UPMC pilots machine learning, telehealth to inform patient transfers

UPMC pilots machine learning, telehealth to inform patient transfers

Thousands of patients each year are transferred between UPMC’s hospitals for high-acuity, complex medical care.

To ensure patients are fully informed before those transfers, the Pittsburgh health system is now piloting a new care process aided by a machine-learning tool.

While it’s sometimes necessary to transfer patients for more specialized care, that transfer can come with unintended consequences—like moving the patient far away from their family and other support systems, a particularly difficult decision for patients close to death and who may not want to spend their final days in the hospital. It’s important for clinicians to discuss such decisions with patients to make sure they understand the severity of their illness and align next steps with what the patient wants.

So to ensure those conversations are taking place, researchers at UPMC and the University of Pittsburgh School of Medicine developed a machine-learning algorithm that predicts mortality for patients who may be transferred to another hospital for a higher level of care. Patients deemed at highest risk are flagged for more in-depth discussions about their care goals.

Researchers published a study validating the algorithm, dubbed Safe Non-elective Emergent Transfers, or SafeNET, in the journal PLOS One earlier this month.

The SafeNET algorithm evaluates 14 variables, including age and vital signs, to assess a patient’s risk of death.
If a patient is deemed at high risk, it kicks off two processes: a three-way conversation between an emergency department physician, intensive-care unit physician at the possible transfer facility and a palliative-care clinician, as well as telehealth palliative-care services between the patient and family members to discuss goals, expectations and options for next steps.

Dr. Daniel Hall, medical director for high-risk populations and outcomes at the UPMC Wolff Center and an author on the study, stressed that the algorithm doesn’t make patient-care decisions. It’s meant to trigger a “pause,” during which physicians and patients talk in detail before making decisions on whether to make a transfer.

The SafeNET algorithm is currently being piloted in three EDs at UPMC. Since November, the algorithm has flagged 11 patients who had the highest probability of dying. After conversations with the palliative-care team, four of the patients ultimately decided to continue with ICU-level care and seven decided not to be transferred.

The seven patients “decided, all things considered—their goals of care, their personal values, what’s important to them—to stay locally,” said Dr. Karl Bezak, medical director for palliative care at UPMC Presbyterian and Montefiore hospitals. Instead of higher-acuity care farther from home, some of those patients chose options like at-home hospice.
dahalli said. 


The mortality risk score isn’t discussed with the patient; it’s just used to identify which patients should have the conversations.

Algorithms like SafeNET could prove a promising way to remind physicians to loop in palliative-care services before making care decisions, said Lori Bishop, vice president of palliative and advanced care at the National Hospice and Palliative Care Organization. Often, hospitals don’t have a standard approach for identifying patients who could benefit from palliative care, she said.

Including palliative care clinicians in decision-making helps to make sure care is patient-centered. “Sometimes, medicine can be a ‘run-away train’ because we make the assumption you want everything done possible until you die,” Bishop added. “What we’ve found is that people don’t always want that option, and sometimes regret that their time was spent in hospitals.”

Health systems like UPMC have built mortality risk-assessment tools for various uses. Researchers at Geisinger Health also in February published a study that found a machine-learning algorithm they developed could predict mortality within a year based on echocardiogram videos of the heart, which could help to inform physicians’ treatment decisions.

When integrating decision-support tools that use artificial intelligence into clinical care, it’s important to make sure the tools are developed and tested on high-quality data from diverse populations, as well as evaluated for possible biases, said Satish Gattadahalli, director of digital health and informatics in advisory firm Grant Thornton’s public sector business. He also highlighted the need to subject algorithms to peer review and design systems so clinicians understand how the tools make recommendations, and the algorithm isn’t a “black box.”

“Make sure there are sufficient guardrails,” Gatta


Published at Sat, 20 Feb 2021 06:00:00 +0000

Use of artificial intelligence in agriculture

From cultivation to improving harvesting quality, AI is known as one of the main elements for a surplus yield but that too for the ones who are capable enough to make use of it. 

Agriculture is seeing rapid adoption of Artificial Intelligence and Machine Learning, both in terms of agricultural products and in field farming techniques. Apart from that, most of the countries are looking forward to involving such techniques. 

In 2016, the estimated value added by the agricultural industry was estimated at just under 1% of the US GDP. 

The US Environmental Protection Agency, estimates that agriculture contributes roughly $330 billion in annual revenue to the economy, thus such techniques would definitely speed things up.

Moving onto a few factual details, the AI in agriculture appears to fall into three major categories, with the first being Agricultural Robots. 

Companies are developing and programming autonomous robots to handle essential agricultural tasks such as harvesting crops at higher volume and faster pace than humans. Next up is the Crop and Soil Monitoring, companies are leveraging computer vision and deep learning algorithms to process data captured by drones and software based technology to monitor crop and soil health. 

Under the Predictive Analytics category machine models are being developed to track and predict various environmental impacts on crop yield such as weather changes. The ability to control weeds is a top priority for farmers and an ongoing challenge as herbicide resistance becomes more commonplace. 

Today, an estimated 250 species of weed have become resistant to herbicides. In a research conducted by the Weed Science Society of America on the impact of uncontrolled weeds on corn and soybean crops, annual losses to farmers are estimated at Rs43 billion.

Companies are using automation and robotics to help farmers find more efficient ways to protect their crops from weeds. A technology known as  “Blue River Technology” has developed a robot called See and Spray which reportedly leverages computer vision to monitor and precisely spray weeds on cotton plants. 

Precision spraying can help prevent herbicide resistance.

Automation is also emerging in an effort to help address challenges in the labour force. Companies such as Harvest CROO Robotics have developed a robot to help strawberry farmers pick and pack their crops. Such robots can harvest 8 acres in one day and replace 30 human labourers. With that being said, the development of soil analysis machines might become essential in the upcoming years due to deforestation which makes soil infertile for deforestation and causes water logging and salinity. 

A system needs to be developed which uses machine learning to provide clients with a sense of their soil’s strengths and weaknesses. 

The emphasis of such services should be on preventing defective crops and optimizing the potential for healthy crop production. Another method which has been implemented and is highly demanded for monitoring is the use of drones.

The market for drones in agriculture is projected to reach $480 million by 2027. 

Once again there needs to be establishment of corporations and companies that aim to help users improve their crop yield and to reduce costs. 

Users should be able to program the drone’s route and once deployed the device will leverage computer vision to record images which will be used for analysis. 

A device such as a USB can then be used to transfer the footage from the drone to a computer and upload the captured data to a cloud drive. Afterwards algorithms can be used to integrate and analyze the captured images and data to provide a detailed report.

Irrigation depends a lot upon the weather and this is something that also affects sustainability. 

Machine learning algorithms in connection with satellites can be used to predict weather, analyze crop sustainability and evaluate farms for the presence of diseases and pests. A lot of farmers do complain about the fact that fertilizers do not need to be used all around fields but this has become a necessity for them. 

Softwares can be developed that can inform users where exactly are fertilizers needed, this can reduce the amount of fertilizer used by nearly 40%. Such softwares should be marketed for use across mobile phones.

AI driven technologies are emerging to help improve efficiency and to address challenges facing the industry including, crop yield, soil health and herbicide resistance. Agricultural robots are poised to become a highly valued application of AI in this sector. 

The above mentioned problems can be catered by feasible mechanisms that can reduce complaints of farmers and provide them with a better environment. 

I t will be important that farmers are equipped with training that is up-to-date to ensure the technologies are used and continue to improve. 

This will help to prove the value of these tools over the long. It is anticipated that the agricultural industry will continue to see steady adoption of AI and will continue to monitor this trend.

The writer is a student of O Level at Aitchison College Lahore.

Published at Fri, 19 Feb 2021 23:04:50 +0000