Cardiac Comorbidity Risk Score: Zero-Burden Machine Learning to Improve Prediction of Postoperative Major Adverse Cardiac Events in Hip and Knee Arthroplasty.

Background In this retrospective, observational study we introduce the Cardiac Comorbidity Risk Score, predicting perioperative major adverse cardiac events (MACE) after elective hip and knee arthroplasty. MACE is a rare but important driver of mortality, and existing tools, eg, the Revised Cardiac Risk Index demonstrate only modest accuracy. We demonstrate an artificial intelligence-based approach to identify patients at high risk of MACE within 4 weeks (primary outcome) of arthroplasty, that imposes zero additional burden of cost/resources. Methods and Results Cardiac Comorbidity Risk Score calculation uses novel machine learning to estimate MACE risk from patient electronic health records, without requiring blood work or access to any demographic data beyond that of sex and age, and accounts for variable/missing/incomplete information across patient records. Validated on a deidentified cohort (age >45 years, n=445 391), performance was evaluated using the area under the receiver operator characteristics curve (AUROC), sensitivity/specificity, positive predictive value, and positive/negative likelihood ratios. In our cohort (age 63.5±10.5 years, 58.2% women, 34.2%/65.8% hip/knee procedures), 0.19% (882) experienced the primary outcome. Cardiac Comorbidity Risk Score achieved area under the receiver operator characteristics curve=80.0±0.4% (95% CI) for women and 80.1±0.5% (95% CI) for males, with 36.4% and 35.1% sensitivities, respectively, at 95% specificity, significantly outperforming Revised Cardiac Risk Index across all studied age-, sex-, risk-, and comorbidity-based subgroups. Conclusions Cardiac Comorbidity Risk Score, a novel artificial intelligence-based screening tool using known and unknown comorbidity patterns, outperforms state-of-the-art in predicting MACE within 4 weeks postarthroplasty, and can identify patients at high risk that do not demonstrate traditional risk factors.

Relationship of plasma metal ions and clinical and imaging findings in patients with ASR XL metal-on-metal total hip replacements.

BACKGROUND: Plasma metal ion levels are commonly used in the postoperative follow-up evaluation of patients who have had a metal-on-metal hip arthroplasty. However, the relationship between these levels and clinical and imaging findings is not well known. METHODS: We evaluated 156 consecutive patients who received a unilateral ASR XL total hip replacement. Patients presented, regardless of symptoms, in response to a voluntary recall of the hip replacement by the manufacturer and were assessed with regard to the presence and type of symptoms and plasma cobalt-chromium levels. In addition, radiographic and magnetic resonance imaging studies were performed and analyzed. RESULTS: Eighty patients were asymptomatic, and seventy-six patients were symptomatic. The median cobalt level was 1.8 ppb, and the median chromium level was 1.0 ppb (at or below measurement threshold). Pseudotumors that could be detected on magnetic resonance imaging were seen in 69% (107) of 156 patients, and radiographic osteolysis was evident in 7% (eleven patients). At a threshold of 5 ppb, no association was detected between abnormal metal ion levels and patient symptoms, prosthetic femoral head size, or acetabular cup inclination. An abnormal cobalt level was significantly associated with the presence of periprosthetic lucency on radiographs and pseudotumor on magnetic resonance imaging (p < 0.05). An abnormal chromium level showed a similar pattern, but the relationships did not reach significance. Both abnormal plasma cobalt and chromium levels were associated with larger sizes of pseudotumor when present (p < 0.05). CONCLUSIONS: In our sample, with a threshold of 5 ppb, abnormal plasma metal ions were associated with larger sizes of pseudotumors when present, but were not predictive of patient symptoms. Abnormal plasma cobalt levels have a significant association with periprosthetic lucency and presence of pseudotumor. Plasma chromium shows a similar pattern of association with lucency and presence of pseudotumor, although the relationships were not significant. Metal ion analysis should be used in conjunction with clinical and imaging evaluation and not as a sole indirect screening test when evaluating patients following metal-on-metal hip arthroplasty.

Metal-on-metal total hip arthroplasty: do symptoms correlate with MR imaging findings?

PURPOSE: To determine the prevalence of magnetic resonance (MR) imaging abnormalities after metal-on-metal total hip arthroplasty and to determine whether presence of symptoms correlates with findings at MR imaging. MATERIALS AND METHODS: This HIPAA-compliant study was approved by the institutional review board, and informed consent was waived. MR imaging was performed with conventional sequences and a 1.5-T clinical imager in 192 hips (174 patients) evaluated during a 15-month period. Two observers retrospectively reviewed the images for the presence and size of pseudotumor, communication with the pseudocapsule, wall thickness, synovial hypertrophy, compartmentalization, solid components, foci of wall susceptibility, osteolysis, bone marrow edema, abductor muscle or tendon abnormality, and Anderson MR grade (normal, infection, or varying severity of metal-on-metal disease). These findings were compared between asymptomatic and symptomatic patients by using the Fisher exact test or the Wilcoxon-Mann-Whitney test, as appropriate. RESULTS: Prevalence of pseudotumors per patient and per hip was 69% (120 of 174 patients, 132 of 192 hips). Bone marrow edema (present in six asymptomatic patients and 19 patients with pain, P < .01) and tendon tearing (present in five asymptomatic patients and 13 patients with pain, P < .05) were predictors of pain. Presence of symptoms was not correlated with presence (P = .4151) or size of pseudotumors. Anderson MR grade binarized into normal versus abnormal showed moderate agreement between readers (κ = 0.439) but was also not correlated with symptoms (P = .6648). CONCLUSION: The presence of bone marrow edema and abductor tendon tears but not the presence or size of pseudotumor was associated with patient pain.