This article was originally published here

ESC Heart Fail. 2021 Nov 23. doi: 10.1002/ehf2.13724. Online ahead of print.

ABSTRACT

AIMS: The diagnosis of heart failure (HF) is an important problem in primary care. We previously demonstrated a 74% increase in registered HF diagnoses in primary care electronic health records (EHRs) following an extended audit procedure. What remains unclear is the accuracy of registered HF pre-audit and which EHR variables are most important in the extended audit strategy. This study aims to describe the diagnostic HF classification sequence at different stages, assess general practitioner (GP) HF misclassification, and test the predictive performance of an optimized audit.

METHODS AND RESULTS: This is a secondary analysis of the OSCAR-HF study, a prospective observational trial including 51 participating GPs. OSCAR used an extended audit based on typical HF risk factors, signs, symptoms, and medications in GPs EHR. This resulted in a list of possible HF patients, which participating GPs had to classify as HF or non-HF. We compared registered HF diagnoses before and after GPs assessment. For our analysis of audit performance, we used GPs assessment of HF as primary outcome and audit queries as dichotomous predictor variables for a gradient boosted machine (GBM) decision tree algorithm and logistic regression model. Of the 18 011 patients eligible for the audit intervention, 4678 (26.0%) were identified as possible HF patients and submitted for GPs assessment in the audit stage. There were 310 patients with registered HF before GP assessment, of whom 146 (47.1%) were judged not to have HF by their GP (over-registration). There were 538 patients with registered HF after GP assessment, of whom 374 (69.5%) did not have registered HF before GP assessment (under-registration). The GBM and logistic regression model had a comparable predictive performance (area under the curve of 0.70 [95% confidence interval 0.65-0.77] and 0.69 [95% confidence interval 0.64-0.75], respectively). This was not significantly impacted by reducing the set of predictor variables to the 10 most important variables identified in the GBM model (free-text and coded cardiomyopathy, ischaemic heart disease and atrial fibrillation, digoxin, mineralocorticoid receptor antagonists, and combinations of renin-angiotensin system inhibitors and beta-blockers with diuretics). This optimized query set was enough to identify 86% (n = 461/538) of GPs self-assessed HF population with a 33% reduction (n = 1537/4678) in screening caseload.

CONCLUSIONS: Diagnostic coding of HF in primary care health records is inaccurate with a high degree of under-registration and over-registration. An optimized query set enabled identification of more than 80% of GPs self-assessed HF population.

PMID:34816632 | DOI:10.1002/ehf2.13724

Go here to read the rest:
Machine learning optimization of an electronic health record audit for heart failure in primary care - DocWire News

In recent years, artificial intelligence programs have been prompting change in the design of computer chips, and novel computers have likewise made possible new kinds of neural networks in AI. There is a feedback loop going on that is powerful.

At the center of that sits the software technology that converts neural net programs to run on novel hardware. And at the center of that sits a recent open-source project gaining momentum.

Apache TVM is a compiler that operates differently from other compilers. Instead of turning a program into typical chip instructions for a CPU or GPU, it studies the "graph" of compute operations in a neural net, in TensorFlow or Pytorch form, such as convolutions and other transformations, and figures out how best to map those operations to hardware based on dependencies between the operations.

At the heart of that operation sits a two-year-old startup, OctoML, which offers ApacheTVM as a service. As explored in March by ZDNet's George Anadiotis, OctoML is in the field of MLOps, helping to operationalize AI. The company uses TVM to help companies optimize their neural nets for a wide variety of hardware.

Also:OctoML scores $28M to go to market with open source Apache TVM, a de facto standard for MLOps

In the latest development in the hardware and research feedback loop, TVM's process of optimization may already be shaping aspects of how AI is developed.

"Already in research, people are running model candidates through our platform, looking at the performance," said OctoML co-founder Luis Ceze, who serves as CEO, in an interview with ZDNet via Zoom. The detailed performance metrics mean that ML developers can "actually evaluate the models and pick the one that has the desired properties."

Today, TVM is used exclusively for inference, the part of AI where a fully-developed neural network is used to make predictions based on new data. But down the road, TVM will expand to training, the process of first developing the neural network.

"Already in research, people are running model candidates through our platform, looking at the performance," says Luis Ceze, co-founder and CEO of startup OctoML, which is commercializing the open-source Apache TVM compiler for machine learning, turning it into a cloud service. The detailed performance metrics mean that ML developers can "actually evaluate the models and pick the one that has the desired properties."

"Training and architecture search is in our roadmap," said Ceze, referring to the process of designing neural net architectures automatically, by letting neural nets search for the optimal network design. "That's a natural extension of our land-and-expand approach" to selling the commercial service of TVM, he said.

Will neural net developers then use TVM to influence how they train?

"If they aren't yet, I suspect they will start to," said Ceze. "Someone who comes to us with a training job, we can train the model for you" while taking into account how the trained model would perform on hardware.

That expanding role of TVM, and the OctoML service, is a consequence of the fact that the technology is a broader platform than what a compiler typically represents.

"You can think of TVM and OctoML by extension as a flexible, ML-based automation layer for acceleration that runs on top of all sorts of different hardware where machine learning models runGPUs, CPUs, TPUs, accelerators in the cloud," Ceze told ZDNet.

"Each of these pieces of hardware, it doesn't matter which, have their own way of writing and executing code," he said. "Writing that code and figuring out how to best utilize this hardware today is done today by hand across the ML developers and the hardware vendors."

The compiler, and the service, replace that hand tuning today at the inference level, with the model ready for deployment, tomorrow, perhaps, in the actual development/training.

Also: AI is changing the entire nature of compute

The crux of TVM's appeal is greater performance in terms of throughput and latency, and efficiency in terms of computer power consumption. That is becoming more and more important for neural nets that keep getting larger and more challenging to run.

"Some of these models use a crazy amount of compute," observed Ceze, especially natural language processing models such as OpenAI's GPT-3 that are scaling to a trillion neural weights, or parameters, and more.

As such models scale up, they come with "extreme cost," he said, "not just in the training time, but also the serving time" for inference. "That's the case for all the modern machine learning models."

As a consequence, without optimizing the models "by an order of magnitude," said Ceze, the most complicated models aren't really viable in production, they remain merely research curiosities.

But performing optimization with TVM involves its own complexity. "It's a ton of work to get results the way they need to be," observed Ceze.

OctoML simplifies things by making TVM more of a push-button affair.

"It's an optimization platform," is how Ceze characterizes the cloud service.

"From the end user's point of view, they upload the model, they compare the models, and optimize the values on a large set of hardware targets," is how Ceze described the service.

"The key is that this is automatic no sweat and tears from low-level engineers writing code," said Ceze.

OctoML does the development work of making sure the models can be optimized for an increasing constellation of hardware.

"The key here is getting the best out of each piece of hardware." That means "specializing the machine code to the specific parameters of that specific machine learning model on a specific hardware target." Something like an individual convolution in a typical convolutional neural network may become optimized to suit a particular hardware block of a particular hardware accelerator.

The results are demonstrable. In benchmark tests published in September for the MLPerf test suite for neural net inference, OctoML had a top score for inference performance for the venerable ResNet image recognition algorithm in terms of images processed per second.

The OctoML service has been in a pre-release, early access state since December of last year.

To advance its platform strategy, OctoML earlier this month announced it had received $85 million in a Series C round of funding from hedge fund Tiger Global Management, along with existing investors Addition, Madrona Venture Group and Amplify Partners. The round of funding brings OctoML's total funding to $132 million.

The funding is part of OctoML's effort to spread the influence of Apache TVM to more and more AI hardware. Also this month, OctoML announced a partnership with ARM Ltd., the U.K. company that is in the process of being bought by AI chip powerhouse Nvidia. That follows partnerships announced previously with Advanced Micro Devices and Qualcomm. Nvidia is also working with OctoML.

The ARM partnership is expected to spread use of OctoML's service to the licensees of the ARM CPU core, which dominates mobile phones, networking and the Internet of Things.

The feedback loop will probably lead to other changes besides design of neural nets. It may affect more broadly how ML is commercial deployed, which is, after all, the whole point of MLOps.

As optimization via TVM spreads, the technology could dramatically increase portability in ML serving, Ceze predicts.

Because the cloud offers all kinds of trade-offs with all kinds of hardware offerings, being able to optimize on the fly for different hardware targets ultimately means being able to move more nimbly from one target to another.

"Essentially, being able to squeeze more performance out of any hardware target in the cloud is useful because it gives more target flexibility," is how Ceze described it. "Being able to optimize automatically gives portability, and portability gives choice."

That includes running on any available hardware in a cloud configuration, but also choosing the hardware that happens to be cheaper for the same SLAs, such as latency, throughput and cost in dollars.

With two machines that have equal latency on ResNet, for example, "you'll always take the highest throughput per dollar," the machine that's more economical. "As long as I hit the SLAs, I want to run it as cheaply as possible."

See more here:
Design of AI may change with the open-source Apache TVM and a little help from startup OctoML - ZDNet

Machine learning for mobile developers

ML Kit brings Googles machine learning expertise to mobile developers in a powerful and easy-to-use package. Make your iOS and Android apps more engaging, personalized, and helpful with solutions that are optimized to run on device.

Video and image analysis APIs to label images and detect barcodes, text, faces, and objects.

Scan and process barcodes. Supports most standard 1D and 2D formats.

Identify objects, locations, activities, animal species, products, and more. Use a general-purpose base model or tailor to your use case with a custom TensorFlow Lite model.

Recognizes handwritten text and handdrawn shapes on a digital surface, such as a touch screen. Recognizes 300+ languages, emojis and basic shapes.

Separate the background from users within a scene and focus on what matters.

Natural language processing APIs to identify and translate between 58 languages and provide reply suggestions.

Determine the language of a string of text with only a few words.

Generate reply suggestions in text conversations.

Detect and locate entities (such as addresses, date/time, phone numbers, and more) and take action based on those entities. Works in 15 languages.

[{ "type": "thumb-down", "id": "missingTheInformationINeed", "label":"Missing the information I need" },{ "type": "thumb-down", "id": "tooComplicatedTooManySteps", "label":"Too complicated / too many steps" },{ "type": "thumb-down", "id": "outOfDate", "label":"Out of date" },{ "type": "thumb-down", "id": "samplesCodeIssue", "label":"Samples / code issue" },{ "type": "thumb-down", "id": "otherDown", "label":"Other" }] [{ "type": "thumb-up", "id": "easyToUnderstand", "label":"Easy to understand" },{ "type": "thumb-up", "id": "solvedMyProblem", "label":"Solved my problem" },{ "type": "thumb-up", "id": "otherUp", "label":"Other" }]

Continued here:
ML Kit | Google Developers

Event You want to know more about the ins and outs of machine learning, but cant figure out where to start? Our AI practitioners' conference MCubed and The Register regular Mark Whitehorn have got you covered.

Join us on December 9 for an interactive online workshop to learn all about ML types and algorithms, and find out about strengths and weaknesses of different approaches by using them yourself.

This limited one-day online workshop is geared towards anyone who wants to gain an understanding of machine learning no matter your background. Mark will start with the basics, asking and answering what is machine learning, before diving deeper into the different types of systems you keep hearing about.

Once youre familiar with supervised, unsupervised, and reinforcement learning, things will get hands-on with practical exercises using common algorithms such as clustering and, of course, neural networks.

In the process, youll also investigate the pros and cons of different approaches, which should help you in assessing what could work for a specific task and what isnt an option, and learn how the things youve just tried relate to what Big Biz are using. However, its not all code and algorithms in the world of ML, which is why Mark will also give you a taster of what else there is to think about when realizing machine learning projects, such as data sourcing, model training, and evaluation.

Since Python has turned into the language of choice for many ML practitioners, exercises and experiments will be performed in Python mostly, so installing it along with an IDE will help you make the most of the workshop if you havent already.

This doesnt mean the course is for Pythonistas only, however. If youre not familiar with the language, exercises will be transformed into demonstrations providing you insight into the inner workings of the associated code, before we start altering some of the parameters together. Like that, you get to find out how each parameter influences the learning that is performed, leaving you in top shape to continue in whatever language (or no-code ML system) you feel comfortable with.

Your trainer, Professor Mark Whitehorn, works as a consultant for national and international organisations, such as the Bank of England, Standard Life, and Sainsburys, designing analytical systems and data science solutions. He is also the Emeritus Professor of Analytics at the University of Dundee where he teaches a master's course in data science and conducts research into the development of analytical systems and proteomics. You can get a taster of his brilliant teaching skills here.

If this sounds interesting to you, head over to the MCubed website to secure your spot now. Tickets are very limited to make sure we can answer all your questions and everyone is getting proper support throughout the day so dont wait for too long.

Excerpt from:
MCubed does web workshops: Join Mark Whitehorns one-day introduction to machine learning next month - The Register