Surgeon Develops Algorithm to Predict Arthroscopic Hip Surgery Outcomes

A machine-learning algorithm developed by an orthopedic surgeon at Hospital for Special Surgery (HSS) and his colleagues identified predictive factors associated with worse outcomes for patients with femoroacetabular impingement (FAI) of the hip who had arthroscopic surgery to treat it. FAI is a condition in which the ball and socket of the hip joint do not fit together properly and can ultimately cause pain and the need for a surgical repair.
 
According to a paper published on January 31 in the American Journal of Sports Medicine, the factors that significantly predicted worse patient outcomes were anxiety and depression, duration of symptoms for more than two years before surgery, a high preoperative score on patient-reported outcome surveys and, surprisingly, receiving preoperative steroid injections.
 
“These findings are important from several perspectives. First of all, they demonstrate the value of integrating a machine-learning tool into clinical practice,” said first author Benedict Nwachukwu MD, MBA, a sports medicine surgeon and co-director of clinical research for the Sports Medicine Institute at HSS in New York City. “From a clinical perspective, our results reinforce that we should be screening for anxiety and depression. The symptom duration finding should encourage more payers and insurance companies to cover hip surgery for patients sooner, rather than keep them in prolonged conservative treatment. Finally, the risk associated with the use of preoperative injections is a novel finding that has not been reported very often in the literature.”
 
Dr. Nwachukwu helped design the study and developed the machine-learning algorithm in collaboration with a data scientist at PatientIQ, the company that provided the data analysis platform. He collaborated with colleagues at Wake Forest Baptist Health in Winston-Salem, North Carolina, and at Rush University Medical Center in Chicago, Illinois. Senior investigator Shane J. Nho, MD, MS, hip arthroscopy specialist at Midwest Orthopaedics at Rush, performed the hip arthroscopy surgeries and provided the patient data. Dr. Nho was a resident in orthopedic surgery at HSS from 2003 to 2008.
 
Dr. Nwachukwu and colleagues built the machine-learning algorithm using electronic health record data for 898 patients with FAI who had hip arthroscopic surgery between January 2012 and July 2016 at Rush University Medical Center. All patients had completed three patient-reported outcome surveys before surgery and again two years after surgery: the Hip Outcome Score-Activities of Daily Living Subscale (HOS-ADL) ; the Hip Outcome Score-Sports Subscale (HOS-SS); and the modified Harris Hip Score (mHHS). These subjective measures collect patients’ reports on their abilities to perform daily activities and sports activities and their overall hip condition, respectively.
 
The researchers determined the factors associated with achieving or not achieving the minimal clinically important difference in these patient-reported outcome measures and then analyzed the large dataset of patient information. In addition to identifying factors that predicted worse patient outcomes, the investigators found two variables that predicted achieving better results: running, at least at the recreational level, and being female.
 
This study is one of few reporting on the negative impact of preoperative steroid injections on patient-reported outcomes after orthopedic hip surgery. Patient response to steroid injections is a common diagnostic approach for confirming the hip joint as the location of the pain. Some insurance companies will not approve surgery for FAI unless a patient has had a diagnostic steroid injection first.
 
“Worse postoperative outcomes after the preoperative use of steroid injections may be due to poor healing of the labral tissue after exposure to steroid,” Dr. Nwachukwu said. “Our finding suggests that surgeons should consider the use of steroid injections judiciously. They have a role to play but using a purely anesthetic injection for diagnostic purposes may be a better option.”