A Research Ethics Framework for the Clinical Translation of Healthcare Machine Learning | This paper talks about a research ethics framework that can apply to the systematic inquiry of ML research across its development cycle. |
| What are Diffusion Models? | This articles introduces the concept of diffusion models. These models work by destroying training data through the successive addition of Gaussian noise. |
| Qure.ai Tech Blog | This article talks about fluentd, a unified data collector for logging which allows you to collect logs from wide variety of sources and save them to different places like S3, mongodb etc. |
| Mitigating Racial Bias in Machine Learning | This paper talks about bias in AI. |
| The Medical Algorithmic Audit. | This article talks about a medical algorithmic audit framework that guides the auditor through a process of considering potential algorithmic errors. |
| Simplified Transfer Learning for Chest Radiography Model Development | Because building robust CXR models requires large labeled training datasets, this articles describes how Google Health utilizes advanced ML methods to generate pre-trained “CXR networks”. |
| Implementation of Clinical Artificial Intelligence in Radiology, Who Decides and How? | In this article, a framework is established for the infrastructure required for clinical AI implementation and presents a road map for governance. |
| As if Sand Were Stone. New Concepts and Metrics to Probe the Ground on which to Build Trustable AI | This paper talks about the importance of interpreting the quality of the labeling used as the input of predictive models to understand the reliability of their output. |
| Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning | This book talks about the correct use of model evaluation, model selection, and algorithm selection. |
| Evaluating machine learning models and their diagnostic value | This chapter describes how to validate a machine learning model |
| What are the Best Words to Use when Talking about Data? | This article talks about the right vocabulary to be used for patient data in care, treatment and research. |
| Evidence standards framework (ESF) for digital health technologies | This article covers the Evidence standards framework (ESF) for digital health technologies written by the National Institute of Healthcare Excellence. The ESF is intended for evaluators and decision makers in the health and care system to help them identify DHTs that are likely to offer benefits. |