Purpose: This study aimed to develop an open-source multimodal large language model (CXR-LLAVA) for interpreting chest X-ray images (CXRs), leveraging recent advances in large language models (LLMs) to potentially replicate the image interpretation skills of human radiologists Materials and Methods: For training, we collected 592,580 publicly available CXRs, of which 374,881 had labels for certain radiographic abnormalities (Dataset 1) and 217,699 provided free-text radiology reports (Dataset 2). After pre-training a vision transformer with Dataset 1, we integrated it with an LLM influenced by the LLAVA network. Then, the model was fine-tuned, primarily using Dataset 2. The model's diagnostic performance for major pathological findings was evaluated, along with the acceptability of radiologic reports by human radiologists, to gauge its potential for autonomous reporting. Results: The model demonstrated impressive performance in test sets, achieving an average F1 score of 0.81 for six major pathological findings in the MIMIC internal test set and 0.62 for seven major pathological findings in the external test set. The model's F1 scores surpassed those of GPT-4-vision and Gemini-Pro-Vision in both test sets. In human radiologist evaluations of the external test set, the model achieved a 72.7% success rate in autonomous reporting, slightly below the 84.0% rate of ground truth reports. Conclusion: This study highlights the significant potential of multimodal LLMs for CXR interpretation, while also acknowledging the performance limitations. Despite these challenges, we believe that making our model open-source will catalyze further research, expanding its effectiveness and applicability in various clinical contexts. CXR-LLAVA is available at https://github.com/ECOFRI/CXR_LLAVA.

Radiology is a crucial component of modern medicine, as it involves the use of medical imaging to diagnose and treat various conditions. However, interpreting these images can be a challenging task that requires significant expertise and experience. This is where artificial intelligence (AI) comes in. In recent years, AI has emerged as a powerful tool in radiology, enabling more accurate and efficient diagnoses. In this article, we will explore the application of Artificial Intelligence in radiology and its potential to revolutionize healthcare.

Artificial intelligence (AI) has revolutionized many industries, and healthcare is no exception. In recent years, AI has made significant strides in healthcare, from assisting doctors in diagnosing diseases to helping researchers develop new drugs. However, with the rapid advances in AI, there is growing concern about whether AI will take over healthcare jobs. Artificial Intelligence has many applications in healthcare, including medical imaging, drug discovery, and patient monitoring. One of the most significant benefits of Artificial Intelligence in healthcare is its ability to analyze vast amounts of data quickly and accurately. This allows doctors and researchers to make more informed decisions and identify patterns that would be difficult or impossible to detect manually.

Harvard Medical School scientists and colleagues at Stanford University have developed an artificial intelligence diagnostic tool that can detect diseases on chest X-rays directly from natural-language descriptions contained in accompanying clinical reports. The step is deemed a major advance in clinical AI design because most current AI models require laborious human annotation of vast reams of data before the labeled data are fed into the model to train it. A report on the work, published Sept. 15 in Nature Biomedical Engineering, shows that the model, called CheXzero, performed on par with human radiologists in its ability to detect pathologies on chest X-rays. The team has made the code for the model publicly available for other researchers. Most AI models require labeled datasets during their "training" so they can learn to correctly identify pathologies. This process is especially burdensome for medical image-interpretation tasks since it involves large-scale annotation by human clinicians, which is often expensive and time-consuming.

Artificial intelligence programs that check medical images for evidence of cancer can be duped by hacks and cyberattacks, according to a new study. Researchers demonstrated that a computer program could add or remove evidence of cancer from mammograms, and those changes fooled both an AI tool and human radiologists. That could lead to an incorrect diagnosis. An AI program helping to screen mammograms might say a scan is healthy when there are actually signs of cancer or incorrectly say that a patient does have cancer when they're actually cancer free. Such hacks are not known to have happened in the real world yet, but the new study adds to a growing body of research suggesting healthcare organizations need to be prepared for them.

The idea behind centaur chess was simple: while the best AI could now defeat the best human at chess, an AI and human working together (a "centaur") would be the most powerful player of all, because man and machine would bring complementary skills to bear. And because humans and AIs are strong on different dimensions, together, as a centaur, they can beat out solo humans and computers alike." AI is now so far superior to humanity in this domain that a human player would simply have nothing to add. For instance, once an AI system can provably drive a truck better and safer in all conditions than a human can--the technology is not there today, but it is getting closer--it simply will not make sense for humans to continue driving trucks. A common refrain in the field of radiology these days goes like this: "AI will not replace radiologists, but radiologists who use AI will replace radiologists who do not." This is a quintessential articulation of the myth of augmentation. So to start, AI will indeed be used to augment human radiologists: to provide a second opinion, for instance, or to sift through troves of images to prioritize those that merit human review. Once it is established beyond dispute that neural networks are superior to human radiologists at classifying medical images--across patient populations, care settings, disease states--will it really make sense to continue employing human radiologists? From security guards to accountants, from taxi drivers to lawyers, from cashiers to stock brokers, from court reporters to pathologists, human workers across the economy will find their skills out of demand and their roles obsolete as increasingly sophisticated AI systems come to perform these activities better, cheaper and faster than humans can. Chief among these are roles that involve empathy, camaraderie, social interaction, the "human touch." Human babysitters, nurses, therapists, schoolteachers, and social workers, for instance, will continue to find work for many years to come. The idea behind centaur chess was simple: while the best AI could now defeat the best human at chess, an AI and human working together (a "centaur") would be the most powerful player of all, because man and machine would bring complementary skills to bear. And because humans and AIs are strong on different dimensions, together, as a centaur, they can beat out solo humans and computers alike."

Geoffrey Hinton is a legendary computer scientist. When Hinton, Yann LeCun, and Yoshua Bengio were given the 2018 Turing Award, considered the Nobel prize of computing, they were described as the "Godfathers of artificial intelligence" and the "Godfathers of Deep Learning." Naturally, people paid attention when Hinton declared in 2016, "We should stop training radiologists now, it's just completely obvious within five years deep learning is going to do better than radiologists." The US Food and Drug Administration (FDA) approved the first AI algorithm for medical imaging that year and there are now more than 80 approved algorithms in the US and a similar number in Europe. Yet, the number of radiologists working in the US has gone up, not down, increasing by about 7% between 2015 and 2019.

Dating back to the Industrial Revolution, people have speculated that machines would render human ... [ ] work obsolete. Unlike in earlier eras, artificial intelligence will prove this prophecy true. "When looms weave by themselves, man's slavery will end." Stanford is hosting an event next month named "Intelligence Augmentation: AI Empowering People to Solve Global Challenges." This title is telling and typical.

India faces a drastic shortage of radiologists with just one radiologist available for 100,000 people living in the country. In comparison, this ratio is one to 10,000 in the US. With such a shortage of qualified professionals in the field, radiologists tend to see hundreds of X-rays in a day making the process error-prone. DeepTek, a Pune-based health-tech firm, has created an AI-based platform, Augmento, that assists radiologists to make faster and accurate diagnoses through X-rays for 20 different pathologies. To understand how the platform works and the advantage it provides in terms of making accurate diagnoses using AI in radiology, Analytics India Magazine caught up with Viraj Kulkarni, Principal Data Scientist at DeepTek.

The practice of medicine is one where innovation is literally a matter of life or death, there's always an urgent need for a new test to diagnose a mysterious new disease and a new miracle treatment to save someone afflicted by it. Innovation in healthcare is essential, and those pushing medicine's boundaries have the supreme motivation to do so; they want to alleviate suffering and save lives. As we turn the corner on 2020, we find ourselves in the midst of the worst pandemic in a century and humanity's brightest minds are focused on rapidly innovating healthcare solutions for pandemic-scale problems to save lives. The failure to scale healthcare systems over the last few decades has resulted in intense pressure to scale pandemic response in months; it is unequivocally clear that as a result our health systems will be transformed in the post pandemic world. Let's explore the major anticipated transformation. In the decade since 2010, smart phones "apps" went from buzzwords to integral parts of healthcare delivery.