Periprosthetic infections are rare, but there is evidence to suggest that their frequency may be underestimated. No single laboratory test has perfect sensitivity and specificity for diagnosing infection. Most tests have better specificity when they are performed for patients in whom infection is suspected clinically rather than when they are used as screening tests. Screening test results that may suggest the possibility of infection include elevation of the erythrocyte sedimentation rate and/or serum C-reactive protein level more than three months after an arthroplasty. Most serologic tests are difficult to interpret when the patient has an underlying inflammatory arthropathy. Cultures of aspirated joint fluid can be especially helpful for patients who have symptoms suggestive of infection, but their results are best interpreted two weeks after administration of antibiotics has been discontinued. Joint fluid cell counts may also be helpful, but Gram stains of joint fluid have poor sensitivity and specificity. Criteria for diagnosing infection on the basis of frozen sections of implant membranes have not yet been standardized, but in many laboratories more than five neutrophils per high-power field in five or more fields (excluding surface fibrin) has been found to be suggestive of infection. Most polymerase chain reactions that detect the universal 16S rRNA bacterial gene have problems with false-positive results, but combining a universal polymerase chain reaction with subsequent bacterial sequencing can help improve specificity. Polymerase chain reactions can detect necrotic bacteria, so the clinical importance of positive results of this analysis in the absence of other features of infection remains to be determined.

Purpose of ReviewWith the unprecedented advancement of data aggregation and deep learning algorithms, artificial intelligence (AI) and machine learning (ML) are poised to transform the practice of medicine. The field of orthopedics, in particular, is uniquely suited to harness the power of big data, and in doing so provide critical insight into elevating the many facets of care provided by orthopedic surgeons. The purpose of this review is to critically evaluate the recent and novel literature regarding ML in the field of orthopedics and to address its potential impact on the future of musculoskeletal care. Recent Findings Recent literature demonstrates that the incorporation of ML into orthopedics has the potential to elevate patient care through alternative patient-specific payment models, rapidly analyze imaging modalities, and remotely monitor patients. Summary Just as the business of medicine was once considered outside the domain of the orthopedic surgeon, we report evidence that demonstrates these emerging applications of AI warrant ownership, leverage, and application by the orthopedic surgeon to better serve their patients and deliver optimal, value-based care.

Our machine-learning algorithm derived from an administrative database demonstrated excellent validity in predicting LOS and costs before primary TKA and has broad value-based applications, including a risk-based patient-specific payment model.

No abstract

No abstract