Liver transplantation is a life-saving procedure for patients with end-stage liver disease. There are two main challenges in liver transplant: finding the best matching patient for a donor and ensuring transplant equity among different subpopulations. The current MELD scoring system evaluates a patient's mortality risk if not receiving an organ within 90 days. However, the donor-patient matching should also take into consideration post-transplant risk factors, such as cardiovascular disease, chronic rejection, etc., which are all common complications after transplant. Accurate prediction of these risk scores remains a significant challenge. In this study, we will use predictive models to solve the above challenge. We propose a deep learning framework model to predict multiple risk factors after a liver transplant. By formulating it as a multi-task learning problem, the proposed deep neural network was trained on this data to simultaneously predict the five post-transplant risks and achieve equally good performance by leveraging task balancing techniques. We also propose a novel fairness achieving algorithm and to ensure prediction fairness across different subpopulations. We used electronic health records of 160,360 liver transplant patients, including demographic information, clinical variables, and laboratory values, collected from the liver transplant records of the United States from 1987 to 2018. The performance of the model was evaluated using various performance metrics such as AUROC, AURPC, and accuracy. The results of our experiments demonstrate that the proposed multitask prediction model achieved high accuracy and good balance in predicting all five post-transplant risk factors, with a maximum accuracy discrepancy of only 2.7%. The fairness-achieving algorithm significantly reduced the fairness disparity compared to the baseline model.

This article is adapted from Voices in the Code: A Story About People, Their Values, and the Algorithm They Made, out Sept. 8 from Russell Sage Foundation Press. In May 2021, I got a call I never expected. I was working on a book about A.I. ethics, focused on the algorithm that gives out kidneys to transplant patients in the United States. Darren Stewart--a data scientist from UNOS, the nonprofit that runs the kidney allocation process--was calling to get my take: How many decimal places should they include when calculating each patient's allocation score? The score is an incredibly important number, given it determines which patient will get first chance at each donated organ.

LAS VEGAS – At 18 months old, Chris Rodriguez was diagnosed with heart failure and required a transplant. "My heart was pumping too much blood and my organs couldn't deal with it," said Rodriguez, now 14. "Most of my life, I've just been in and out of the hospital. More than 100,000 people are on the national transplant waiting list, and approximately 17 people die each day waiting to receive an organ transplant, according to the Health Resources and Services Administration. COVID-19 has complicated the situation even more, as travel restrictions and fewer commercial flights have made it difficult to transplant organs and highlighted the need for alternative travel methods to deliver vital organs. Nevada Donor Network partnered with MissionGo to test drones to deliver vital organs. "As a result of the COVID-19 pandemic, we have been subjected to fewer commercial flights to be able to transport organs for transplantation," Joe Ferreira, Nevada Donor Network CEO said. "We've had to look ...

Artificial intelligence (AI) is a buzzword in tech these days. The term, which encompasses a range of technologies including machine learning and data analysis. The goal is to create systems that can perceive, learn, and reason in ways that mimic human capabilities. At its best, AI will allow machines to understand the gestalt of a situation and react accordingly, a capability that humans take for granted – but has tends to elude computer systems, which in their turn excel at analyzing minute details. A wide range of tech companies are working on AI systems; artificial intelligence holds the promise of real-time data analysis and situation monitoring, with the machines capable of handling routine decisions.

Artificial intelligence (AI) is a buzzword in tech these days. The term, which encompasses a range of technologies including machine learning and data analysis. The goal is to create systems that can perceive, learn, and reason in ways that mimic human capabilities. At its best, AI will allow machines to understand the gestalt of a situation and react accordingly, a capability that humans take for granted – but has tends to elude computer systems, which in their turn excel at analyzing minute details. A wide range of tech companies are working on AI systems; artificial intelligence holds the promise of real-time data analysis and situation monitoring, with the machines capable of handling routine decisions. While it hasn’t been achieved yet, the outlines of success are visible on the horizon. Every smart investor knows to keep his eyes on the horizon; that is, to plan every investment with long-range intentions. Just how long is up to the individual, but most investors agree that a move isn’t long-term unless it’s held for more than one year. Warren Buffett has famously said, “If you are not willing to own a stock for 10 years, do not even think about owning it for 10 minutes.” With this in mind, we used TipRanks' database to identify three AI stocks that have been highlighted by some of Wall Street’s best tech sector analysts. These are analysts with 5-star ratings, standing above their peers in accuracy and average returns – and they’ve tapped Artificial Intelligence as a tech segment for the long run. Veritone, Inc. (VERI) We’ll start with Veritone. This media tech company offers a cloud-based operating system for AI that uses machine learning to turn data into useful intelligence. The software allows users to process audio and video in real time, enhance analytics and research apps, reduce content review times, and streamline time spent on ‘low-value, high-effort’ tasks. The value of the product to the customers can be seen in the quarterly earnings trends and the share appreciation. The last six months – covering the worst of the global pandemic and economic recessionary pressures – have seen VERI’s earnings steadily improve and the share price rise to its best level in over two years. Earlier this month, Veritone showed its confidence by adjusting its Q2 revenue guidance upwards. The guidance, of $13.1 to $13.3 million, is well above the previous upper guide of $12.2 million. The share price has tracked the gains in revenue and earnings. The stock has more than doubled since the February/March market collapse, rising from $3.03 to $10.83 now. Patrick Walravens, writing from JMP Securities, was impressed by Veritone’s new revenue guidance, and reiterated his Buy rating on the stock. In his comments, he said, “Veritone seems to be gaining traction in its Government, Legal, and Compliance verticals as it experienced record bookings in the quarter… we believe the company is moving its cost structure in the right direction with recent cost-reduction initiatives and upgrades…” With his $17 price target, Walravens shows his own confidence that VERI will see 57% growth in the year ahead. (To watch Walravens’ track record, click here) Overall, VERI’s Moderate Buy analyst consensus rating is based on 4 Buys and just a single Sell. The stock’s current price is $11.80, and the average price target $16.25 suggests it has a 50% upside potential. Note that even the low-ball target estimate, of $15, is well above the current price. (See Veritone stock analysis on TipRanks) ZoomInfo Technologies (ZI) Next up is ZoomInfo, a marketing tech company. ZI offers the usual features and services that customers expect in digital marketing intelligence, including account management, data management, demand generation, and lead prospecting. The company’s AI cloud software is specifically designed to improve efficiency in these tasks, letting sellers get to the business of selling. ZoomInfo is a newly public company, having held its IPO just this past June. The opening was a success, with share prices almost doubling on the first day and nearly tripling in the first few trading sessions. Even now, after nearly two months during which the initial excitement waned and the glow came off the rose, the stock is still trading 88% above its initial price of $21. The strong IPO prompted SunTrust Robinson analyst Terry Tillman – who is rated in the top 10 of the TipRanks analyst database – to initiate coverage of the stock with a Buy rating. Tillman wrote of ZoomInfo, “We believe ZoomInfo represents a rare combination of strong top-line growth and best-in-class profitability. Its go-to-market (GTM) sales intelligence platform drives positive outcomes for B2B sales and marketing organizations - increasing leads, customers and revenue. Premium valuation justified owing to accelerating demand for GTM intelligence and company-specific drivers leading to significant revenue and profit upside.” Tillman’s Buy rating comes with a $60 price target, implying an impressive 51% upside potential. (To watch Tillman’s track record, click here) ZoomInfo holds a Moderate Buy rating from the analyst consensus. This is based on 16 reviews, including 7 Buys and 9 Holds. The stock’s $55.07 average price target suggests it has room for 32% growth from the $41.66 trading price this year. (See ZoomInfo stock analysis on TipRanks) CareDx (CDNA) Last on today’s list is a tech company in the health care sector. CareDx develops and delivers diagnostic surveillance systems for heart transplant patients. The company’s AI-powered software monitors patient progress in real time, allowing both the patient and the doctors to respond to any rapidly changing health issues in time to ensure a more successful outcome. The result is a novel development in long-term care. While CareDx’s products were originally designed to monitor heart transplants, the company has expanded. Its products now monitor most human organ transplants – including kidneys, an important niche, as the first successful organ transplant was conducted with a kidney, and this procedure is still among the most common of transplants. CareDx also has cloud-based AI systems to monitor lab results, and to connect digital implants with remote monitors. The company’s earnings have proven mostly immune to recent economic instability, as medical transplant patients and doctors cannot simply stop using the monitoring systems. And with a firm user base, the stock recovered well from the late-winter market crash. CDNA is up over 130% since bottoming out in March. Covering the stock for Piper Sandler, analyst Steven Mah wrote, “We believe CareDx has the broadest transplant care platform in the industry and we remain confident that it is well-positioned to protect and extend its first-mover advantage in both pre- and post-transplant patient management to drive long-term growth. In addition, we are encouraged by the resiliency of its essential tests and ability to operate in a COVID-19 environment.” Mah gives CDNA a Buy rating, along with a $54 price target that implies an upside of 66% for the next 12 months. (To watch Mah’s track record, click here) All in all, with 4 recent reviews on record, all Buys, CareDx has a unanimous Strong Buy rating from the analyst consensus. The stock is currently selling for $32.59, and the average price target, at $42.75, suggests a one-year upside of 31%. (See CareDx stock-price forecast on TipRanks) To find good ideas for tech stocks trading at attractive valuations, visit TipRanks’ Best Stocks to Buy, a newly launched tool that unites all of TipRanks’ equity insights.

BRISBANE, Calif., May 02, 2019 (GLOBE NEWSWIRE) -- CareDx, Inc. (Nasdaq:CDNA), a molecular diagnostics company focused on the discovery, development and commercialization of clinically differentiated, high-value diagnostic solutions for transplant patients, today announced a partnership with Cibiltech, a French MedTech company that develops AI-based products for predictive medicine, to commercialize Predigraft. Predigraft is a data analysis tool that provides an early prediction of an individual's risk of allograft rejection and transplant loss. It was developed from Cibiltech's proprietary software algorithm called iBox, which is built off the outcomes data from tens of thousands of transplant patients. "I see incredible value in using prognostic data alongside a measure of organ injury from non-invasive biomarkers such as AlloSure," said Gaurav Gupta, MD, Virginia Commonwealth University. "This can give me insights that shape the care I give to my transplant patients."

Drone technology is increasingly proving itself across a variety of industries, including the medical field where the machine's ability to be quickly deployed and move at speed across urban areas for vital deliveries can be a literal lifesaver. In what's believed to be a world first, researchers at the University of Maryland this week announced the successful transportation of a kidney for a woman needing a transplant. "This whole thing is amazing," the unnamed patient said. "Years ago, this was not something that you would think about." Following the successful operation, the 44-year-old Baltimore resident was discharged from hospital on Tuesday.