Connect with us

AI

Building predictive disease models using Amazon SageMaker with Amazon HealthLake normalized data

Avatar

Published

on

In this post, we walk you through the steps to build machine learning (ML) models in Amazon SageMaker with data stored in Amazon HealthLake using two example predictive disease models we trained on sample data using the MIMIC-III dataset. This dataset was developed by the MIT lab for Computational Physiology and consists of de-identified healthcare data associated with approximately 60,000 ICU admissions. The dataset includes multiple attributes about the patients like their demographics, vital signs, and medications, along with their clinical notes. We first developed the models using the structured data such as demographics, vital signs, and medications. Then we augmented these models with additional data extracted and normalized from clinical notes to test and compare their performance. In both these experiments, we found an improvement in model performance when modelled as a supervised learning (classification) or an unsupervised learning (clustering) problem. We present our findings and the setup of the experiments in this post.

Why multiple modalities?

Modality can be defined as the classification of a single independent sensory input/output between a computer and a human. For example, we can see objects and hear sounds by using our senses. These can be considered as two separate modalities. Datasets that represent multiple modalities are categorized as a multi-modal dataset. For instance, images can consist of tags that help search and organize them, and textual data can contain images to explain what’s in the image. When medical practitioners make clinical decisions, it’s usually based on information gathered from a variety of healthcare data modalities. A physician looks at patient’s observations, their past history, their scans, and even physical characteristics of the patient during the visit to make a definitive diagnosis. ML models need to take this into account when trying to achieve real-world performance. The post Building a medical image search platform on AWS shows how you can combine features from medical images and their corresponding radiology reports to create a medical image search platform. The challenge with creating such models is the preprocessing of these multi-modal datasets and extracting appropriate features from them.

Amazon HealthLake makes it easier to train models on multi-modal data

Amazon HealthLake is a HIPAA eligible service that enables healthcare providers, health insurance companies, and pharmaceutical companies to store, transform, query, and analyze health data on the AWS Cloud at petabyte scale. As part of the transformation, Amazon HealthLake tags and indexes unstructured data using specialized ML models. These tags and indexes can be used to query and search as well as understand relationships in the data for analytics.

When you export data from Amazon HealthLake, it adds a resource called DocumentReference to the output. This resource consists of clinical entities (Like medications, medical conditions, anatomy, and Protected Health Information (PHI)), the RxNorm codes for medications, and the ICD10 codes for medical conditions that are automatically derived from the unstructured notes about the patients. These are additional attributes about the patients that are embedded within the unstructured portions of their clinical records and would have been largely ignored for downstream analysis. Combining the structured data from the EHR with these attributes provides a more holistic picture of the patient and their conditions. To help determine the value of these attributes, we created a couple of experiments around clinical outcome prediction.

Architecture overview

The following diagram illustrates the architecture for our experiments.

The following diagram illustrates the architecture for our experiments.

You can export the normalized data to an Amazon Simple Storage Service (Amazon S3) bucket using the Export API. Then we use AWS Glue to crawl and build a catalog of the data. This catalog is shared by Amazon Athena to run the queries directly off of the exported data from Colossus. Athena also normalizes the JSON format files to rows and columns for easy querying. The DocumentReference resource JSON file is processed separately to extract indexed data derived from the unstructured portions of the patient records. The file consists of an extension tag that has a hierarchical JSON output consisting of patient attributes. There are multiple ways to process this file (like using Python-based JSON parsers or even string-based regex and pattern matching). For an example implementation, see the section Connecting Athena with HealthLake in the post Population health applications with Amazon HealthLake – Part 1: Analytics and monitoring using Amazon QuickSight.

Example setup

Accessing the MIMIC-III dataset requires you to request access. As part of this post, we don’t distribute any data but instead provide the setup steps so you can replicate these experiments when you have access to MIMIC-III. We also publish our conclusions and findings from the results.

For the first experiment, we build a binary disease classification model to predict patients with congestive heart failure (CHF). We measure its performance using accuracy, ROC, and confusion matrix for both structured and unstructured patient records. For the second experiment, we cluster a cohort of patients into a fixed number of groups and visualize the cluster separation before and after the addition of the unstructured patient records. For both our experiments, we build a baseline model and compare it with the multi-modal model, where we combine existing structured data with additional features (ICD-10 codes and Rx-Norm codes) in our training set.

These experiments are not intended to produce a state-of-the-art model on real-world datasets; its purpose is to demonstrate how you can utilize features exported from Amazon Healthlake for training models on structured and unstructured patient records to improve your overall model performance.

Features and data normalization

We took a variety of features related to patient encounters to train our models. This included the patient demographics (gender, marital status), the clinical conditions, procedures, medications, and observations. Because each patient could have multiple encounters consisting of multiple observations, clinical conditions, procedures, and medications, we normalized the data and converted each of these features into a list. This allowed us to get a training set with all these features (as a list) for each patient.

Similarly, for the unstructured features that Amazon Healthlake converted into the DocumentReference resource, we extracted the ICD-10 codes and Rx-Norm codes (using the methods described in the architecture) and converted them into feature vectors.

Feature engineering and model

For the categorical attributes in our dataset, we used a label encoder to convert the attributes into a numerical representation. For all other list attributes, we used term frequency-inverse document frequency (FI-IDF) vectors. This high-dimensional dataset was then shuffled and divided into 80% train and 20% test sets for training and evaluation of the models, respectively. For training our model, we used the gradient boosting library XGBoost. We considered mostly default hyperparameters and didn’t perform any hyperparameter tuning, because our objective was only to train a baseline model with structured patient records and then show improvement on those results with the unstructured features. Adopting better hyperparameters or changing to other feature engineering and modelling approaches can likely improve these results.

Example 1: Predicting patients with a congestive heart failure

For the first experiment, we took 500 patients with a positive CHF diagnosis. For the negative class, we randomly selected 500 patients who didn’t have a CHF diagnosis. We removed the clinical conditions from the positive class of patients that were directly related to CHF. For example, all the patients in the positive class were expected to have ICD-9 code 428, which stands for CHF. We filtered that out from the positive class to make sure the model is not overfitting on the clinical condition.

Baseline model

Our baseline model had an accuracy of 85.8%. The following graph shows the ROC curve.

Our baseline model had an accuracy of 85.8%. The following graph shows the ROC curve.

The following graph shows the confusion matrix.

The following graph shows the confusion matrix.

Amazon HealthLake augmented model

Our Amazon HealthLake augmented model had an accuracy of 89.1%. The following graph shows the ROC curve.

The following graph shows the ROC curve.

The following graph shows the confusion matrix.

The following graph shows the confusion matrix.

Adding the features extracted from Amazon HealthLake allowed us to improve the model accuracy from 85% to 89% and also the AUC from 0.86 to 0.89. If you look at the confusion matrices for the two models, the false positives reduced from 20 to 13 and the false negatives reduced from 27 to 20.

Optimizing healthcare is about ensuring the patient is associated with their peers and the right cohort. As patient data is added or changes, it’s important to continuously identify and reduce false negative and positive identifiers for overall improvement in the quality of care.

To better explain the performance improvements, we picked a patient from the false negative cohort in the first model who moved to true positive in the second model. We plotted a word cloud for the top medical conditions for this patient for the first and the second model, as shown in the following images.

There is a clear difference between the medical conditions of the patient before and after the addition of features from Amazon HealthLake. The word cloud for model 2 is richer, with more medical conditions indicative of CHF than the one for model 1. The data embedded within the unstructured notes for this patient extracted by Amazon HealthLake helped this patient move from a false negative category to a true positive.

These numbers are based on synthetic experimental data we used from a subset of MIMIC-III patients. In a real-world scenario with higher-volume of patients, these numbers may differ.

Example 2: Grouping patients diagnosed with sepsis

For the second experiment, we took 500 patients with a positive sepsis diagnosis. We grouped these patients on the basis of their structured clinical records using k-means clustering. To show that this is a repeatable pattern, we chose the same feature engineering techniques as described in experiment 1. We didn’t divide the data into training and testing datasets because we were implementing an unsupervised learning algorithm.

We first analyzed the optimal number of clusters of the grouping using the Elbow method and arrived at the curve shown in the following graph.

This allowed us to determine that six clusters were the optimal number in our patient grouping.

Baseline model

We reduced the dimensionality of the input data using Principal Component Analysis (PCA) to two and plotted the following scatter plot.

The following were the counts of patients across each cluster:

Cluster 1
Number of patients: 44

Cluster 2
Number of patients: 30

Cluster 3
Number of patients: 109

Cluster 4
Number of patients: 66

Cluster 5
Number of patients: 106

Cluster 6
Number of patients: 145

We found that the at least four of the six clusters had a distinct overlap of patients. That means the structured clinical features weren’t enough to clearly divide the patients into six groups.

Enhanced model

For the enhanced model, we added the ICD-10 codes and their corresponding descriptions for each patient as extracted from Amazon HealthLake. However, this time, we could see a clear separation of the patient groups.

We also saw a change in distribution across the six clusters:

Cluster 1
Number of patients: 54

Cluster 2
Number of patients: 154

Cluster 3
Number of patients: 64

Cluster 4
Number of patients: 44

Cluster 5
Number of patients: 109

Cluster 6
Number of patients: 75

As you can see, adding features from the unstructured data for the patients allows us to improve the clustering model to clearly divide the patients into six clusters. We even saw that some patients moved across clusters, denoting that the model became better at recognizing those patients based on their unstructured clinical records.

Conclusion

In this post, we demonstrated how you can easily use SageMaker to build ML models on your data in Amazon HealthLake. We also demonstrated the advantages of augmenting data from unstructured clinical notes to improve the accuracy of disease prediction models. We hope this body of work provides you with examples of how to build ML models using SageMaker with your data stored and normalized in Amazon HealthLake and improve model performance for clinical outcome predictions. To learn more about Amazon HealthLake, please check the website and technical documentation for more information.


About the Authors

Ujjwal Ratan is a Principal Machine Learning Specialist in the Global Healthcare and Lifesciences team at Amazon Web Services. He works on the application of machine learning and deep learning to real world industry problems like medical imaging, unstructured clinical text, genomics, precision medicine, clinical trials and quality of care improvement. He has expertise in scaling machine learning/deep learning algorithms on the AWS cloud for accelerated training and inference. In his free time, he enjoys listening to (and playing) music and taking unplanned road trips with his family.

Nihir Chadderwala is an AI/ML Solutions Architect on the Global Healthcare and Life Sciences team. His background is building Big Data and AI-powered solutions to customer problems in variety of domains such as software, media, automotive, and healthcare. In his spare time, he enjoys playing tennis, watching and reading about Cosmos.

Parminder Bhatia is a science leader in the AWS Health AI, currently building deep learning algorithms for clinical domain at scale. His expertise is in machine learning and large scale text analysis techniques in low resource settings, especially in biomedical, life sciences and healthcare technologies. He enjoys playing soccer, water sports and traveling with his family.

Source: https://aws.amazon.com/blogs/machine-learning/building-predictive-disease-models-using-amazon-sagemaker-with-amazon-healthlake-normalized-data/

AI

Digital ID Verification Service IDnow Acquires identity Trust Management AG, a Global Provider of ID Software from Germany

Avatar

Published

on

IDnow, a provider of identity verification-as-a-service solutions, will be acquiring identity Trust Management, a global provider of digital and offline ID verification software from Germany.

IDnow confirmed that it would continue to maintain identity Trust Management’s Düsseldorf location and will retain its employees as well.

The acquisition of Identity Trust Management should help IDnow with further expanding into new verticals while offering its services to a larger and potentially more diverse client base in Germany and other areas.

The combined product portfolio will aim to provide comprehensive ID verification methods, ranging from automated to human-assisted and from being purely online to point-of-sale. All these ID verification methods will be accessible through the IDnow platform.

Identity Trust Management has established its operations in Germany’s identity industry during the past 10 years, with a solid reputation and portfolio of clients focused on telecommunications and insurance services.

Andreas Bodczek, CEO at IDnow, stated:

“Identity Trust Management AG has built an impressive company both in terms of product portfolio and client relationships. We have known the leadership team for years and have established a partnership rooted in deep loyalty and mutual understanding. We are excited to welcome identity Trust Management AG’s talented team to the IDnow family and look forward to combining the strengths of both companies to create a unified, market-leading brand.”

Uwe Stelzig, CEO at identity Trust Management AG, remarked:

“This combination unites the power of IDnow’s innovative technology with identity Trust Management AG’s diverse set of capabilities to create a differentiated identity verification platform. Together, we will be well-positioned to achieve our joint vision of providing clients with a unique, one-stop solution for identity verification.”

This is reportedly IDnow’s second acquisition in just the past 6 months following that of Wirecard Communication Services in September of last year.

As covered in December 2020, the European Investment Bank (EIB) had decided to provide €15 million of growth funding to Germany-based identity verification platform, IDnow. Founded in 2014, IDnow covers a wide range of use cases both in regulated sectors in Europe and for completely new digital business models worldwide.

The platform allows the identity flow to be adapted to different regional, legal, and business requirements on a per-use case basis.

As explained by the IDnow team:

“IDnow uses Artificial Intelligence to check all security features on ID documents and can therefore reliably identify forged documents. Potentially, the identities of more than 7 billion customers from 193 different countries can be verified in real-time. In addition to safety, the focus is also on an uncomplicated application for the customer. Achieving five out of five stars on the Trustpilot customer rating portal, IDnow technology is particularly user-friendly.”

Checkout PrimeXBT
Trade with the Official CFD Partners of AC Milan
The Easiest Way to Way To Trade Crypto.
Source: https://www.crowdfundinsider.com/2021/03/172910-digital-id-verification-service-idnow-acquires-identity-trust-management-ag-a-global-provider-of-id-software-from-germany/

Continue Reading

AI

China five-year plan aims for supremacy in AI, quantum computing

Avatar

Published

on

China’s tech industry has been hit hard by US trade battles and the economic uncertainties of the pandemic, but it’s eager to bounce back in the relatively near future. According to the Wall Street Journal, the country used its annual party meeting to outline a five-year plan for advancing technology that aids “national security and overall development.” It will create labs, foster educational programs and otherwise boost research in fields like AI, biotech, semiconductors and quantum computing.

The Chinese government added that it would increase spending on basic research (that is, studies of potential breakthroughs) by 10.6 percent in 2021, and would create a 10-year research strategy.

China has a number of technological advantages, such as its 5G availability and the sheer volume of AI research it produces. This is one of the few countries where completely driverless taxis are serving real customers. In that light, the country is really cementing some of its strong points.

However, this may also be a matter of survival. US trade restrictions have hobbled companies like Huawei and ZTE, in part due to a lack of cutting-edge chip manufacturing. The US also leads in overall research, and the Biden administration is boosting spending on advancements for 5G, AI and electric cars. As experienced as China is in some areas, it risks slipping behind if it doesn’t counter the latest American efforts.

Checkout PrimeXBT
Trade with the Official CFD Partners of AC Milan
The Easiest Way to Way To Trade Crypto.
Source: https://www.engadget.com/china-five-year-plan-for-technology-225618577.html

Continue Reading

AI

How Machine Learning is Being Applied to Software Development

Avatar

Published

on

Author profile picture

When Elon Musk proposed the idea of autonomous vehicles, everyone assumed it to be a hypothetical dream and never took it seriously. However, the same vehicles are now on the roads, being one of the top-selling cars in the United States.

The applications of artificial intelligence and machine learning are visible in all areas, from Google Photos in your smartphone to Amazon’s Alexa at your home, and software development is no exception. AI has already changed the way iOS and Android app developers work.

Machine learning can enhance the way a traditional software development cycle works. It allows a computer to learn and improve from the experiences without the need for programming. The sole purpose of AI and ML is to allow computers to learn automatically.

Moreover, being a software developer, you might need to specify minute details to let your computer know what it has to do. Developing software integrated with machine learning can help you make a significant difference in your developing experience.

Machine Intelligence is the last invention that humanity will ever need to make!

When it comes to how machine learning and AI help developers, only the sky’s the limit. Taking it even broader, AI has always transformed every industry it has ever entered. Here’s a quick rundown of stats that convey the same:

As the figures stated, artificial intelligence and machine learning are surely transforming the world, and the development industry is no exception. Let’s have a look at how it can help you write flawless code, deploy, and rectify bugs.

AI and ML in Development – How Does This Benefit Software Developers?

Whether you’re a person working as an android app developer or someone who writes codes for a living, you might have wondered what AI has in it for you. Here’s how developers can harness the capabilities of machine learning and AI:

1. Controlled Deployment of Code

AI and machine learning technologies help in enhancing the efficiency of code deployment activities required in development. In the development spectrum, the deployment mechanisms include a development phase where you need to upgrade your programs and applications to a newer version.

However, if you fail to execute the process properly, you need to face several risks including corruption of the software or application. With the help of AI, you can easily prevent such vulnerabilities and upgrade your code with ease.

2. Bugs and Error Identification

With the advancements in Artificial intelligence, the coding experience is getting even better and improved. It allows developers to easily spot bugs in their code and fix them instantly. They don’t have to read their code, again and again, to find potential flaws in their code anymore.

Several machine learning algorithms can automatically test your software and suggest changes.

AI-powered testing tools are certainly saving a plethora of time to developers and help them deliver their projects faster.

3. Secure Data Storage

With the ever-growing transfer of data from numerous networks, cybersecurity experts often find it complex and overwhelming to monitor every activity going on in the network. Due to this, there might be a threat or breach that may go away unnoticed, without producing any alerts.

However, with the capabilities of artificial intelligence, you can avoid issues such as delayed warnings and get notified about bugs in your code as soon as possible. These tools gradually lessen the time it takes a company to get notified about a breach.

4. Strategic Decision Making and Prototyping 

It’s a habit for a developer to go through a hefty and endless list of what needs to be included in a project or code they’re making. However, technological solutions driven by machine learning and AI are capable of analyzing and evaluating the performance of existing applications.æ

With the help of this technology, both business leaders and engineers can work on a solution that cuts down the risk and maximizes the impact. By using natural language and visual interfaces, technical domain experts can develop technologies faster.

5. Skill Enhancement

To keep evolving with the upcoming technology, you need to evolve with the advancement in technology. For the freshers and young developers, AI-based tools help them to collaborate on various software programs and share insights with fellow team members and seniors to learn more about the programming language and software.

Parting Words

While machine learning and AI simplify numerous tasks and activities related to software development, it doesn’t mean that testers and developers are going to lose their jobs. A hired android app developer will still write codes in a faster, better, and more efficient environment, supported by AI and machine learning.

Tags

Join Hacker Noon

Create your free account to unlock your custom reading experience.

Checkout PrimeXBT
Trade with the Official CFD Partners of AC Milan
The Easiest Way to Way To Trade Crypto.
Source: https://hackernoon.com/how-machine-learning-and-ai-are-helping-developers-6g2s33w6?source=rss

Continue Reading

AI

Future of Mobile Apps: Here’s Everything that’s Worth the Wait

Avatar

Published

on

Author profile picture

@devansh-khetrapalDevansh Khetrapal

Devansh writes all about tech. He mainly talks about AI, Machine Learning and Software Development.

This year has been really rough on everyone and I guess we’ve seen enough of that already, but what we’ve also seen during this period are some amazing technological inventions. With phones, however, it’s kinda gotten boring. 

Every year the mobile users are excited because of the new Snapdragon processors and other bleeding-edge specs that these devices are pumping so they can insanely outperform the previous generation smartphones, but are the mobile apps in these phones evolving as congruently?

From the most interactive social media and messaging apps like Facebook, Instagram, WhatsApp, etc, it seems like there isn’t anything beyond that. So what’s next? Well, that’s exactly what we’re going to talk about.

Here’s the Future of Mobile Apps

When we say future of mobile apps, we don’t completely mean that these technologies aren’t already here. In fact, several of these are being incorporated right now. It’s just that these are in their primitive stages of development.

Here they are:

IoT (Internet of Things)

Image source

It’s projected that by 2023, the global spending on IoT technology will be $1.1 trillion. Through Machine Learning and integrated Artificial Intelligence (AI), it has the potential to not just enable billions of devices simultaneously but also leverage the huge volumes of actionable data that can automate diverse business processes.

What does this entail for the future of mobile apps? Well, get ready to be able to control your car, thermostats, and kitchen appliances through your mobile devices. The IoT is being presently used in Manufacturing, Transportation, Healthcare, Energy, and many other industries.

Artificial Intelligence

Image source

AI will single handedly change the future of mobile app design.

Mobile apps are coded to operate within the constraints of certain parameters, the implications of which have to be predefined. Simply put, if you’re browsing for a homestay on Airbnb, the results you see are based on predetermined parameters like your location, your size, and amenity requirements.

Those predetermined parameters, with the assistance of AI, can evolve to a point where you’ll be able to get results based on your preferences that it learned along the way, such as the kind of accommodation you usually prefer, the kind of facilities you need, and may even suggest you buy a place because your favourite restaurant is nearby. 

Augmented Reality (AR) / Virtual Reality (VR)

Image source

AR and VR are attracting a high amount of investments and are forecasted to reach $72.8 billion by 2024. We can already see their success in the gaming and entertainment industry with Pokemon Go, Sky Siege, Google Cardboard, iOnRoad, and Samsung Gear VR.

Brands like Jaguar Land Rover and BMW have already started using VR to conduct design and engineering evaluation sessions to finalize their visual design before they spend any money on manufacturing the parts physically.

Gradually, you’ll be able to make more immersive simulations that can revolutionize any form of architecture involved in it.

Cross-Platform Development

Image source

The future of mobile apps will definitely make native app development obsolete. Currently, React Native offers exceptional flexibility while developing Android and iOS apps. This will save tons of time since you won’t have to develop 2 separate apps.

More importantly, cross-platform app development will eliminate the downside of having to compromise on certain nuanced features. All of this will gradually make the app development process a lot cheaper, simpler, and time-saving.

5G

Image source

Imagine if you could download an entire Netflix series in about 10 seconds. That’s how great the potential of 5G is. Theoretically, it has the potential to reach speeds of 10 Gigabits per second and not just high speeds, but low latency. Even in its infancy, we can witness 5-6 Gigabits per second on our smartphones in the US.

Speaking of the future of mobile apps, well, fast internet would mean faster download and upload speeds, which changes everything from Augmented and Virtual Reality, IoT, supply chain, transportation, smart cities, because everything can happen in real-time because of the latency of merely 2 – 20 milliseconds.

Blockchain

Image source

Blockchain is a term being thrown around a lot lately. Well, it’s a technology that allows data to be stored globally on thousands of servers. Now because it’s decentralized, completely transparent, and immutable, it becomes difficult for one user to gain control over the network.

This means that it’s almost impossible for anyone to hack into blockchain and make changes. The future of app development depends highly on blockchain technology because of its ability to deliver highly secure mobile apps.

Wearable Devices

Image source

You see wearables, or “smartwatches”, being popularly used as fitness bands these days. They’re smart in the sense that they’re able to tell you your heart rate, blood oxygen, count steps, are able to notify you in case of irregular heart rhythms. And of course, it does tell time.

The tech, when combined with IoT, opens up so many doors. Be it checking appointments, making calls, sending messages, getting reminders, it’s just scratching the surface. This tech has a huge potential to evolve and can eventually eliminate the need to use a smartphone. 

Wrapping Up

It’s pretty assuring that the future of mobile apps is ridiculously exciting. We can only imagine how the user experience is going to unfold. 

Be it data visualization with the help of VR and AR, or maximization of convenience with the help of wearables, they’re all going to bring about a massive change in the mobile app development trends. Hopefully, we’ve helped you scratch that itch of curiosity and you got to learn about how our interaction with the world is about to change.

Author profile picture

Read my stories

Devansh writes all about tech. He mainly talks about AI, Machine Learning and Software Development.

Tags

Join Hacker Noon

Create your free account to unlock your custom reading experience.

Checkout PrimeXBT
Trade with the Official CFD Partners of AC Milan
The Easiest Way to Way To Trade Crypto.
Source: https://hackernoon.com/future-of-mobile-apps-heres-everything-thats-worth-the-wait-782k335e?source=rss

Continue Reading
Blockchain5 days ago

‘Bitcoin Senator’ Lummis Optimistic About Crypto Tax Reform

Blockchain5 days ago

Dogecoin becomes the most popular cryptocurrency

Blockchain5 days ago

Billionaire Hedge Fund Manager and a Former CFTC Chairman Reportedly Invested in Crypto Firm

Blockchain5 days ago

Bitcoin Price Analysis: Back Above $50K, But Facing Huge Resistance Now

Blockchain5 days ago

Institutional Investors Continue to Buy Bitcoin as Price Tops $50K: Report

Blockchain5 days ago

NEXT Chain: New Generation Blockchain With Eyes on the DeFi Industry

Big Data3 days ago

Online learning platform Coursera files for U.S. IPO

Blockchain4 days ago

Elrond & Reef Finance Team Up for Greater Connectivity & Liquidity

Blockchain4 days ago

SushiSwap Goes Multi-Chain after Fantom Deployment

Blockchain4 days ago

Here’s why Bitcoin could be heading towards $45,000

Blockchain4 days ago

Non-Fungible Tokens – NFT 101 – Why People are Spending Millions of Dollars for Crypto Art and Digital Items

Blockchain5 days ago

UK Budget Avoids Tax Hikes for Bitcoin Gains

Blockchain4 days ago

eToro and DS TECHEETAH Change Face of Sponsorship With Profit-Only Deal

Blockchain4 days ago

Apple Pay Users Can Now Buy COTI Via Simplex

Blockchain4 days ago

TomoChain (TOMO) Increases after Retesting Previous All-Time High

Business Insider2 days ago

Wall Street people moves of the week: Here’s our rundown of promotions, exits, and hires at firms like Goldman Sachs, JPMorgan, and Third Point

Blockchain5 days ago

Ethereum’s price prospects: What you need to know

Blockchain5 days ago

Silicon Valley-based Taraxa Unveils Details of Upcoming Public Sale

Blockchain4 days ago

Tron Dapps Market Gets A Boost As Bridge Oracle All Set to Launch MainNet Soon

Blockchain5 days ago

Drug traffickers ‘increasingly’ used Bitcoin ATMs to aid illicit transfers in 2020

Trending