AI Algorithm Improves Intravenous Nutrition for Premature Babies, Stanford Study Finds

AI can help doctors provide IV nutrition to preemies, study finds

Artificial intelligence can improve intravenous nutrition for premature babies, a Stanford Medicine study has shown. The study, which published March 25 in Nature Medicine, is among the first to demonstrate how an AI algorithm can enable doctors to make better clinical decisions for sick newborns. The algorithm uses information in preemies' electronic medical records to predict which nutrients they need and in what quantities. The AI tool was trained on data from almost 80,000 past prescriptions for intravenous nutrition, which was linked to information about how the tiny patients fared. Using AI to help prescribe IV nutrition could reduce medical errors, save time and money, and make it easier to care for preemies in low-resource settings, the researchers said. IV nutrition, also known as total parenteral nutrition, is the only way to feed preemies who are born before their digestive systems are mature enough to absorb nutrients. "Right now, we come up with a TPN prescription for each baby, individually, every day. We make it from scratch and provide it to them," said senior study author Nima Aghaeepour, PhD, associate professor of anesthesiology, perioperative and pain medicine and of pediatrics. "Total parenteral nutrition is the single largest source of medical error in neonatal intensive care units, both in the United States and globally." Not only is the process error-prone but it also makes it difficult for doctors to know if they've gotten the formula right. There's no blood test to measure whether a preemie received the right number of calories each day, for example, and unlike full-term babies, preemies don't necessarily cry when they are hungry and show contentment when they are full. "Nutrition is one of the areas of neonatal intensive care where we are weakest," said study coauthor David Stevenson, MD, a neonatologist and the Harold K. Faber Professor in Pediatrics. "We can't approximate what the placenta is doing," he said. About 10% of babies are born prematurely, meaning at least three weeks before their due dates. Babies born more than about eight weeks early are not ready to absorb nutrients through their intestines and require IV feeding. In addition, some preemies experience gastrointestinal complications of early birth and need IV nutrition while the gut heals. At present, IV nutrition is prescribed daily for these patients on an individual basis. Patients need macronutrients, the molecular building blocks of protein, fat and carbohydrates; micronutrients such as vitamins, minerals and electrolytes; and medications such as heparin, which is added to the IV preparation to reduce risk of blood clots. The current prescriptions are based on factors such as the baby's weight, stage of development and the results of their lab work. Providing these prescriptions requires input from six experts working together over a multihour process: A neonatologist or pharmacist writes each prescription, which is checked by a dietitian for nutrient composition and by a second pharmacist for safety. The prescription goes to a compounding pharmacy, where it is prepared, then to the neonatal intensive care unit, where one nurse gives the IV and a second nurse double-checks that each patient receives the correct preparation. "It's a high-risk drug because it is a mixture of many different things," said study co-author Shabnam Gaskari, PharmD, executive director and chief pharmacy officer at Stanford Medicine Children's Health. "If we had manufactured, ready-to-use TPNs, that would be very beneficial. I think it would be safer for patients." The researchers wondered if they could use AI to help provide hospitals with manufactured, ready-to-use nutrient formulas. Their AI algorithm was trained on 10 years of electronic medical record data from the neonatal intensive care unit at Lucile Packard Children's Hospital Stanford, including 79,790 prescriptions for IV nutrition from 5,913 premature patients. The algorithm also had access to information about patients' medical outcomes, enabling it to find subtle patterns that connected nutrient levels to babies' health. Although the doctors had not always gotten each prior prescription exactly right, the volume of data helped overcome that problem, enabling the algorithm to learn in a general way about what works for babies in different medical situations. "This is a strength of AI: Sometimes imperfect data is good enough as long as you have a lot of it," Aghaeepour said. After training on the decade of patient data, the algorithm grouped similar nutrient prescriptions to determine how many standard formulas would meet all patients' nutrition needs, and what would go into each. "We wondered: What if we make three standard formulas, or 10, or 100?" Aghaeepour said. "It turns out that with 15 distinct formulas for IV nutrition, what you are recommending is pretty similar to what the physicians, pharmacists and dietitians would have done anyway. But then these 15 AI-based formulas can be used to significantly improve speed and safety." Further, the researchers showed that the AI algorithm could use data from patients' electronic medical records to predict which of the 15 formulas each baby might need, and it could adjust the recommendations each day, as patients grew and their medical condition changed. So, the algorithm might recommend that a specific baby needed formula No. 8 for five days, then formula No. 3 for a week, then formula No. 14 for a few days, and so on. To test how this approach would stack up against real prescriptions, the research team created a test for 10 neonatologists: The doctors were shown clinical information for past patients, alongside the IV nutrition prescriptions they had actually received and the prescriptions the algorithm would recommend. Doctors were not told which prescription was which; they were asked which they thought was better. Doctors consistently preferred the AI-generated prescriptions to the real prescriptions. The researchers also used AI to scan the electronic medical records from past patients, looking for instances where the patient's actual nutrition prescription was quite different from what the AI would have recommended. For those patients, risk of mortality, sepsis and bowel disease were significantly higher than for patients whose prescriptions matched what the AI would have recommended, they found. The team also validated the AI model using real data from the University of California, San Francisco (including 63,273 nutrition prescriptions from 3,417 patients) and found that the model did a good job of predicting nutrient needs for this population, too. The next step will be to run a randomized clinical trial in which some patients receive nutrient prescriptions using the manual method, others receive AI-recommended prescriptions and the researchers see how each group fares. Assuming the system is implemented, the team plans to have doctors and pharmacists continue to check the AI recommendations and adjust the prescriptions if necessary. "The AI recommendation is based on whatever information has been added to a patient's electronic medical record, so if something is missing from the record, the recommendation won't be accurate," Gaskari said. "We need a clinician to look at it and review." But once the prescription has medical approval, one of the 15 standard nutrient formulas, kept on a hospital shelf, could be given to the patient immediately, she added. Using standard formulas would also make IV nutrition more accessible and less expensive, as it would no longer require the large expert team now involved, nor access to a compounding pharmacy. This could have benefits for hospitals in lower-income countries or other low-resource settings. "This reflects our hope for how AI will enhance medicine: What it's going to do is make doctors better and make top-notch care more accessible," Stevenson said. "Hopefully, it will also give our physicians more time to do the things computers can't do, such as spending time with babies and their families, listening to them, and providing comfort and reassurance."

AI can help doctors give intravenous nutrition to preemies

Artificial intelligence can improve intravenous nutrition for premature babies, a Stanford Medicine study has shown. The study, which will publish March 25 in Nature Medicine, is among the first to demonstrate how an AI algorithm can enable doctors to make better clinical decisions for sick newborns. The algorithm uses information in preemies' electronic medical records to predict which nutrients they need and in what quantities. The AI tool was trained on data from almost 80,000 past prescriptions for intravenous nutrition, which was linked to information about how the tiny patients fared. Using AI to help prescribe IV nutrition could reduce medical errors, save time and money, and make it easier to care for preemies in low-resource settings, the researchers said. IV nutrition, also known as total parenteral nutrition, is the only way to feed preemies who are born before their digestive systems are mature enough to absorb nutrients. "Right now, we come up with a TPN prescription for each baby, individually, every day. We make it from scratch and provide it to them," said senior study author Nima Aghaeepour, PhD, associate professor of anesthesiology, perioperative and pain medicine and of pediatrics. "Total parenteral nutrition is the single largest source of medical error in neonatal intensive care units, both in the United States and globally." Not only is the process error-prone but it also makes it difficult for doctors to know if they've gotten the formula right. There's no blood test to measure whether a preemie received the right number of calories each day, for example, and unlike full-term babies, preemies don't necessarily cry when they are hungry and show contentment when they are full. "Nutrition is one of the areas of neonatal intensive care where we are weakest," said study coauthor David Stevenson, MD, a neonatologist and the Harold K. Faber Professor in Pediatrics. "We can't approximate what the placenta is doing," he said. A slow process About 10% of babies are born prematurely, meaning at least three weeks before their due dates. Babies born more than about eight weeks early are not ready to absorb nutrients through their intestines and require IV feeding. In addition, some preemies experience gastrointestinal complications of early birth and need IV nutrition while the gut heals. At present, IV nutrition is prescribed daily for these patients on an individual basis. Patients need macronutrients, the molecular building blocks of protein, fat and carbohydrates; micronutrients such as vitamins, minerals and electrolytes; and medications such as heparin, which is added to the IV preparation to reduce risk of blood clots. The current prescriptions are based on factors such as the baby's weight, stage of development and the results of their lab work. Providing these prescriptions requires input from six experts working together over a multihour process: A neonatologist or pharmacist writes each prescription, which is checked by a dietitian for nutrient composition and by a second pharmacist for safety. The prescription goes to a compounding pharmacy, where it is prepared, then to the neonatal intensive care unit, where one nurse gives the IV and a second nurse double-checks that each patient receives the correct preparation. "It's a high-risk drug because it is a mixture of many different things," said study co-author Shabnam Gaskari, PharmD, executive director and chief pharmacy officer at Stanford Medicine Children's Health. "If we had manufactured, ready-to-use TPNs, that would be very beneficial. I think it would be safer for patients." Toward standard formulas The researchers wondered if they could use AI to help provide hospitals with manufactured, ready-to-use nutrient formulas. Their AI algorithm was trained on 10 years of electronic medical record data from the neonatal intensive care unit at Lucile Packard Children's Hospital Stanford, including 79,790 prescriptions for IV nutrition from 5,913 premature patients. The algorithm also had access to information about patients' medical outcomes, enabling it to find subtle patterns that connected nutrient levels to babies' health. Although the doctors had not always gotten each prior prescription exactly right, the volume of data helped overcome that problem, enabling the algorithm to learn in a general way about what works for babies in different medical situations. "This is a strength of AI: Sometimes imperfect data is good enough as long as you have a lot of it," Aghaeepour said. After training on the decade of patient data, the algorithm grouped similar nutrient prescriptions to determine how many standard formulas would meet all patients' nutrition needs, and what would go into each. "We wondered: What if we make three standard formulas, or 10, or 100?" Aghaeepour said. "It turns out that with 15 distinct formulas for IV nutrition, what you are recommending is pretty similar to what the physicians, pharmacists and dietitians would have done anyway. But then these 15 AI-based formulas can be used to significantly improve speed and safety." Further, the researchers showed that the AI algorithm could use data from patients' electronic medical records to predict which of the 15 formulas each baby might need, and it could adjust the recommendations each day, as patients grew and their medical condition changed. So, the algorithm might recommend that a specific baby needed formula No. 8 for five days, then formula No. 3 for a week, then formula No. 14 for a few days, and so on. To test how this approach would stack up against real prescriptions, the research team created a test for 10 neonatologists: The doctors were shown clinical information for past patients, alongside the IV nutrition prescriptions they had actually received and the prescriptions the algorithm would recommend. Doctors were not told which prescription was which; they were asked which they thought was better. Doctors consistently preferred the AI-generated prescriptions to the real prescriptions. The researchers also used AI to scan the electronic medical records from past patients, looking for instances where the patient's actual nutrition prescription was quite different from what the AI would have recommended. For those patients, risk of mortality, sepsis and bowel disease were significantly higher than for patients whose prescriptions matched what the AI would have recommended, they found. The team also validated the AI model using real data from the University of California, San Francisco (including 63,273 nutrition prescriptions from 3,417 patients) and found that the model did a good job of predicting nutrient needs for this population, too. Steps to implementation The next step will be to run a randomized clinical trial in which some patients receive nutrient prescriptions using the manual method, others receive AI-recommended prescriptions and the researchers see how each group fares. Assuming the system is implemented, the team plans to have doctors and pharmacists continue to check the AI recommendations and adjust the prescriptions if necessary. "The AI recommendation is based on whatever information has been added to a patient's electronic medical record, so if something is missing from the record, the recommendation won't be accurate," Gaskari said. "We need a clinician to look at it and review." But once the prescription has medical approval, one of the 15 standard nutrient formulas, kept on a hospital shelf, could be given to the patient immediately, she added. Using standard formulas would also make IV nutrition more accessible and less expensive, as it would no longer require the large expert team now involved, nor access to a compounding pharmacy. This could have benefits for hospitals in lower-income countries or other low-resource settings. "This reflects our hope for how AI will enhance medicine: What it's going to do is make doctors better and make top-notch care more accessible," Stevenson said. "Hopefully, it will also give our physicians more time to do the things computers can't do, such as spending time with babies and their families, listening to them, and providing comfort and reassurance." Scientists from the University of Southern California Keck School of Medicine and Children's Hospital of Los Angeles contributed to the research. This work was supported by the National Institutes of Health (grant R35GM138353), the National Center for Advancing Translational Sciences (grant UL1TR001872), the Eunice Kennedy Shriver National Institute of Child Health and Human Development (grant R42HD115517), the Burroughs Wellcome Fund, the March of Dimes, the Alfred E. Mann Foundation, the Stanford Maternal and Child Health Research Institute through Stanford's SPARK Translational Research Program, Stanford High Impact Technology Fund, and Stanford Biodesign. This project was also supported by the National Center for Advancing Translational Sciences, National Institutes of Health, through UCSF Clinical & Translational Science Institute.

Study shows artificial intelligence can improve intravenous nutrition for premature babies

Stanford MedicineMar 25 2025 Artificial intelligence can improve intravenous nutrition for premature babies, a Stanford Medicine study has shown. The study, which will publish March 25 in Nature Medicine, is among the first to demonstrate how an AI algorithm can enable doctors to make better clinical decisions for sick newborns. The algorithm uses information in preemies' electronic medical records to predict which nutrients they need and in what quantities. The AI tool was trained on data from almost 80,000 past prescriptions for intravenous nutrition, which was linked to information about how the tiny patients fared. Using AI to help prescribe IV nutrition could reduce medical errors, save time and money, and make it easier to care for preemies in low-resource settings, the researchers said. IV nutrition, also known as total parenteral nutrition, is the only way to feed preemies who are born before their digestive systems are mature enough to absorb nutrients. Right now, we come up with a TPN prescription for each baby, individually, every day. We make it from scratch and provide it to them. Total parenteral nutrition is the single largest source of medical error in neonatal intensive care units, both in the United States and globally." Nima Aghaeepour, PhD, senior study author, associate professor of anesthesiology, perioperative and pain medicine and of pediatrics Not only is the process error-prone but it also makes it difficult for doctors to know if they've gotten the formula right. There's no blood test to measure whether a preemie received the right number of calories each day, for example, and unlike full-term babies, preemies don't necessarily cry when they are hungry and show contentment when they are full. "Nutrition is one of the areas of neonatal intensive care where we are weakest," said study coauthor David Stevenson, MD, a neonatologist and the Harold K. Faber Professor in Pediatrics. "We can't approximate what the placenta is doing," he said. A slow process About 10% of babies are born prematurely, meaning at least three weeks before their due dates. Babies born more than about eight weeks early are not ready to absorb nutrients through their intestines and require IV feeding. In addition, some preemies experience gastrointestinal complications of early birth and need IV nutrition while the gut heals. At present, IV nutrition is prescribed daily for these patients on an individual basis. Patients need macronutrients, the molecular building blocks of protein, fat and carbohydrates; micronutrients such as vitamins, minerals and electrolytes; and medications such as heparin, which is added to the IV preparation to reduce risk of blood clots. The current prescriptions are based on factors such as the baby's weight, stage of development and the results of their lab work. Providing these prescriptions requires input from six experts working together over a multihour process: A neonatologist or pharmacist writes each prescription, which is checked by a dietitian for nutrient composition and by a second pharmacist for safety. The prescription goes to a compounding pharmacy, where it is prepared, then to the neonatal intensive care unit, where one nurse gives the IV and a second nurse double-checks that each patient receives the correct preparation. "It's a high-risk drug because it is a mixture of many different things," said study co-author Shabnam Gaskari, PharmD, executive director and chief pharmacy officer at Stanford Medicine Children's Health. "If we had manufactured, ready-to-use TPNs, that would be very beneficial. I think it would be safer for patients." Toward standard formulas The researchers wondered if they could use AI to help provide hospitals with manufactured, ready-to-use nutrient formulas. Their AI algorithm was trained on 10 years of electronic medical record data from the neonatal intensive care unit at Lucile Packard Children's Hospital Stanford, including 79,790 prescriptions for IV nutrition from 5,913 premature patients. The algorithm also had access to information about patients' medical outcomes, enabling it to find subtle patterns that connected nutrient levels to babies' health. Although the doctors had not always gotten each prior prescription exactly right, the volume of data helped overcome that problem, enabling the algorithm to learn in a general way about what works for babies in different medical situations. "This is a strength of AI: Sometimes imperfect data is good enough as long as you have a lot of it," Aghaeepour said. After training on the decade of patient data, the algorithm grouped similar nutrient prescriptions to determine how many standard formulas would meet all patients' nutrition needs, and what would go into each. "We wondered: What if we make three standard formulas, or 10, or 100?" Aghaeepour said. "It turns out that with 15 distinct formulas for IV nutrition, what you are recommending is pretty similar to what the physicians, pharmacists and dietitians would have done anyway. But then these 15 AI-based formulas can be used to significantly improve speed and safety." Further, the researchers showed that the AI algorithm could use data from patients' electronic medical records to predict which of the 15 formulas each baby might need, and it could adjust the recommendations each day, as patients grew and their medical condition changed. So, the algorithm might recommend that a specific baby needed formula No. 8 for five days, then formula No. 3 for a week, then formula No. 14 for a few days, and so on. To test how this approach would stack up against real prescriptions, the research team created a test for 10 neonatologists: The doctors were shown clinical information for past patients, alongside the IV nutrition prescriptions they had actually received and the prescriptions the algorithm would recommend. Doctors were not told which prescription was which; they were asked which they thought was better. Doctors consistently preferred the AI-generated prescriptions to the real prescriptions. The researchers also used AI to scan the electronic medical records from past patients, looking for instances where the patient's actual nutrition prescription was quite different from what the AI would have recommended. For those patients, risk of mortality, sepsis and bowel disease were significantly higher than for patients whose prescriptions matched what the AI would have recommended, they found. The team also validated the AI model using real data from the University of California, San Francisco (including 63,273 nutrition prescriptions from 3,417 patients) and found that the model did a good job of predicting nutrient needs for this population, too. Steps to implementation The next step will be to run a randomized clinical trial in which some patients receive nutrient prescriptions using the manual method, others receive AI-recommended prescriptions and the researchers see how each group fares. Assuming the system is implemented, the team plans to have doctors and pharmacists continue to check the AI recommendations and adjust the prescriptions if necessary. "The AI recommendation is based on whatever information has been added to a patient's electronic medical record, so if something is missing from the record, the recommendation won't be accurate," Gaskari said. "We need a clinician to look at it and review." But once the prescription has medical approval, one of the 15 standard nutrient formulas, kept on a hospital shelf, could be given to the patient immediately, she added. Using standard formulas would also make IV nutrition more accessible and less expensive, as it would no longer require the large expert team now involved, nor access to a compounding pharmacy. This could have benefits for hospitals in lower-income countries or other low-resource settings. "This reflects our hope for how AI will enhance medicine: What it's going to do is make doctors better and make top-notch care more accessible," Stevenson said. "Hopefully, it will also give our physicians more time to do the things computers can't do, such as spending time with babies and their families, listening to them, and providing comfort and reassurance." Scientists from the University of Southern California Keck School of Medicine and Children's Hospital of Los Angeles contributed to the research. This work was supported by the National Institutes of Health (grant R35GM138353), the National Center for Advancing Translational Sciences (grant UL1TR001872), the Eunice Kennedy Shriver National Institute of Child Health and Human Development (grant R42HD115517), the Burroughs Wellcome Fund, the March of Dimes, the Alfred E. Mann Foundation, the Stanford Maternal and Child Health Research Institute through Stanford's SPARK Translational Research Program, Stanford High Impact Technology Fund, and Stanford Biodesign. This project was also supported by the National Center for Advancing Translational Sciences, National Institutes of Health, through UCSF Clinical & Translational Science Institute. Stanford Medicine Journal reference: Phongpreecha, T., et al. (2025). AI-guided precision parenteral nutrition for neonatal intensive care units. Nature Medicine. doi.org/10.1038/s41591-025-03601-1.

AI can help doctors give intravenous nutrition to preemies

Artificial intelligence can improve intravenous nutrition for premature babies, a Stanford Medicine study has shown. The study, which was published in Nature Medicine, is among the first to demonstrate how an AI algorithm can enable doctors to make better clinical decisions for sick newborns. The algorithm uses information in preemies' electronic medical records to predict which nutrients they need and in what quantities. The AI tool was trained on data from almost 80,000 past prescriptions for intravenous nutrition, which was linked to information about how the tiny patients fared. Using AI to help prescribe IV nutrition could reduce medical errors, save time and money, and make it easier to care for preemies in low-resource settings, the researchers said. IV nutrition, also known as total parenteral nutrition, is the only way to feed preemies who are born before their digestive systems are mature enough to absorb nutrients. "Right now, we come up with a TPN prescription for each baby, individually, every day. We make it from scratch and provide it to them," said senior study author Nima Aghaeepour, Ph.D., associate professor of anesthesiology, perioperative and pain medicine and of pediatrics. "Total parenteral nutrition is the single largest source of medical error in neonatal intensive care units, both in the United States and globally." Not only is the process error-prone but it also makes it difficult for doctors to know if they've gotten the formula right. There's no blood test to measure whether a preemie received the right number of calories each day, for example, and unlike full-term babies, preemies don't necessarily cry when they are hungry and show contentment when they are full. "Nutrition is one of the areas of neonatal intensive care where we are weakest," said study co-author David Stevenson, MD, a neonatologist and the Harold K. Faber Professor of Pediatrics. "We can't approximate what the placenta is doing," he said. A slow process About 10% of babies are born prematurely, meaning at least three weeks before their due dates. Babies born more than about eight weeks early are not ready to absorb nutrients through their intestines and require IV feeding. In addition, some preemies experience gastrointestinal complications of early birth and need IV nutrition while the gut heals. At present, IV nutrition is prescribed daily for these patients on an individual basis. Patients need macronutrients, the molecular building blocks of protein, fat and carbohydrates; micronutrients such as vitamins, minerals and electrolytes; and medications such as heparin, which is added to the IV preparation to reduce the risk of blood clots. The current prescriptions are based on factors such as the baby's weight, stage of development and the results of their lab work. Providing these prescriptions requires input from six experts working together over a multi-hour process: a neonatologist or pharmacist writes each prescription, which is checked by a dietitian for nutrient composition and by a second pharmacist for safety. The prescription goes to a compounding pharmacy, where it is prepared, then to the neonatal intensive care unit, where one nurse gives the IV and a second nurse double-checks that each patient receives the correct preparation. "It's a high-risk drug because it is a mixture of many different things," said study co-author Shabnam Gaskari, PharmD, executive director and chief pharmacy officer at Stanford Medicine Children's Health. "If we had manufactured, ready-to-use TPNs, that would be very beneficial. I think it would be safer for patients." Toward standard formulas The researchers wondered if they could use AI to help provide hospitals with manufactured, ready-to-use nutrient formulas. Their AI algorithm was trained on 10 years of electronic medical record data from the neonatal intensive care unit at Lucile Packard Children's Hospital Stanford, including 79,790 prescriptions for IV nutrition from 5,913 premature patients. The algorithm also had access to information about patients' medical outcomes, enabling it to find subtle patterns that connected nutrient levels to babies' health. Although the doctors had not always gotten each prior prescription exactly right, the volume of data helped overcome that problem, enabling the algorithm to learn in a general way about what works for babies in different medical situations. "This is a strength of AI: Sometimes imperfect data is good enough as long as you have a lot of it," Aghaeepour said. After training on a decade of patient data, the algorithm grouped similar nutrient prescriptions to determine how many standard formulas would meet all patients' nutrition needs, and what would go into each. "We wondered: What if we make three standard formulas, or 10, or 100?" Aghaeepour said. "It turns out that with 15 distinct formulas for IV nutrition, what you are recommending is pretty similar to what the physicians, pharmacists and dietitians would have done anyway. But then these 15 AI-based formulas can be used to significantly improve speed and safety." Further, the researchers showed that the AI algorithm could use data from patients' electronic medical records to predict which of the 15 formulas each baby might need, and it could adjust the recommendations each day, as patients grew and their medical condition changed. So, the algorithm might recommend that a specific baby needed formula No. 8 for five days, then formula No. 3 for a week, then formula No. 14 for a few days, and so on. To test how this approach would stack up against real prescriptions, the research team created a test for 10 neonatologists: The doctors were shown clinical information for past patients, alongside the IV nutrition prescriptions they had actually received and the prescriptions the algorithm would recommend. Doctors were not told which prescription was which; they were asked which they thought was better. Doctors consistently preferred the AI-generated prescriptions to the real prescriptions. The researchers also used AI to scan the electronic medical records from past patients, looking for instances where the patient's actual nutrition prescription was quite different from what the AI would have recommended. For those patients, the risk of mortality, sepsis and bowel disease was significantly higher than for patients whose prescriptions matched what the AI would have recommended, they found. The team also validated the AI model using real data from the University of California, San Francisco (including 63,273 nutrition prescriptions from 3,417 patients) and found that the model did a good job of predicting nutrient needs for this population, too. Steps to implementation The next step will be to run a randomized clinical trial in which some patients receive nutrient prescriptions using the manual method, others receive AI-recommended prescriptions and the researchers see how each group fares. Assuming the system is implemented, the team plans to have doctors and pharmacists continue to check the AI recommendations and adjust the prescriptions if necessary. "The AI recommendation is based on whatever information has been added to a patient's electronic medical record, so if something is missing from the record, the recommendation won't be accurate," Gaskari said. "We need a clinician to look at it and review." But once the prescription has medical approval, one of the 15 standard nutrient formulas, kept on a hospital shelf, could be given to the patient immediately, she added. Using standard formulas would also make IV nutrition more accessible and less expensive, as it would no longer require the large expert team now involved, nor access to a compounding pharmacy. This could have benefits for hospitals in lower-income countries or other low-resource settings. "This reflects our hope for how AI will enhance medicine: what it's going to do is make doctors better and make top-notch care more accessible," Stevenson said. "Hopefully, it will also give our physicians more time to do the things computers can't do, such as spending time with babies and their families, listening to them, and providing comfort and reassurance." Scientists from the University of Southern California Keck School of Medicine and Children's Hospital of Los Angeles contributed to the research.

AI Improves IV Nutrition For Preemies

THURSDAY, March 27, 2025 (HealthDay News) -- Artificial intelligence (AI) can help improve how premature babies are fed, giving them a better chance at normal growth and development, a new study says. Currently, preemies in a neonatal intensive care unit are fed by IV, receiving a drip-drop handmade blend of nutrients that doctors call total parenteral nutrition, or TPN. This is the only way to feed newborns whose digestive systems haven't matured enough to properly absorb nutrients, researchers said. "Right now, we come up with a TPN prescription for each baby, individually, every day," senior researcher Nima Aghaeepour, an associate professor of pediatrics at Stanford University, said in a news release. "We make it from scratch and provide it to them." Unfortunately, the process is error-prone, and it's tough for docs to know if they've gotten the formula right, researchers said. There's no blood test to measure whether a preemie has received enough daily calories, and preemies don't necessarily cry when they're hungry or become calm and content when they're full. "Total parenteral nutrition is the single largest source of medical error in neonatal intensive care units, both in the United States and globally," Aghaeepour said. To try to solve this problem, researchers trained an AI program on nearly 80,000 past prescriptions for preemie IV nutrition, linked to data on how the tiny patients fared. The AI uses information in a preemie's electronic medical chart to predict which nutrients they need and in what quantities, researchers said. Tests of the AI show that it could perform better than a team of human doctors in getting babies the nutrition and medication they need, researchers reported March 25 in the journal Nature Medicine. About 10% of babies are born prematurely, at least three weeks prior to their due date. Babies born more than eight weeks early generally are not ready to absorb nutrients through their intestines and require IV feeding, researchers said. Based on the AI's results, researchers honed down the countless variations in potential TPN prescriptions to 15 standard formulas. "It turns out that with 15 distinct formulas for IV nutrition, what you are recommending is pretty similar to what the physicians, pharmacists and dietitians would have done anyway," Aghaeepour said. "But then these 15 AI-based formulas can be used to significantly improve speed and safety." Researchers then tested whether the AI could use the preemie's medical data to predict which of the 15 formulas a baby might need, and whether it could adjust the recommendations daily as the newborns grow and their medical condition changes. In one test, researchers asked 10 neonatologists to review clinical information for past patients, alongside the IV nutrition prescriptions the preemies had actually received and the prescriptions that the AI would recommend. Researchers asked the doctors, who were not told which prescription was human- or AI-generated, to pick the one that best matched the preemie's condition. The neonatologists consistently preferred the AI-generated prescriptions to the real prescriptions, researchers reported. In another test, researchers scanned the medical records of past patients to find instances where the preemie's TPN prescription was different from what the AI recommended. The team then assessed how the AI prescription might have improved the newborn's outlook. Results show that patients had a significantly higher risk of death, sepsis and bowel disease if their actual nutrition was significantly different from what the AI would have prescribed. For example, babies had a more than three times higher risk of necrotizing enterocolitis, a serious GI problem affecting preemies, if their human-created TPN differed from what the AI would have recommended, the study says. The researchers' next step will be to run a clinical trial in which preemies fed the usual way will be compared to others receiving AI-recommended nutrition. The research team noted that the AI's recommendations will still need to be run past doctors and pharmacists, to make sure the program isn't overlooking anything. "The AI recommendation is based on whatever information has been added to a patient's electronic medical record, so if something is missing from the record, the recommendation won't be accurate," researcher Shabnam Gaskari, executive director and chief pharmacy officer at Stanford Medicine Children's Health, said. "We need a clinician to look at it and review." But if the system works, a preemie can promptly be provided one of the 15 standard nutrient formulas, which would be waiting on a hospital shelf, researchers said. Using standard formulas also would make IV nutrition more accessible and less expensive, researchers noted. Currently, crafting nutrition prescriptions requires the combined input of six experts, researchers said. These prescriptions include a blend of proteins, fats, carbohydrates, vitamins, minerals and electrolytes, as well as any medicines a preemie might need. "This reflects our hope for how AI will enhance medicine: What it's going to do is make doctors better and make top-notch care more accessible," researcher Dr. David Stevenson, a neonatologist and professor of pediatrics at Stanford, said in a news release. "Hopefully, it will also give our physicians more time to do the things computers can't do, such as spending time with babies and their families, listening to them, and providing comfort and reassurance," he added.