Deep Learning in Medicine—Promise, Progress, and Challenges

By Fei Wang, Lawrence Peter Casalino, and Dhruv Khullar

JAMA Network Open, December 17, 2018

 

Recent years have seen a surge of interest in machine learning and artificial intelligence techniques in health care.1 Deep learning2 represents the latest iteration in a progression of artificial intelligence technologies that have allowed machines to mimic human intelligence in increasingly sophisticated and independent ways.3 Early medical artificial intelligence systems relied heavily on experts to train computers by encoding clinical knowledge as logic rules for specific clinical scenarios. More advanced machine learning systems train themselves to learn these rules by identifying and weighing relevant features from the data, such as pixels from medical images, or raw information from electronic health records (EHRs).

Access article here

Tags:
10 Hits
0 Comments

Making Machine Learning Models Clinically Useful

By Nigam H. Shah, Arnold Milstein, and Steven C. Bagley

JAMA Network Open, August 8, 2019

 

Recent advances in supervised machine learning have improved diagnostic accuracy and prediction of treatment outcomes, in some cases surpassing the performance of clinicians.1 In supervised machine learning, a mathematical function is constructed via automated analysis of training data, which consists of input features (such as retinal images) and output labels (such as the grade of macular edema). With large training data sets and minimal human guidance, a computer learns to generalize from the information contained in the training data. The result is a mathematical function, a model, that can be used to map a new record to the corresponding diagnosis, such as an image to grade macular edema. Although machine learning–based models for classification or for predicting a future health state are being developed for diverse clinical applications, evidence is lacking that deployment of these models has improved care and patient outcomes.2

Access article here

Tags:
12 Hits
0 Comments

Antibody Treatment against Angiopoietin-Like 4 Reduces Pulmonary Edema and Injury in Secondary Pneumococcal Pneumonia

By Liang Li, Benjamin Jie Wei Foo, Ka Wai Kwok, Noriho Sakamoto, Hiroshi Mukae, Koichi Izumikawa, Stéphane Mandard, Jean-Pierre Quenot, Laurent Lagrost, Wooi Keong Teh, Gurjeet Singh Kohli, Pengcheng Zhu, Hyungwon Choi, Martin Lindsay Buist, Ju Ee Seet, Liang Yang, Fang He, Vincent Tak Kwong Chow, Nguan Soon Tan

mBio. June 4, 2019

 

Secondary bacterial lung infection by Streptococcus pneumoniae (S. pneumoniae) poses a serious health concern, especially in developing countries. We posit that the emergence of multiantibiotic-resistant strains will jeopardize current treatments in these regions. Deaths arising from secondary infections are more often associated with acute lung injury, a common consequence of hypercytokinemia, than with the infection per se. Given that secondary bacterial pneumonia often has a poor prognosis, newer approaches to improve treatment outcomes are urgently needed to reduce the high levels of morbidity and mortality. Using a sequential dual-infection mouse model of secondary bacterial lung infection, we show that host-directed therapy via immunoneutralization of the angiopoietin-like 4 c-isoform (cANGPTL4) reduced pulmonary edema and damage in infected mice. RNA sequencing analysis revealed that anti-cANGPTL4 treatment improved immune and coagulation functions and reduced internal bleeding and edema. Importantly, anti-cANGPTL4 antibody, when used concurrently with either conventional antibiotics or antipneumolysin antibody, prolonged the median survival of mice compared to monotherapy. Anti-cANGPTL4 treatment enhanced immune cell phagocytosis of bacteria while restricting excessive inflammation. This modification of immune responses improved the disease outcomes of secondary pneumococcal pneumonia. Taken together, our study emphasizes that host-directed therapeutic strategies are viable adjuncts to standard antimicrobial treatments.

Access article here

Tags:
74 Hits
0 Comments

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography

 

By Diego Ardila, Atilla P. Kiraly, Sujeeth Bharadwaj, Bokyung Choi, Joshua J. Reicher, Lily Peng, Daniel Tse, Mozziyar Etemadi, Wenxing Ye, Greg Corrado, David P. Naidich & Shravya Shetty

Nature Medicine, May 20, 2019

 

With an estimated 160,000 deaths in 2018, lung cancer is the most common cause of cancer death in the United States. Lung cancer screening using low-dose computed tomography has been shown to reduce mortality by 20–43% and is now included in US screening guidelines. Existing challenges include inter-grader variability and high false-positive and false-negative rates. We propose a deep learning algorithm that uses a patient’s current and prior computed tomography volumes to predict the risk of lung cancer. Our model achieves a state-of-the-art performance (94.4% area under the curve) on 6,716 National Lung Cancer Screening Trial cases, and performs similarly on an independent clinical validation set of 1,139 cases. We conducted two reader studies. When prior computed tomography imaging was not available, our model outperformed all six radiologists with absolute reductions of 11% in false positives and 5% in false negatives. Where prior computed tomography imaging was available, the model performance was on-par with the same radiologists. This creates an opportunity to optimize the screening process via computer assistance and automation. While the vast majority of patients remain unscreened, we show the potential for deep learning models to increase the accuracy, consistency and adoption of lung cancer screening worldwide.

Continue reading
Tags:
147 Hits
0 Comments

Artificial Intelligence in Health Care Will the Value Match the Hype?

By Ezekiel J. Emanuel and Robert M. Wachter

JAMA Network Open, May 20, 2019

 

Artificial intelligence (AI) and its many related applications (ie, big data, deep analytics, machine learning) have entered medicine’s “magic bullet” phase. Desperate for a solution for the never-ending challenges of cost, quality, equity, and access, a steady stream of books, articles, and corporate pronouncements makes it seem like health care is on the cusp of an “AI revolution,” one that will finally result in high-value care.

While AI has been responsible for some stunning advances, particularly in the area of visual pattern recognition,1-3 a major challenge will be in converting AI-derived predictions or recommendations into effective action.

Continue reading
Tags:
13 Hits
0 Comments