The Apgar Test – Clinical Analytics Then and Now

June 7, 2018 would have been Dr. Virginia Apgar’s 109th birthday, memorably commemorated by Google, and a good opportunity to review her life’s work and contribution to modern medicine. It’s also a good opportunity to consider how clinical analytics has evolved from 5 simple data points measured once or twice to 600 data points measured in milliseconds.

Virginia Apgar – Early Life & Career

Dr. Virginia Apgar was born in Westfield, New Jersey on June 7, 1909, and died in New York City on August 7, 1974. Virginia was the youngest of three children, her father was an insurance executive and an inventor and astronomer on the side. When Virginia graduated high school, she knew she wanted to be a medical doctor. We don’t know what inspired her to be a medical doctor, it may have been her oldest brother’s tuberculosis death, her other brother’s chronic childhood illness her father’s hobbies, or most likely a combination of all three influenced her decision.

Virginia Apgar graduated with a degree in Zoology from Mt. Holyoke College in 1929, she went on to the Columbia University College of Physicians and Surgeons and graduated in the top four of her class in 1933. In 1937 she completed her surgical residency. She was convinced by the university Chairman Dr. Allen Whipple that she would have a greater impact and success as an Anesthesiologist than a surgeon. She listened to Dr. Whipple, switched her specialty and was certified in Anesthesiology in 1937, she returned to Columbia University College of Physicians and Surgeons as the director of the new Anesthesia division.

Dr. Apgar was appointed as a full professor at Columbia in 1949, while there she also did research and clinical work at the affiliated Sloane Hospital for Women. In 1952 Apgar designed and introduced the Apgar Score, the first standardized method for evaluating a newborn baby after birth.

When on sabbatical in 1959, Dr. Apgar got her master’s degree in public health from the Johns Hopkins University. She then left Columbia and became the director of the division of congenital defects at the National Foundation for Infantile Paralysis (now the March of Dimes). Dr. Apgar received many honors and awards for her work there.

The Apgar Score

According to medical folklore, a student questioned Dr. Apgar in the hospital cafeteria. “You always tell us to look at the baby when it’s born, but what exactly are we looking for?” In response Dr. Apgar found a napkin and wrote down five things, including heart rate, breathing, and muscle tone. The concept of the Apgar test and score was formulated, Dr. Apgar presented the score at an anesthesiology meeting in 1952 and it was published in 1953. The Apgar test consists of measuring five key criteria, heart rate, respiratory effort, muscle tone, reflex response, and color. The five criteria are scored and summed to arrive at the baby’s score.

The Apgar score has been described as “ridiculously simple,” but its impact is huge, according to Dr. Richard Smiley on the NewYork-Presbyterian Health Matters website. “It was essentially the birth of clinical neonatology,” Smiley said. “A large number of neonates could have survived if they had simply been given oxygen or warmed up.” said Smiley. The Health Matters website also explains the impact of the Apgar test on many infant’s lives, “Before the scoring system was adopted, newborns who had trouble breathing or were small and blue were often labeled as stillborn. It was assumed they would be too sick to live and, unfathomably, were simply left to die. There was no protocol for trying to resuscitate newborns or intervene medically.”

Despite initial resistance, the score was eventually accepted and is now used throughout the world. The score was originally intended to be taken once one minute after birth, to help the doctors decide on the resuscitation or other treatments. Doctors then began to take measurements after treatments to see how the baby responded to the treatment. Eventually, the one- and five-minute Apgar Score became standard.

Apgar score concept proved successful

Dr. Apgar, Dr. Duncan Holaday, and Dr. Stanley James wrote: “Evaluation of the Newborn Infant—Second Report” in 1958. This report proved that the Apgar score predicted the health of newborn infants.

In the study, Dr. Apgar and her colleagues related the Apgar score more closely to the effects of labor, delivery, and maternal anesthetics on the baby’s condition, by using new methods of measuring blood gases and blood levels of anesthesia.

They demonstrated that babies with low levels of blood oxygen and highly acidic blood had low Apgar Scores and that giving cyclopropane anesthesia to the mother was the likely cause of an infant’s low Apgar Score. The Collaborative Project, a study involving twelve-institutions and 17,221 babies, proved the Apgar Score, especially the five-minute score, predicts neonatal survival and neurological development in infants.

Apgar Score in Use

The Apgar test in detail is a standardized scoring protocol used to assess an infant’s health after birth, with the result referred to as the infant’s “Apgar score”. “Five points—heart rate, respiratory effort, muscle tone, reflex response, and color—are observed and given 0, 1, or 2 points. The points are then totaled to arrive at the baby’s score,” Dr. Apgar explains the Apgar score in the “Evaluation of the Newborn Infant-Second Report.” “Scores for each infant can range between 0 and 10, with 10 being the best possible condition for an infant.” The test was to be given one minute after birth, and additional tests could be given in five-minute increments to guide treatment if the infant’s condition did not sufficiently improve.

The Apgar score gained popularity and by the 1960s was used in many hospitals in the United States. The score is still used today it’s an effective, accepted and convenient method for measuring the health of the newborn baby.

The Apgar test using only 5 data points has been successful in saving many infants as it introduced the notion that babies born depressed (in distress) can be revived and saved. The Apgar score gave doctors data points to analyze to decide on the best care to get the best outcome. Fast forward to the 21st century and just imagine what we can do with many more data points and the strength of Artificial Intelligence (AI).

The Future of Analytics in Medicine

Today’s clinical reality is far more complex, the average patient digital footprint has 600 unique elements, some measured every millisecond. This amount of data far exceeds the clinician’s ability to translate it into meaningful clinical practice. Yet, hidden in this data is information that can predict a patient’s deterioration, improve clinical outcomes and patient safety, streamline the level of care and decrease healthcare costs. CLEW – whose name is taken from the ball of thread used by Theseus to navigate the labyrinth – helps healthcare providers to navigate the maze of patient data – optimizing the level of care across all settings. CLEW predicts the future state of a patient, providing information to make informed clinical decisions. Using AI and data science, CLEW has developed ICU-proven, physiological, patient-level predictive models. These models identify patients at risk of unexpected clinical deterioration, allowing for timely rapid response team notification, better allocation of clinical resources, and removal of discharge barriers.