Natural language processing (NLP) is a field of deep learning (DL), with the ability for a computer to understand and analyze human language. DL is a class of ML characterized by the use of neural networks, in which the algorithm learns to distinguish patterns directly from data and learns on its own to select features to classify the input data.
The goal of NLP is to translate the natural human language of a patient’s medical record, for example, surgery reports, into structured format data to query for the presence or absence of a finding. In orthopedics, NLP has been applied to identify surgical site infections in free-text notes of medical records and achieved predictive abilities comparable with the manual abstraction process and superior to models that used administrative data only. In hip arthroplasty, NLP has been used to identify common data elements and the classification of periprosthetic femur fractures.
Computer vision is a domain of DL and describes the process of a machine understanding images or videos, and could be useful to aid diagnostic decision-making in fracture care. In computer vision, convolutional neural networks (CNNs) have proven to be effective for these purposes. Using pre-trained CNNs enables the transfer of knowledge to a specific new fracture recognition task, without the need for new time-consuming computational training.
However, subtle and occult fractures may be more challenging than fractures that are easy to detect. Even specialists cannot detect some scaphoid fractures on radiographs – so-called radiographically occult fractures. When applying computer vision to identify true fractures among suspected fractures, many of which are radiographically invisible to human observers, computer vision does not outperform humans.
This uncovers one of the problems of supervised learning of CNN for musculoskeletal computer vision of occult fractures: training of the algorithm requires a great number of cases, with a reference standard (MRI, CT or follow-up radiographs) which is at best debatable in accuracy.
Risk stratification in orthopedics has the potential to neutralize the influence of biased surgeons and thus overcome treatment inconsistencies, thereby improving patients’ functional outcomes and reducing associated healthcare costs. Thus, small significant changes in daily decision-making in high-volume patient care will result in important overall public health advances.
In orthopedics, ML-derived decision tools to assist clinicians in treatment outcomes have been developed in arthroplasty, trauma, oncology and spinal disorders. In oncology, decision tools show accurate performance characteristics in the pre-operative estimation of survival in patients with spinal or extremity metastatic disease.
The developed tools may enhance personalized survival prediction, from 30 days up to five years, and aid shared treatment decision-making, both surgical and non-surgical. In arthroplasty, estimation of patients who will benefit from elective surgery will support optimization in treatment strategy and prevent patients from undergoing an elective procedure with an unacceptably high (individual) risk of adverse events.
The increase in powerful (cheap) computers and the availability of larger and more robust data have driven the use of ML in the health area and will bring about new solutions in the orthopedics industry, such as PeekMed®.
We have been working on developing powerful preoperative planning solutions based on AI and if you are looking for solutions like PeekMed®, feel free to contact us.