Category Archives: Uncategorized

New Dartmouth Center Applies AI to Improve Health Outcomes – Dartmouth News

Dartmouth has created a Center for Precision Health and Artificial Intelligence to spur interdisciplinary research that can better leverageas well as more safely and ethically deploybiomedical data in assessing and treating patients and improving their health care outcomes.

The center is being launched with initial funding of $2 million from the Geisel School of Medicine and Dartmouth Cancer Center and is based in the Williamson Translational Research Building, a Dartmouth-owned building on the Dartmouth Hitchcock Medical Center campus in Lebanon, N.H.

Artificial intelligence is poised to play a transformative role in health care by delivering rapid and innovative solutions to real-world clinical challenges, improving patient outcomes, and creating better and more equitable access for all, says President Philip J. Hanlon 77.

This new center will help foster innovation and collaboration in these critically important fields.

Precision health is a holistic approach that aims to personalize health care by tailoring treatments and disease prevention strategies to a persons unique biologytheir genes, medical history, lifestyle, and environment.

A wealth of biomedical data can be gathered through genomic sequencing, molecular testing, imaging techniques, and wearable monitoring devices, all of which have become more advanced, affordable, and broadly available over the past decade.


It is truly a Dartmouth center with leaders and advisers from across the institution connecting clinicians and AI scientists.


Duane Compton, dean of the Geisel School of Medicine

AI holds the key to extracting valuable insight from this deluge of data because it can sift through and analyze complex and heterogeneous information to identify trends and patterns and extract digital biomarkers that can guide clinically actionable decisions.

Machine learning models trained on a host of different data sets can predict disease risk, enhance the accuracy of diagnoses, anticipate the course of an illness, and tailor treatment options best suited to the patient.

CPHAI will be governed by the dean of Geisel and advised by a committee that will have representatives and stakeholders from Geisel, Dartmouth Cancer Center, Thayer School of Engineering, Arts and Sciences, and Dartmouth Health.

It is truly a Dartmouth center with leaders and advisers from across the institution connecting clinicians and AI scientists, says Geisel Dean Duane Compton.

By harnessing the power of AI and machine learning, CPHAI aims to create a toolbox of digital technologies that will empower providers to identify and deliver the most effective health care strategy for each patient.

Researchers will work on projects such as developing AI-driven diagnostic tools, optimizing treatment strategies, and analyzing biomedical data to inform public health policies.

AI models created through collaborations with radiologists and pathologists will be able to draw precise and complex inferences directly from medical images that complement the knowledge and experience of human imaging professionals and make diagnoses more reliable and efficient, reducing potential diagnostic errors.

The center will also enable researchers to evaluate new digital tools they develop in clinical settings, paving the way for creating and building applications that can be integrated into health care systems after seeking FDA approval.

What makes CPHAI unique is its interdisciplinary and comprehensive approach to precision health and artificial intelligence, focusing not only on technological advancements but also on ethical and societal implications, says Saeed Hassanpour, associate professor of biomedical data science, epidemiology, and computer science, who serves as the centers inaugural director.

Saeed Hassanpour stands outside the Williamson Translational Research Building, where the new center is based, on the campus of Dartmouth Hitchcock Medical Center in Lebanon, N.H. (Photo by Katie Lenhart)

The center, which will collaborate with the Dartmouth Ethics Institute, Neukom Institute for Computational Science, and the Wright Center for the Study of Computation and Just Communities, is committed to ensuring the ethical use of AI and fostering diversity and inclusion in the field, says Hassanpour. This commitment will help identify the limitations of AI, address issues related to biases in AI algorithms and datasets, improve transparency and privacy, and ensure equitable outcomes for all individuals, regardless of their background.

CPHAI will also create new educational and training opportunities, attracting students and professionals interested in pursuing careers in AI and precision health, says Hassanpour. These opportunities will help develop a skilled workforce in the Upper Valley region, making it an attractive destination for technology and health care companies.

Medical residents, postdocs, and studentsboth graduate and undergraduateinterested in working with artificial intelligence will also find unique opportunities for learning and research, Compton says.

We want every individual to reach their optimal health, which means both prevention and care medicine must come together. Precision health is a broader application than precision medicine, says Compton.

The new Dartmouth center has been in the works for several years and comes as the market for AI in health care is expected to grow tremendouslyfrom just under $5 billion in 2020 to more than $45 billion in 2026.

Many of us at Dartmouth have been working in AI in the last several years. We have the talent, skills, experience, and material to develop and implement innovative AI-driven diagnostic tools, says Arief Suriawinata, chair of pathology and laboratory medicine and a member of the centers advisory committee. The formation of CPHAI will foster intercampus and interdisciplinary collaborations, attract and retain top talent, and secure additional funding for our concerted efforts.

The technologies developed at CPHAI will help pathologists in triaging and screening cases, improve the diagnostic standard and quality, and optimize workflow, he says.

Another member of the advisory committee, Jocelyn Chertoff, chair of radiology, also sees great promise for patients from the centers work.

From management of administrative clinical tasks to computer-aided detection of cancers, radiologists are already using AI, Chertoff says. Tools based on deep learning algorithms promise to transform the practice by helping radiologists better interpret images, make the process of producing images from scanners more accurate and efficient, and improve a hospitals overall workflow so that patients get the most timely care.

Also on the advisory committee are Steven Leach, director of the Dartmouth Cancer Center, Elizabeth F. Smith, dean of the Faculty of Arts and Sciences, Steven Bernstein, Dartmouth Health chief research officer, Michael Whitfield, chair of biomedical data science, and Charles Thomas Jr. 79, chief of radiation oncology.

Hassanpour expects that the center will actively engage with local and global communities to ensure their perspectives, concerns, and needs are considered in the development and application of AI technologies. This engagement will serve to build trust and awareness about the benefits and potential risks of AI in health care.

Overall, CPHAIs presence in our region could lead to significant advancements in health care, education, and economic development, positioning the area as a leader in AI and precision health research, he says.


An FAQ on the CPHAI is also available.

More here:
New Dartmouth Center Applies AI to Improve Health Outcomes - Dartmouth News

Artificial intelligence in factory maintenance is no longer a matter of the future – ReadWrite

Undetected machine failures are the most expensive ones. That is why many manufacturing companies are looking for solutions that automate and reduce maintenance costs. Traditional vibrodiagnostic methods can be too late in many cases. Taking readings in the presence of a diagnostician occasionally may not detect a fault in advance. 2017 Position Paper from Deloitte (Deloitte Analytics Institute 7/2017) claimed that maintenance in the environment of Industry 4.0.The benefits of predictive maintenance are dependent on the industry or the specific processes that it is applied to. However, Deloitte analyses at that time have already concluded that material cost savings amount to 5 to 10% on average. Equipment uptime increases by 10 to 20%. Overall maintenance costs are reduced by 5 to 10% and maintenance planning time is even reduced by 20 to 50%! Neuron Soundware has developed a artificial intelligence powered technology for predictive maintenance.

Stories from companies that have embarked on the digital journey are no longer just science fiction. They are real examples of how companies are coping with the lack of skilled labor on the market. Usually mechanic-maintainer who regularly goes around all the machines and diagnoses their condition by listening to them. Some companies are nowlooking for new maintenance technologies to replace

A failure without early identification means replacing the entire piece of equipment or its part. Waiting for the spare part which may not be in stock right now. Because it is expensive to stock replacement equipment. Devaluation of the current pieces of the component in the production thus the discarding of the entire production run. Finally, yet importantly, it would represent up to XY hours of production downtime. The losses might run into tens of thousands of euros.

Such a critical scenario is not possible if the maintenance technology is equipped with artificial intelligence in addition to the mechanical knowledge of the machines. It applies this knowledge itself to the current state of the machine. It is also able to recognize which anomalous behavior is currently occurring on the machine. Based on that send the send the corresponding alert with precise maintenance instructions. Manufacturers of mechanical equipment such as lifts, escalators, and mobile equipment use this today, for example.

However, predictive maintenance technologies have much wider applications. Thanks to the learning capabilities of artificial intelligence, they are very versatile. For example, the technology is able to assist in end-of-line testing. For example to identify defective parts of produced goods which are invisible to the eye and appear randomly.

The second area of application lies in the monitoring of production processes. We can imagine this with the example of a gravel crusher. A conveyor delivers different sized pieces of stone into grinders, which are to yield a given granularity of gravel. Previously, the manufacturer would run the crusher for a predetermined amount of time. To make sure that even in the presence of the largest pieces of rock, sufficient crushing occurred. With the artificial intelligence listening to the size of the gravel. He can stop the crushing process at the right point. This means not only saving wear and tear on the crushing equipment but more importantly, saving time and increasing the volume of gravel delivered per shift. This brings great financial benefit to the producer.

When implementing predictive maintenance technology, it does not matter how big the company is. The most common decision criterion is the scalability of the deployed solution. In companies with a large number of mechanically similar devices, it is possible to quickly collect samples that represent individual problems. From which the neural network learns. It can then handle any number of machines at once. The more machines, the more opportunities for the neural network to learn and apply detection of unwanted sounds.

Condition monitoring technologies are usually designed for larger plants rather than for workshops with a few machine tools. However, as hardware and data transmission and processing get progressively cheaper, the technology is getting there too. So even a home marmalade maker will soon have the confidence that his machines will make enough produce, deliver orders to customers on time, and not ruin its reputation.

In the future, predictive maintenance will be a necessity. In industry also in larger electronic appliances such as refrigerators and coffee machines, or in cars. For example, we can all recognize a damaged exhaust or an unusual sounding engine. Nevertheless, it is often too late to drive the car safely home from a holiday. For example, without a visit to the workshop. With the installation of an AI-driven detection device, we will know about the impending breakdown in time and be able to resolve the problem in time, before the engine seizes up and we have to call a towing service.

Pavel is a tech visionary, speaker, and founder of AI and IoT startup Neuron Soundware. He started his career at Accenture, where he took part in 35+ technology and strategy projects on 3 continents over 11years. He got into entrepreneurship in 2016 when he founded a company focused on predictive machine maintenance using sound analysis.

Here is the original post:
Artificial intelligence in factory maintenance is no longer a matter of the future - ReadWrite