Collaborating Authors

health & medicine

Machine Learning-Enabled Prediction of 3D-Printed Microneedle Features


Microneedles (MNs) introduced a novel injection alternative to conventional needles, offering a decreased administration pain and phobia along with more efficient transdermal and intradermal drug delivery/sample collecting. 3D printing methods have emerged in the field of MNs for their time- and cost-efficient manufacturing. Tuning 3D printing parameters with artificial intelligence (AI), including machine learning (ML) and deep learning (DL), is an emerging multidisciplinary field for optimization of manufacturing biomedical devices. Herein, we presented an AI framework to assess and predict 3D-printed MN features. Biodegradable MNs were fabricated using fused deposition modeling (FDM) 3D printing technology followed by chemical etching to enhance their geometrical precision. DL was used for quality control and anomaly detection in the fabricated MNAs. Ten different MN designs and various etching exposure doses were used create a data library to train ML models for extraction of similarity metrics in order to predict new fabrication outcomes when the mentioned parameters were adjusted. The integration of AI-enabled prediction with 3D printed MNs will facilitate the development of new healthcare systems and advancement of MNs’ biomedical applications.

Azure OpenAI Service helps customers accelerate innovation with large AI models


The service has a new responsible AI system that filters out harmful content and helps detect abuse. Additionally, Azure OpenAI Service now offers access to more models, including GPT-3, Codex and embeddings models. Codex can generate code and translate plain language to code, while embeddings make semantic search and other tasks easier. The service also offers new capabilities for customers to fine tune models for more tailored results. Azure OpenAI Service is enabling customers across industries from health care to financial services to manufacturing to quickly perform an array of tasks.

Council Post: An Outsider's View Into Healthcare--What AI Can And Can't Do


Eric is President of Suki and seasoned technology executive with expertise co-founding and scaling companies including Hotwire and Expedia. I recently wrote about the promise of AI and its potential to play an important role in transforming how physicians interact with technology. Even today, AI is making meaningful inroads in specialties ranging from radiology to cardiology. The potential for AI to help physicians work faster and with greater accuracy has industry analysts predicting explosive 10x growth in this decade alone, with estimates reaching $96 billion in 2028. That said, most physicians are only beginning to become familiar with AI and understand its use cases.

Study Says AI Improves Sensitivity of Fracture Detection by 20 Percent


Researchers have noted that traumatic fractures are among the most commonly missed diagnoses.1,2 However, a new study suggests that artificial intelligence (AI) may have significant benefit in improving the assessment of fractures.3 In the study of 500 patients (268 men and 232 women), researchers compared unassisted assessment of acute fractures versus assessment with the assistance of an FDA-cleared algorithm (Boneview, Gleamer) and stand-alone use of AI. The authors found that AI assisted assessment had a 20 percent higher sensitivity (86 percent) of diagnosing fractures on radiographs in comparison to unassisted assessment (66 percent). The use of AI assistance led to a lower number of false negatives (26) in comparison to unassisted radiograph assessment (64), according to the study.

A neural network picks promising antibiotics from a library of chemicals


Biochemists have had some success designing drugs to meet specific goals. But much of drug development remains a tedious grind, screening hundreds to thousands of chemicals for a "hit" that has the effect you're looking for. There have been several attempts to perform this grind in silico, using computers to analyze chemicals, but they had mixed results. Now, a US-Canadian team reports that it modified a neural network to deal with chemistry and used it to identify a potential new antibiotic. Two factors greatly influence the success of neural networks: the structure of the network itself and the training it undergoes.

DIGITIMES: Why are Smart Cities the Future Momentum


DIGITIMES Research report shows that Taiwan's ICT industry development has shifted from focusing on hardware to hardware/software integration models. The industry is combining big data analysis and AI applications in public IoT to facilitate the development of smart city management. Tools such as IoT, AI, cloud computing, and communications technologies are efficiently integrated with urban infrastructure to ultimately produce economic benefits and improve quality of life. It is estimated that the business opportunities of smart cities will reach $2.6 trillion in 2025, mainly in the Asia Pacific region. This includes sectors such as smart poles, building, parking, monitor, government, transportation, fire protection, water conservancy and WITMED.

Elon Musk Fathered Twins With Neuralink Executive In November 2021: Report

International Business Times

A court document petitioning to change the babies' last names to Musk revealed the births. Zilis is the director of operations and special projects at Musk's Neuralink startup. Prior to that, she served as a project director at Tesla. She gave birth to the twins just weeks prior to the arrival of Musk and Grimes' second child born via surrogate, Insider reported. International Business Times was not able to independently verify this report.

Life-threatening ventricular arrhythmia prediction in patients with dilated cardiomyopathy using explainable electrocardiogram-based deep neural networks


The study population were patients with dilated cardiomyopathy, in which an explainable pre-trained deep neural network (FactorECG) was trained for the outcome of life-threatening ventricular arrhythmias. This network encoded the median beat ECG into 21 factors to generate an ECG using only these factors, allowing to evaluate most characteristics that make up an ECG automatically, in a relatively small dataset. LVAD, left ventricular assist device.

Elon Musk fathered twins with one of his executives last year – report

The Guardian

Elon Musk fathered two children in 2021 with Shivon Zilis, a top executive at his artificial intelligence company Neuralink, new court documents show. The world's wealthiest man now has nine known children, including five children with his first wife, Justine Musk, and two with the singer Claire Boucher, known professionally as Grimes. Court documents obtained by Insider and published on Wednesday showed that Elon Musk and Zilis filed a petition to change their twin babies' names to "have their father's last name and contain their mother's last name as part of their middle name". The petition was filed in Austin, Texas, where the babies were born, and was approved by the judge. Zilis reportedly gave birth in November 2021, weeks before Musk and Boucher had their second child via a surrogate.

Genetic Basis for Joint Replacement Failure


Scientists from ExplantLab have identified a genotype that is associated with joint replacement failure in some patients. Based on these findings, the scientists developed a machine-learning algorithm called Orthotype, which uses a patient's genotype and other factors to accurately predict the outcome of joint replacement surgery. More than five million joint replacements are performed globally each year. Although most patients are satisfied with the results of their surgery, a significant number of joint replacements fail early, following adverse immune responses. One of the most popular implant materials used in joint replacements is cobalt chrome (CoCr).