Great article on what it takes for #artificialintelligence initiatives to succeed. Hiring a data scientist is only one of the steps :-) Happy to share some of my perspective on technology strategy on #6
https://bit.ly/3tMJHcN
In this article I discuss how AI is being used to predict and prevent a range of chronic health concerns, including healthcare-associated infections for MedCity News: http://ow.ly/KODo50CAxxL
I’m briefly cited towards the end of this article on #AI and speech technology https://bit.ly/3cPMf44 Super interesting how it can take decades for research to finally have an impact, only made possible by certain technologies aligning. For example, neural networks have been around for a while, but recent advances in compute and the digitization of data has made them more relevant than ever (resulting in a rebranding as “deep learning”). The same can be said of AI in general. In a similar way, I think affective computing and other AI specific #UX will likely have a resurgence. Super fun to be pushing the envelope on these technologies
So excited to be working on innovation in #AI for clinical surveillance with real impact on clinical outcomes and cost. AI is the enabler, but the evidence of impact is the real takeaway. http://ow.ly/jO8750EcdUV
I’ll be giving a talk on applications of AI in Cybersecurity for Dark Reading. It includes real examples of specific algorithms and how they’re used to address different threats. No specific products are mentioned or endorsed. https://webinar.darkreading.com/5703
Our #AI model for predicting hospital acquired infections went general release in product! Always super exciting to see new tech adopted and used in practice. And there’s a little video of me too :-) Of course the thumbnail always seems to catch me at inopportune moments. Oh well. #healthcareai #healthcare #artificialintelligence #machinelearning https://bit.ly/34z1ryo
Frost and Sullivan recognized Wolters Kluwer in its recent analysis of AI in the healthcare industry. The work of my team earned us a spot in the top 20 along with larger companies like AWS and Microsoft. I’m encouraged by this recognition and super excited for what will come from our much more ambitious projects currently underway! You can view the report here: https://bit.ly/2X55CNU
Not all #AI is created equal. The hype around AI has been both good and bad for data scientists. It’s great that any developer can now download a python library and create machine learning models. And I love that so many folks are passionate and interested in getting started in this field. Indeed, many problems can be solved with pretty straightforward approaches (or even “autoML”). But when it comes to tough, real-world use cases, I do believe an understanding of the underlying algorithms makes the difference between an AI solution that works, and one that does not. In a healthcare setting, it is critical that solutions work and provide clinicians the information necessary to make decisions. Black boxes aren’t going to cut it. At Wolters Kluwer, we’ve customized algorithms for class-imbalanced, time-series analysis to predict the onset of hospital-acquired infections. The most common algorithms we’ve seen in research for this use case include random forests and logistic regression. However, these algorithms do not consider the timing or order of features. The timing and order of events during a patient’s hospital stay are critical for practical applications of predictive analytics. Real-world solutions either need to employ algorithms that intrinsically deal with time series data, and/or data scientists must take great care during feature engineering to preserve information about the order and timing of events. I chat about all of these issues and how we predict hospital acquired infections in the article linked below.
https://www.wolterskluwer.com/en/expert-insights/predicting-hospital-infections-how-ai-makes-it-possible
This was a really fun conversation about how we use AI to predict the onset of C.Diff. Pilot studies have been super positive, with clinicians taking action based on our decision support solution. It’s hugely rewarding being able to do cutting edge research, apply it in the real world, and make a meaningful impact in healthcare.
Super excited to speak at #AMIA2019 on how to use AI to extract info from clinical text. Looks like there are some great talks I look forward to attending. #artificialintelligence #ai #nlp #machinelearning #deeplearning https://bit.ly/2XhSHXO