The Adelaide Score: An AI measure that predicts discharge after general surgery

A derived artificial intelligence measure developed by South Australian researchers has successfully predicted general surgery patient discharge within 12 and 24 hours with over 80 per cent accuracy.

The Adelaide Score, the brainchild of researchers at the University of Adelaide, Queen Elizabeth Hospital, and Health and Information (HI) collaborative, could be tested in South Australian hospitals later this year, following an extensive study which examined the performance of machine learning algorithms.

Dr Joshua Kovoor, a full-time PhD in surgery candidate at Queen Elizabeth Hospital in Adelaide said hospital stays of almost 9000 South Australian general surgery patients were analysed in the derivation study.

“Currently, no tool accurately predicts patient discharge in real-time within the Australian health care system,” Dr Kovoor said.

“We hope the Adelaide score will streamline and simplify discharge planning after surgery for everyone in the healthcare system, including doctors, nurses and most importantly the patient and their loved ones.

“The Adelaide Score involves artificial intelligence algorithms. With proper training, the more it is used, the more accurate it will become in predicting patient discharge times.”

Dr Kovoor said the study referenced tens of thousands of ward round note timings and included inputs including vital signs and blood test data.

“Because the Adelaide Score uses objective inputs, it can be implemented in any hospital around the world, delivering extraordinary cost savings,” Dr Kovoor said.

“We’re exploring options, however, the Adelaide Score could one day be integrated into a patient’s electronic medical record or accessed via an app.

“We hope the Adelaide Score will be a mainstay of every Australian hospital within the next decade.”

Dr Kovoor and team’s research was unveiled at the Royal Australasian College of Surgeons Annual Scientific Congress in Adelaide (1-5 May).

 

Aboriginal Liaison Officers transforming patient outcomes in Alice Springs

The Australian-first decision to introduce Aboriginal Liaison Officers within the orthopaedic multi-disciplinary team at Alice Springs Hospital has transformed patient outcomes, specifically, a 37 per cent reduction of self-discharge among Indigenous patients and significantly fewer self-discharges before definitive surgical and medical treatment.

Two patient cohorts were analysed as part of the study, patients admitted in the nine-months prior to the introduction of Aboriginal Liaison Officers (February 2021), and patients admitted nine-months following the introduction of Aboriginal Liaison Officers.

Dr Morgan Berman, a RACS member and orthopaedic registrar was based at Alice Springs Hospital during the trial period and said the introduction of Aboriginal Liaison Officers significantly reduced the risk of self-discharge in Indigenous patients.

“At Alice Springs Hospital, we noted a high percentage of Indigenous patients self-discharging before their treatment had concluded, and in some instances before surgery,” Dr Berman said.

“Risk factors for self-discharge were younger in age, pensioners and unemployed. They were more likely to be residents of Alice Springs Town-Camps or live in communities within 51 to 100 kilometres of Alice Springs Hospital.

“They became members of the orthopaedic multi-disciplinary team, accompanied doctors on daily ward rounds, attended patient reviews, and helped make hospitals a culturally safe place for Indigenous patients.

“Some Indigenous men and women are sceptical of Australia’s health care system. The Aboriginal Liaison Officers played a key role brokering appropriate treatment and insured significantly fewer Indigenous patients self-discharged before they had concluded treatment.

“The decision to trial Aboriginal Liaison Officers within the orthopaedic multi-disciplinary team at Alice Springs Hospital was successful in improving patient care, and Aboriginal Liaison Officers continue to be a part of the orthopaedic team.

“The results of our trial highlights the importance of Aboriginal Liaison Officers in hospitals servicing areas with high Indigenous populations.”

Dr Berman’s research was unveiled at the Royal Australasian College of Surgeons Annual Scientific Congress in Adelaide (1-5 May).

 

Artificial intelligence to predict chemotherapy toxicities in colon cancer patients

A team of Melbourne-based researchers and doctors have successfully used artificial intelligence automated body composition measurements to predict the risk of chemotherapy-related toxicities to improve chemotherapy dosing in cancer treatment.

The Australian-first, retrospective study was performed on stage 3 colon cancer patients receiving a chemotherapy drug, oxaliplatin, following surgery at a major Melbourne teaching hospital, Western Health.

Results:

• Between 2012 and 2021,129 patients were identified
• Male 53 per cent, female 47 per cent
• Mean age – 58 years
• Dose-limiting toxicity experienced in 84 patients (65.1per cent) higher in females
• Females had significantly lower muscle indices and higher adiposity (a condition of having too much fatty tissue in the body)
• The optimal oxaliplatin cut point identified as 3.41 mg/kg lean body mass
• Within the first four cycles of chemotherapy, 37 patients experienced dose-limiting toxicity, of which 29 (78per cent) received a dose equal to or greater than the predicted cut-point.

Professor Justin Yeung, a Royal Australasian College of Surgeons Fellow, is Head of the Department of Surgery, Western Precinct, University of Melbourne and is a consultant colorectal surgeon at Western Health.

Professor Yeung led the multidisciplinary research and said the study has the potential to revolutionise the way chemotherapy drugs are administered to cancer patients around the world. 
“For the past three decades we have effectively been using the same drugs and the same approach to determine chemotherapy dosages,” Professor Yeung said.

“Currently, chemotherapy dosages are based on body surface area, a derivative from the patient’s height and weight. Body make-up is not taken into consideration.

“Using artificial intelligence automated body composition measurements, we have been able to predict the risk of chemotherapy-related toxicities.

“It’s a game-changer given 40per cent of colorectal cancer patients require chemotherapy. Of those, up to 70per cent experience some form of chemotherapy-related toxicity, including nerve damage, gastrointestinal disturbances including nausea and diarrhoea, as well as increased risks of severe infection.

“Artificial intelligence is removing the guess work from chemotherapy dosing, predicting likely toxicities and ultimately benefiting the patient.

“This has the potential to change medicine. Shortly we’ll be expanding the research to include other cancers including breast cancer.

“We’re hopeful that in a decade’s time, artificial intelligence using body composition measurements combined with patient characteristics to predict the risk of chemotherapy-related toxicities will be the norm in every Australian hospital.”

Professor’s Yeung’s research was unveiled at the Royal Australasian College of Surgeons Annual Scientific Congress in Adelaide (1-5 May).

 

Auckland surgeons call for lap belt restraints to be banned on Aotearoa New Zealand roads

Surgeons at Starship Children’s Hospital in Auckland have recommended the phasing out of lap belt restraints in all vehicles on Aotearoa New Zealand roads following an eight-year retrospective review.

Between January 2013and January 2020, 28 children were admitted to Starship Children’s Hospital following a serious road traffic crash.

In total, there were five paediatric lap belt injuries of the abdominal aorta.
• Ages ranged between three and 12 years of age, with a median age of eight years of age
• 60 per cent of patients were documented to have sustained abdominal wall ecchymoses
• All five patients sustained a hollow viscus injury, with three patients suffering a hollow viscus peroration
• All five patients sustained lumbar spine fractures, with four patients suffering Chance fractures.

Dr Dhru Ramson, a RACS Trainee at Auckland’s Starship Children’s Hospital said car accidents are responsible for a large number of child deaths In New Zealand.

“Age-appropriate seating restraints have been shown to offer a safety benefit,” Dr Ramson said.

“Lap belts have been heavily implicated in contributing to injury with a 50 per cent reduction in fatalities from automobile collisions following the introduction of the three-point harness.

“Child restraint practises in Aotearoa New Zealand have been demonstrated to fall short of best practise recommendations.

“In our retrospective study, all five patients who sustained lap belt injuries of the abdominal aorta had a triad of gastrointestinal injury, lumbar spine fracture and abdominal aortic injury.

“Our single centre audit demonstrates lap belts continue to cause significant injury, which could be reduced by using three-point restraints and age-appropriate restraints.

“We recommend the phasing out of lap belts and increased utilisation of age-appropriate restraints.

“Anecdotally, paediatric lap belt injuries of the abdominal aorta occur in later model vehicles.

“They don’t happen very often, but when they do, they are catastrophic, which is alarming, because the severity of this type of injury can be reduced with appropriate safety measures, including a three-point restraint.

“I encourage the Hipkins Government to consider legislation which prohibits the use of lap belt restraints in all vehicles on New Zealand roads.”

Dr Ramson’s research was unveiled at the Royal Australasian College of Surgeons Annual Scientific Congress in Adelaide (1-5 May).

 

Audits lead to dramatic decrease in surgical deaths

Delegates attending the Royal Australasian College of Surgeons Annual Scientific Congress (ASC) heard how the College’s surgical quality program that reviews 'death under a surgeon' has been associated with a substantial reduction in deaths.

Australia is the only country with a national surgical mortality audit—the Australian and New Zealand Audit of Surgical Mortality (ANZASM). This audit ensures that every patient in Australia who dies in hospital under a surgeon—whether they had an operation or not—undergoes an independent, anonymous, and external peer review by another surgeon.

Such external review is normal practice in any safety critical industry, but not in medicine. ANZASM commenced in 2002 in Western Australia and has included all states since 2011 and has been part of the College’s Continuous Professional Development program since 2013.

The first presentation reported that the Standardised Mortality Ratio (SMR), a standard methodology used around the world to track changes in mortality, has shown a significant fall in deaths under a surgeon in all Australian states and territories and in all surgical specialties.

The reduced mortality, typically 20 per cent or more over the last five years and even greater for states that joined ANZASM earlier, is a reflection of the education provided to surgeons through self-reflection, patient-specific independent, external review and shared learning through reports and symposia.

The second presentation, based on a national pilot study accessing the outcome, reported mortality following very high-risk emergency major abdominal surgery—the Australian and New Zealand Emergency Laparotomy Audit (ANZELA). The audit has shown the mortality after emergency laparotomy in Australia is around seven per cent, at least one third less than reported internationally. This represents an estimated 500 Australian lives saved every year. 

An important difference between Australian and overseas studies is the avoidance of an emergency laparotomy for extremely high-risk patients for whom survival is unlikely, and for those who do leave hospital is very often associated with poor quality of life. This has been a strong focus of the ANZASM for many years.

Chair of the ANZELA working party, Dr James Aitken, said the results demonstrated the enormous benefit that can be gained from investing in Clinical Quality Registries.

“The ANZASM and ANZELA are a practical demonstration of the College’s strong commitment to Clinical Quality Registries. The College strongly endorses the Australian Commission for Safety and Quality in Health Care revised Framework for Australian Clinical Quality Registries released for discussion in January 2023.

“Both ANZASM and ANZELA have clearly demonstrated how relatively modest funding of Clinical Quality Registries will result in much improved outcomes for patients. The Commission’s own work has demonstrated that they also result in long term financial savings."

 

Australian kidney transplantation rates nosedive to a 10-year low

New Australian research has discovered that since the start of the COVID-19 pandemic, Australian kidney transplantation rates have fallen dramatically to a 10-year low.

Australia and New Zealand Dialysis and Transplant Registry (ANZDATA) data was evaluated from 2011–2021 to determine the annual rates of kidney transplantation in Australia.

Dr Darshan Sitharthan a Urology Registrar at Bankstown Hospital in Sydney said only 33 people per million are currently receiving a kidney transplant.

“2018 was our best year on record, with a transplantation rate per capita of 46 people per million, however, since COVID, Australian kidney transplantation rates have nosedived to a 10-year low,” Dr Sitharthan said.

“For more than half a century, kidney transplantation has become a mainstay for treating end-stage kidney disease.

“Kidney transplantation offers patients the greatest chance of increased longevity and improved quality of life. However, even today, the demand for kidneys far exceeds the supply.

“This is even more alarming considering kidney transplantation rates are at a 10-year low.

“The majority of kidney transplants are elective surgery, and surgeons are working through a backlog, triggered by the COVID-19 pandemic.

“There are thousands of patients who are searching for a suitable kidney donor and are stuck in dialysis. It’s essential kidney transplantation rates return to pre-COVID-19 levels as quickly as possible.”

The research also revealed that of the 10,598 kidney transplants which occurred between 2011 and 2021, only 2,614 or 24.6 per cent of patients are currently alive.

Dr Sitharthan’s research was unveiled at the Royal Australasian College of Surgeons Annual Scientific Congress in Adelaide (1-5 May).

 

Ethnic disparities in access to bariatric surgery

New Zealand research has highlighted the ethnic disparities in access to bariatric surgery. To determine these disparities a seven-year retrospective study from July 2015 to April 2022 reviewed all referred bariatric surgery cases for the South Island against national ethnicity data.

Key finding: 

• 2506 patients' data were captured
• 995 received surgery
• 1511 were declined (39.7 per cent acceptance rate)
• Across the South Island, all regions had a higher population percentage identify as NZ/Other European (82-92 per cent) compared to nationally (70 per cent)

Of patients that received bariatric surgery:

• 71.2 per cent NZ/other European
• 21.5 per cent Māori
• 4.9 per cent Pacific peoples
• 7 per cent Asian

This is in comparison to the Aotearoa New Zealand population demographic of which 8.3 per cent are Pacific peoples and 15.7 per cent are Asian.

Dr Mark Stewart, a RACS Fellow and Bariatric Surgeon at Nelson Hospital, said ethnicity is currently not a factor considered in prioritising bariatric surgery.

“There is a disproportionate lack of access for ethnic minorities to receive bariatric surgery,” Dr Stewart said.

“Approximately one in three New Zealanders are obese, while 15 per cent of New Zealanders are morbidly obese.

“When ethnicity is taken into consideration, Pacific peoples account for 46 per cent of all morbidly obese patients in New Zealand, followed by Māori (26 per cent), NZ/Other European (12 per cent) and Asian (5 per cent).

“The research suggests the ethnic groups who would most benefit from bariatric surgery are not having the procedure at rates consistent with their need.

“Bariatric surgery is a precious resource which is not well funded. Because ethnicity is currently not a factor considered in prioritising bariatric surgery, vulnerable groups are likely missing out.

“We must ensure Pacific peoples and Māori patients, who are more likely to be morbidly obese, can access bariatric surgery.

“More funding is essential. Bariatric surgery is expensive up front, but there are long term financial benefits. 

“People who undergo bariatric surgery have improved quality of life, which also saves the taxpayer in the millions of dollars.”

Dr Stewart’s research was unveiled at the RACS Annual Scientific Congress in Adelaide (1-5 May). 

 

Should breast density become a compulsory component of breast cancer screening tests?

A cross-sectional study conducted at Adelaide’s Queen Elizabeth Hospital Breast and Endocrine Clinic outpatient department has highlighted the overwhelming majority of women do not know their breast density, which is a risk factor for breast cancer and masks cancer on a mammogram.

Women waiting for their mammogram were given a breast density survey to complete.

Key findings

• Sample size – 300 patients
• 40 per cent had not heard the term ‘breast density’ before
• Of those who had heard of breast density, 29 per cent and 70 per cent respectively knew it could increase risk of breast cancer and it could mask breast cancer
• 33 per cent of women who had heard of breast density were aware it could not be determined by touch or feel
• Among all respondents, 80 per cent were interested to know their own breast density.

Dr Avisak Bhattacharjee, a Consultant Surgeon and Surgical Epidemiologist said the ongoing study found the overwhelming majority of women are unaware of their breast density.

“Western Australia is the only Australian state, which informs women about their breast density as part of breast cancer screening tests,” Dr Bhattacharjee said.

“The USA and most of the provinces of Canada have passed legislation making it compulsory for breast cancer screening reports to include information about a patient’s breast density.

“However, most women in Australia are in the dark when it comes to their breast density.

“Breast density is important for two key reasons. It’s an important risk predictor for breast cancer and can hide a tumor on a mammogram.

“The higher a patient’s breast density, the higher the chance of missing a lump in a mammogram.

“It’s also impossible to determine breast density without having a mammogram as it has no correlation to the size and feel of a breast.

“Without breast density notification, women are not getting a full picture of their breast health.

“It’s time we had a serious discussion about the benefits of breast density notification and whether it should become a compulsory component of breast cancer screening reports for all Australian women.”

Inappropriate over-prescribing of opioids after surgery

Global research led by Aotearoa New Zealand medical students has found opioids are being prescribed at double the quantity of that which is consumed by patients in the week after surgery.

Doctors and researchers at Middlemore and Whangarei Hospital also found the quantity of opioids prescribed at discharge was independently associated with a 30 per cent increase in opioid consumption.

The research was an international, multicentre prospective cohort study of general surgical, urological, gynaecological and orthopaedic surgery. It involved a seven-day post-discharge phone call follow-up which was carried out by the Trials and Audits in Surgery by Medical students in Australia and Aotearoa New Zealand (TASMAN) Collaborative.

Key findings:

• 4273 patients were recruited from 144 hospital centres across 25 countries
• Median age was 50 years
• 53.1 per cent were female and 46.9 per cent male
• Patients underwent 19 common surgeries- At discharge, 1311 (30.7 per cent) were prescribed an opioid pain killer, a median 100 milligrams or 10 tablets of 10 mg sevredol
• Seven days after surgery, a median of only 40 milligrams (four tablets of 10 mg sevredol) had been consumed.

Further analysis showed taking opioids did not improve patients’ pain when they were at home or satisfaction with pain relief but did increase the risk of representation to medical services for opioid side effects.

Dr Chris Varghese, an honorary lecturer at the University of Auckland and junior doctor at Middlemore Hospital in Auckland said after accounting for patient factors including pain, the surgery type and patient comorbidities, the quantity of opioids prescribed at discharge was independently associated with increased use of opioids.

“The inappropriate over-prescribing of opioids after surgery is contributing to the global opioid crisis,” Dr Varghese said.

“Our international cohort study aims to identify factors that drive increased opioid consumption at seven days after discharge from common surgical procedures.

“Generally, surgeons prescribe double the number of opioids a patient consumes in the first week after surgery.

“The more opioids we prescribe, the more a patient uses at home, and this is not explained by differences in pain levels.

“We also found prescribing more opioids did not improve the experience of pain or satisfaction with pain relief but did increase the risk of side effects.

“We send patients home with too many opioids after surgery. The over-prescription of opioids is not a problem isolated to the United States, it’s an issue in Aotearoa New Zealand too.

“We need to better-tailor opioid prescriptions to individual patients, there is no ‘one size fits all’ answer.
 
“This research offers doctors and patients real-world data to guide when an opioid is needed, and if an opioid is being prescribed, how much opioid is typically used by patients. The data will help us think more carefully about our pain relief prescriptions, so it’s tailored to patients’ needs.”