If you are looking for an answer to the question What is Artificial Intelligence? and you only have a minute, then here's the definition the Association for the Advancement of Artificial Intelligence offers on its home page: "the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines."
However, if you are fortunate enough to have more than a minute, then please get ready to embark upon an exciting journey exploring AI (but beware, it could last a lifetime) …
Machine learning, a form of artificial intelligence, may help improve care for patients with kidney failure. Chronic kidney disease is a life-long condition in which the kidneys can gradually stop working over a period of months or years. A significant number of patients with the condition are either on dialysis or have had a kidney transplant. The findings on how machine learning may improve kidney patient care come from a study that are being presented this week at ASN Kidney Week 2019 that takes place from November 5 – November 10 at the Walter E. Washington Convention Center in Washington. For the study, researcher, Ollie Fielding, and his colleagues deployed a machine learning model to identify patients at risk of requiring kidney replacement therapy, such as dialysis or kidney transplantation.
The robot-assisted radical prostatectomy was segmented into 12 steps, and for each step, 41 validated automated performance metrics were reported. The predictive models were trained with three data sets: 1) 492 automated performance metrics; 2) 16 clinicopathological data (for example prostate volume, Gleason score); 3) automated performance metrics plus clinicopathological data. The authors utilized a random forest model (800 trees) to predict continence recovery (no pads or one safety pad) at three and six months after surgery. The prediction accuracy was estimated through a 10-fold cross-validation process. The area under the curve (AUC) and standard error (SE) was used to estimate prediction accuracy. Finally, the out-of-bag Gini index was used to rank the variables of importance.
Despite those obstacles, Indiana University School of Medicine faculty and Regenstrief Institute research scientists had their research published in Nature Communications on April 14, which is an even more significant feat considering one of the leading authors has been quarantined in Wuhan, China for the last two months of their work. The team consists of Affiliated Scientist Jie Zhang, PhD, Regenstrief Institute Research Scientist Kun Huang, PhD, both Indiana University School of Medicine faculty members, Jun Cheng, PhD, of Shenzhen University and colleagues including Liang Cheng, M.D. of IU School of Medicine. The study was led by Dr. Zhang, an assistant professor of medical and molecular genetics at IU School of Medicine. The work focuses on the application of machine learning and image analysis to help researchers distinguish a rare subtype of kidney cancer (translocational renal cell carcinoma, or tRCC) from other subtypes by examining the features of cells and tissues on a microscopic level. Dr. Zhang said the structural similarities have caused a high rate of misdiagnosis.
Tree-based machine learning models are among the most popular non-linear predictive learning models in use today, with applications in a variety of domains such as medicine, finance, advertising, supply chain management, and more. These models are often described as a "black box" -- while their predictions are based on user inputs, how the models arrived at their predictions using those inputs is shrouded in mystery. This is problematic for some use cases, such as medicine, where the patterns and individual variability a model might uncover among various factors can be as important as the prediction itself. Now, thanks to researchers in the Allen School's Laboratory of Artificial Intelligence for Medicine and Science (AIMS Lab) and UW Medicine, the path from inputs to predicted outcome has become a lot less dense. In a paper published today in the journal Nature Machine Intelligence, the team presents TreeExplainer, a novel set of tools rooted in game theory that enables exact computation of optimal local explanations for tree-based models.
In high stakes applications such as healthcare and finance analytics, the interpretability of predictive models is required and necessary for domain practitioners to trust the predictions. Traditional machine learning models, e.g., logistic regression (LR), are easy to interpret in nature. However, many of these models aggregate time-series data without considering the temporal correlations and variations. Therefore, their performance cannot match up to recurrent neural network (RNN) based models, which are nonetheless difficult to interpret. In this paper, we propose a general framework TRACER to facilitate accurate and interpretable predictions, with a novel model TITV devised for healthcare analytics and other high stakes applications such as financial investment and risk management. Different from LR and other existing RNN-based models, TITV is designed to capture both the time-invariant and the time-variant feature importance using a feature-wise transformation subnetwork and a self-attention subnetwork, for the feature influence shared over the entire time series and the time-related importance respectively. Healthcare analytics is adopted as a driving use case, and we note that the proposed TRACER is also applicable to other domains, e.g., fintech. We evaluate the accuracy of TRACER extensively in two real-world hospital datasets, and our doctors/clinicians further validate the interpretability of TRACER in both the patient level and the feature level. Besides, TRACER is also validated in a high stakes financial application and a critical temperature forecasting application. The experimental results confirm that TRACER facilitates both accurate and interpretable analytics for high stakes applications.
Mount Sinai Hospital last year switched on an artificial intelligence program to search the hospital's records for evidence of malnourished patients in its wards. NEW YORK -- Last year, Mount Sinai Hospital switched on an artificial intelligence program to search the hospital's records for evidence of malnourished patients in its wards. The numbers it turned up were eye-popping: 20 percent more cases were diagnosed than in the previous year. Around the same time, Barbara Murphy, chief of the renowned health system's department of medicine, was helping to develop another AI program, to predict whether diabetic patients are at near-term risk of kidney disease and to help prioritize specialist visits for those who are. One of the early findings, according to Murphy: "We probably need some more nephrologists."
DeepMind Technologies, a Google subsidiary and Artificial Intelligence (AI) firm, disclosed that it will adopt Blockchain technology and make use of Distributed Ledger Technology (DLT).This move will help the company secure patient data more efficiently. DeepMind creates algorithms designed for applications, gaming protocols and stimulation. It earned fame for developing a machine-learning program that can be capable of playing video games. Likewise, DeepMind developed the so-called "Neural Turing Machine" that copies short-term memory of human beings. It signed a five-year contract with Royal Free London NHS Trust recently so it can apply the technology to healthcare.
The healthcare sector has been exploring applications of 3D printing for decades, but the cost and complexity of scaling the technology has stunted its path to mass adoption. Axial3D is hoping to overcome these barriers by incorporating machine learning into the process. The Belfast-based startup has developed a system that uses computer vision algorithms to automatically label CT and MRI scans and then converts the images into 3D-printed models of an individual patient's anatomy. Using machine learning to produce the models helps cut the time to create and deliver the 3D-printed files from up to eight weeks down to 24-48 hours, the startup claims. "The challenge is really to identify the anatomy within an MRI or CT scan," Axial3D CTO Niall Haslan tells Techworld.
Deep learning has demonstrated success in health risk prediction especially for patients with chronic and progressing conditions. Most existing works focus on learning disease Network (StageNet) model to extract disease stage information from patient data and integrate it into risk prediction. StageNet is enabled by (1) a stage-aware long short-term memory (LSTM) module that extracts health stage variations unsupervisedly; (2) a stage-adaptive convolutional module that incorporates stage-related progression patterns into risk prediction. We evaluate StageNet on two real-world datasets and show that StageNet outperforms state-of-the-art models in risk prediction task and patient subtyping task. Compared to the best baseline model, StageNet achieves up to 12% higher AUPRC for risk prediction task on two real-world patient datasets. StageNet also achieves over 58% higher Calinski-Harabasz score (a cluster quality metric) for a patient subtyping task.
"Our results show that it is possible to train an AI system to detect and grade prostate cancer on the same level as leading experts," study author Martin Eklund, with Karolinska Institutet in Sweden, said in a statement. "This has the potential to significantly reduce the workload of uro-pathologists and allow them to focus on the most difficult cases."