Hospitals are turning to AI to Shorten Hospital Stays
Hospitals are turning to an unlikely hero in hard times, and it's A.I.
How quickly the world changes, when given a challenge or a shock, we adapt. We also have smart machines to augment how we cope and the healthcare system circa 2022 is a greater example of this.
During the pandemic with staff shortages, labor shortages, churn from the profession and many other challenges, Hospitals have had to make do. How do you make do with less and make sure your staff doesn’t burnout?
Amid things like the weird surge in hepatitis among children, the healthcare systems we once knew, are no more. Amid surgery delays, and rising costs of healthcare, an unlikely hero is there to help, and it’s artificial intelligence.
If A.I. can make healthcare more efficient, it can reduce nurse burn-out, minimize hospital errors and ultimately save lives. So how does this work in a world of massive labor shortages and persistent recurrent waves of a pandemic?
While more industries are embracing artificial intelligence or tech meant to solve problems that humans traditionally have handled. In the field of health care, the field is quickly learning to look into it to ease the worker shortage and shorten hospital stays.
Better appointment setting
Shortening hospital stays
Noticing signs of nurse burnout and mental health signals
How much could A.I. help shorten average hospital duration of stays? A Wall Street Journal analysis estimates by 3 to 5 days.
The same “emotion reading” tech we are seeing in Zoom calls or for teachers, could soon come to help doctors in reading the patients on telemedicine calls. Anything to give physicians better insights on how to treat patients.
A.I. will also eventually optimize and personalize patient-centric care.
A startup called Viz.ai is developing technology that can read brain scans and suggest treatment options. A.I is also being used increasingly to determine the patients most at risk, so as to avoid “alarm fatigue” when things go bitterly wrong all of a sudden.
Do you know someone who might enjoy this Newsletter? Here is my referral discount link.
Early tests show artificial "assistants" can help doctors and nurses spot potentially deadly problems in time to take life-saving action.
From interpreting CT scans to diagnosing eye disease, artificial intelligence is taking on medical tasks once reserved for only highly trained medical specialists — and in many cases outperforming its human counterparts. Yet in the nitty gritty of a pandemic and a lot of disruption to our healthcare systems due to churn in the profession, A.I. is helping hospitals do more with less.
New technology could also mean additional fees for patients associated with it. However in the grand scheme of things, A.I. has massive ability to reduce the cost of healthcare and vastly improve accessibility to those who need it most.
When you look at the price of a piece of technology, it goes down over time. That hasn't been true in healthcare and it will be especially true as we embed automation, A.I. and better human-centric design in our clinics, ERs, hospitals and healthcare system at large.
The pressure on our system during waves of the pandemic has also given us new insights into how A.I. can be implemented at scale. From telemedicine to more data in the home. The spread of Covid-19 is stretched the operational capacity of our systems in health care and beyond. The reason is both simple: Our economy and health care systems are geared to handle linear, incremental demand, while the virus grew at a sometimes exponential rate.
What we learned when we were most vulnerable handling the overload will make our hospitals and healthcare system better prepared to handle crisis and emergencies in the future.
A.I. is Streamlining Care in Hospitals That will Reduce Hospital Stay
Fast forward to 2022 and it’s a brave new world of data-integration. Artificial-intelligence algorithms are processing vast troves of data in electronic medical records, searching for patterns to predict future outcomes and recommend treatments.
They are creating early-warning systems to help hospital staff spot subtle but serious changes in a patient’s condition that aren’t always visible or noticed in a busy unit, and predicting which patients about to be discharged from the hospital are at highest risk of being readmitted.
Better EMR predictions
More helpful recommendation engines for treatment
More automation tools to save physicians time
Better appointment setting
Better alarm systems to spot patients that may soon require more care
Improved discharge decision-making
If A.I. is a boon in diagnosing disease, it’s becoming better at helping how hospitals are managed and run. It’s assisting in clerical, managerial and patient facing decisions, at more and more patient and treatment touchpoints.
Towards Real-Time Treatment Decisions and Prioritization
A.I. is reaching a sophistication levels whereby prediction technology holds especially significant promise to transform care and improve patient safety in ER and ICU cases—as long as the systems can be designed to avoid some of the medical, technological and ethical concerns that have emerged in mixing the science of machine learning with the art of medicine.
We don’t exactly know how far out in years this is, but when it comes together it won’t just save lives but reduce hospital stay duration and optimize treatment plans, reduce hospital admission recurrence levels and save costs across the board.
I think we’ll see this level of care go up and the cost of the automation go down significantly starting around the year 2029. Healthcare policy will approve many A.I. tools in the common decade that could radically transform how we engage with the healthcare system. Think about it, clinicians still have to be in the driver’s seat, but artificial intelligence and predictive models can provide us with a way to put the most insights gleaned from voluminous amounts of data at their fingertips, so at the right moment of care it can improve patient outcomes.
I see nearly unlimited potential for A.I. to improve our smart clinics and create hospitals that are truly augmented with various technologies. Physicians augmented with machine learning and nurses augmented by smart robots will help a lot ease the strain of staff shortages, external shocks and mental health struggles when emergencies occur. The pandemic will have resulted in a new wave of A.I. tools to optimize and improve how our hospitals function. We’ll learn from all of this.
A.I. Unique Ability to Predict Likely Outcomes
Maybe most startling will be A.I’s ability to save and buy us more time and here I don’t only mean early diagnosis benefits at scale, I mean in-hospital interventions. For instance, little things like avoiding a ‘Code Blue’.
Once a patient’s deteriorating condition triggers an emergency like a Code Blue—which hastens a team to the bedside—it is often too late to prevent the patient from needing life-support therapy or intensive care. In the future A.I. will be able to alert nurses to the patients most at risk and only get better at this kind of prediction.
By using data analytics to predict a patient’s downward spiral up to 12 hours in advance, such emergencies could be prevented, and patients could either avoid the ICU or be in better shape when they got there. We’ll be living in a different era of smart healthcare, which we haven’t had the privilege of experiencing quiet yet.
In a study at 19 of its hospitals over nearly three years, published last November in the New England Journal of Medicine, Kaiser Permanente tested its predictive model called Advance Alert Monitor that can identify about half of patients who will deteriorate.
So how it works is that it scans patient data continuously, assigning scores that predict the risk of transfer to the ICU or death. The time horizon allows staffers to reach patients when they are still relatively stable and may just need enhanced screening or monitoring. It’s searching for the needles in the haystack, so it has to sift through all the patients to try to find those at highest risk. There are dozens of such tools in development, offering solutions for various case studies in real hospital and ER settings.
Back in 2018 Google was already using 46 billion data points to predict the medical outcomes of hospital patients. The research paper, published Jan. 24, 2018 with 34 co-authors and not peer-reviewed, claimed better accuracy than existing software at predicting outcomes like whether a patient will die in the hospital, be discharged and readmitted, and their final diagnosis.
What do you make of all of this?
If you want to support me so I can keep writing, please don’t hesitate to give me tips, a paid subscription or some donation. With a conversion rate of less than two percent, this Newsletter exists mostly by the grace of my goodwill (passion for A.I.) & my own experience of material poverty as I try to pivot into the Creator Economy.
Thanks for reading!