This website is intended for healthcare professionals only.

Hospital Healthcare Europe
Hospital Pharmacy Europe     Newsletter    Login            

Press Releases

Take a look at a selection of our recent media coverage:

CNN model improves orthopaedic surgeons’ detection of CT scan fractures

21st October 2022

A CNN model significantly aided orthopaedic surgeons detection of pelvic, rib and spine fractures on CT scans and their time for diagnosis

The use of a convolutional neural network (CNN) deep learning model significantly improved the diagnostic accuracy of orthopaedic surgeons’ detection of fractures as well as the time taken to make the diagnosis according to a study by Japanese researchers.

One of the main causes of diagnostic errors in the emergency department is the failure to correctly interpret radiographs and that the majority of diagnoses missed on radiographs are fractures. Moreover, in patients with multiple traumas, whole body CT scans are generally the preferred imaging modality, but a study has suggested that on a per-scan basis, there were 12.9% of missed injuries, of which 2.5% were clinically significant. The use of a CNN model for automatic detection of rib fractures detection could assist radiologists in improving diagnostic efficiency, reducing diagnosis time and radiologists’ workload. With some evidence that a CNN model can detect individual fractures, there remains uncertainty over whether such models could be of assistance in reducing missed fractures in a wide range of sites such as the spine, ribs and pelvis.

For the present study, the Japanese team examined whether a fracture detection algorithm could be of assistance to orthopaedic surgeons and compared their diagnostic accuracy with and without the CNN model. The team retrospectively reviewed patients who were diagnosed with either a pelvic, rib or spine fracture and who had undergone a CT scan within 7 days of their trauma. The CNN model was trained, and the performance assessed in terms of sensitivity, precision and the F1-score (which is a measure of the model’s accuracy).

CNN model and orthopaedic surgeon’s diagnostic performance

The training and validation set included 181 patients with a mean age of 54.3 (35.3% female). The testing set included 19 patients (mean age 51.2, 31.5% female) with 2,447 CT images and an average of 129 images per patients. The prevalence of pelvic, rib and spine fractures among the images were 5.8%, 3.6% and 5.5% respectively.

The CNN model itself had an overall mean sensitivity of 78.6%, a precision of 64.8% and an F1-score of 71.1% and also high for the individual fracture regions, e.g., pelvic (83.9%), rib (71.3%) and spine (78%).

Three orthopaedic surgeons with 3, 3 and years of experience respectively, reviewed the CT scans both with and without assistance from the CNN model.

For the detection of fractures of a whole-body CT scan, the mean sensitivity for the first surgeon was 69.7% alone but increased to 82.9% with the CNN model (p < 0.0001) and there were similar and significant differences for the other two surgeons. The model also improved the diagnostic accuracy for each of the three scanned areas.

When the researchers examined the time to diagnose the fracture, i.e., based on reading and interpreting the scan, the first surgeon diagnosed a fracture in 278.4 seconds, and this reduced to 162.3 seconds with assistance from the CNN model (p < 0.0001). Once again, there were significantly shorter diagnostic times for the other two surgeons.

The authors concluded that while their CNN model provided a good sensitivity for the detection of pelvic, rib and spinal fractures, when used by the orthopaedic surgeons their sensitivity improved as did the time to make a fracture diagnosis.

Inoue T et al. Automated fracture screening using an object detection algorithm on whole-body trauma computed tomography Sci Rep 2022

Meet the Expert: Javad Parvizi on orthopaedics and VTE

18th August 2022

Professor of orthopaedic surgery, Javad Parvizi MD FRCS, shares his thoughts on the latest international consensus meeting recommendations on venous thromboembolism and how this guideline could impact clinical care.

Dr Parvizi originally trained for four years to be cardiovascular surgeon before moving to the US to undertake research on blood flow based in an orthopaedics laboratory.

He later took up a residency in orthopaedics at the Mayo Clinic before finally moving to Philadelphia, where he has been since 2003.

The Rothman Institute is part of Thomas Jefferson University and one of the largest orthopaedic practices in the world, employing over 300 physicians and surgeons. According to Dr Parvizi, this busy department ‘performs approximately 20,000 joint replacements every year’.

Defining DVT and VTE

‘A DVT is a deep vein thrombosis and is a clotting problem that occurs in people’s veins and blocks the vein,’ says Dr Parvizi. ‘Sometimes a clot in the lungs can stop people from breathing, leading to a fatal outcome. Both a DVT and pulmonary embolism or, collectively, a venous thromboembolism (VTE), are potentially life-threatening conditions if not treated or prevented.’

According to Dr Parvizi, ‘most VTEs happen after surgical procedures but a VTE can be an unprovoked occurrence, for instance, through air travel, sitting for a long period of time or even out of the blue’.

Although there is always a risk of developing a DVT after a surgical procedure, Dr Parvizi adds that current thinking suggested that some patients have a genetic predisposition to develop a VTE. 

That said, the risk of developing a VTE after an orthopaedic procedure, even when accounting for other risk factors, is variable.

There are two types of VTE: a distal DVT, which occurs below the knee, and a proximal DVT, which occurs above the knee. The latter is associated with a greater risk to a patient.

Dr Parvizi explains that distal DVTs are common, suggesting that these can occur ‘in 10-15% of cases after a joint replacement’. However, fortunately, ‘these are all self-limiting, non-significant events.’ In fact, he notes how in many cases, both clinicians and patients would be unaware that a DVT occurred and that distal DVTs invariably resolve over time.

Nevertheless, the development of a pulmonary embolism (PE) is a much more serious complication, but the rate at which these develop is much lower. Dr Parvizi estimated that a PE might occur at a rate of ‘perhaps 0.5% or even lower, although the rate of a fatal PE is even lower, perhaps one in 1,000, although the literature suggests that the actual incidence might be lower still, at one in 4,000’. 

The burden of a VTE

In most cases where a patient develops a distal DVT after surgery, this is a benign event that commonly resolves without any lasting problems. In contrast, a chronic VTE is more problematic and could lead to postphlebitic syndrome, where there is a blockage of the veins in the legs.

Postphlebitic syndrome can result in ‘chronic swelling, and chronic ulcerations for a patient’, Dr Parvizi explains. However, he ventures that perhaps the most important reason to assess whether a patient has a DVT is to prevent the formation of a PE.

Although there is a widely held belief in the mechanical propagation theory – where a DVT literally travels from distal veins to the pulmonary circulation – Dr Parvizi says recent work has questioned this theory and that now ‘we think that a DVT doesn’t really travel to the lungs but that a PE and DVT can develop at the same time in a patient who is in a hypercoagulable state’.

Not only is the patient burden significant, the economic impact is considerable. With chronic DVT, patients require long-term treatment, which might include hospitalisation as well as chronic use of anticoagulants.

A DVT is more likely to become chronic if a patient develops several DVTs during their procedure, or when they become unresponsive to anticoagulation, and this latter effect can arise if an individual has an underlying problem with the anatomy of the veins. 

New VTE recommendation

Surgery induces a hypercoagulable state, which, in turn, increases the risk for the development of VTE. In the past after joint replacement, patients usually stayed in bed for a prolonged period of time and, as a result, ‘during the 1970s and 80s, the rates of DVT and PE were very high’, Dr Parvizi says.

In recent years, with a shift towards outpatient surgery and implementation of rapid recovery protocols, the overall incidence of VTE has declined drastically.

Nevertheless, one practice from the past that has continued is the post-operative use of aggressive anticoagulation and Dr Parvizi discusses how, in recent years, given the change in surgical practice and advice to avoid prolonged bed rest, the value of such aggressive anticoagulation has been called into question.

A further consideration that might reduce the need for anticoagulation is greater use of intermittent compression devices. According to Dr Parvizi, due to a major shift in the delivery of care, there is now less requirement for aggressive anticoagulation.

However, an important driver for change is the attendant risk associated with the use of anticoagulants, which lead to bleeding, increasing the risk for a haematoma, gross bleeding into the surgical wound or even in other organs such as the brain.

Additionally, anticoagulants are expensive and can be inconvenient to the patient, given the need for healthcare professionals to administer and/or monitor the anticoagulation drugs.

Furthermore, anticoagulants are not benign drugs, and their use is associated with several other problems that include the need for re-hospitalisation, re-operation, infection and joint stiffness. In fact, Dr Parvizi notes how ‘there have been studies showing that aggressive anticoagulation can kill patients, just like fatal PE’. 

While there are current guidelines available to help surgeons, Dr Parvizi acknowledges that these are subject to several limitations. For instance, most relate to hip and knee replacement and do not specifically cover other orthopedic procedures such as spine, foot and ankle, and sports surgeries.

In addition, ‘the current guidelines are totally disparate and conflicting in nature, with some recommending either for or against aggressive anticoagulation’, he says.

A further limitation of the current guidelines is that they do not take into account the genetic or geographic predisposition for formation of VTE. ‘For example, Asian patients are at a much lower risk of developing VTE than Caucasians,’ Dr Parvizi explains.

A final constraint of the previous guidelines is that they were outdated, relating to surgical protocols that are not in effect any more, or limited themselves to reviewing literature that was mostly conducted by industry, which of course introduces some degree of bias. 

Given all of the limitations, the International Consensus Meeting (ICM) gathered over 500 experts and specialists from across the world to produce updated and global guidelines using a strict and well-defined process.

The guideline committee reviewed the current literature, formulated relevant questions for current practice and sought consensus on these questions. Ultimately, the finished product was designed to be a global guideline for the prevention of VTE after all orthopaedic procedures.

A further advantage of the new guidelines is the inclusion of physicians from other medical disciplines, such as cardiology, haematology, anaesthesia, vascular medicine and others, which enhanced the value of the guidelines and have made them more applicable with regards to the multidisciplinary team (MDT).

Key principles and recommendations

The overarching principle of the guideline is the prevention and management of VTE for all orthopaedic procedures. The guideline isdivided up into 10 parts, one of which was a general section designed to answer questions relevant to all patients who undergo an orthopaedic surgical procedure.

Each of the subsequent sections relates to the different sub-specialities, such as the foot and ankle, spine, and so on. 

A total of 200 issues are covered, which include questions such as, ‘are there genetic predispositions that cause VTE?’ or ‘does prolonged bed rest increase the incidence of VTE?’ – with the answer being yes to both questions.

For Dr Parvizi, the most important recommendation is: ‘administration of aggressive anticoagulation is not necessary for the majority of patients undergoing orthopaedic procedures.’

His reasoning is that there is now plenty of evidence to show that intermittent compression devices work very well to prevent VTE but also that they provide additional benefits such as a reduction in post-surgical swelling of extremities, offer a better range of motion for the knee, and are associated with better patient satisfaction compared with the use of aggressive anticoagulation.

An overarching conclusion of the guideline, stemming from the available literature, is that low-dose aspirin is cost-effective and a safe modality for prevention of VTE. Studies have shown that the use of aspirin also reduces post-operative fever, which is a common event that worries both patients and healthcare professionals.

Moreover, Dr Parvizi says aspirin has also been used to reduce the rate of extra bone formation in the soft tissues (heterotopic ossification) and stiffness after orthopaedic procedures. The guideline now recommends that ‘aspirin should preferably be given twice a day for a period of four weeks but even two weeks of aspirin appears to be enough for most of these patients’.

Overall, Dr Parvizi believes the new guidelines will allow clinicians to move away from the use of aggressive anticoagulants and to make greater use of intermittent compression devices and aspirin.

In fact, he believes that the use of aggressive anticoagulants should now be reserved for those patients with a ‘genetic predisposition and/or patients an extremely high risk for a VTE’.

The impact on clinical practice

In the US, there has been a general shift over the last few years away from the use of aggressive anticoagulation towards the use of aspirin and intermittent compression devices. In fact, Dr Parvizi quotes data from ‘a survey of over 3,000 joint surgeons showing that over 90% of surgeons now use compression devices and/or aspirin for prevention of VTE after joint replacement’.

While there has been an important change in practice among US surgeons, he believes that adoption of aspirin and intermittent compression devices by surgeons from other parts of the world has been slow mostly due to medico-legal concerns.

A further barrier to this adoption is the resistance of colleagues from other specialties, such as haematology and cardiology, who might not be aware of the wealth of orthopaedic literature endorsing the use of aspirin.

Now, with the publication of the new guidelines that have been developed with the MDT in mind, it is hoped that this will provide the necessary endorsement and reassurance to the medical community to embrace a change in practice. 

Overcoming further challenges

Dr Parvizi says that one of the benefits of developing a new guideline was that while providing robust evidence to support a change in orthopaedic practice, it also highlighted gaps in the current evidence and enabled the formulation of relevant questions that should be addressed by future research.

He believes that there is a need for independent studies to compare the efficacy of low-dose aspirin with other anticoagulation agents. He mentioned the ongoing PEPPER trial, which is comparing low-dose aspirin, coumadin and factor 10 inhibitors for VTE prevention. The results are eagerly awaited.

Dr Parvizi notes how more studies are required to better understand the genetic mutations that predispose individuals towards having a VTE as well as more work on the role of intermittent compression devices.

Taken together, Dr Parvizi hopes that future studies will facilitate a move away from the use of expensive anticoagulants, which ultimately have a huge economic impact.

‘In the US alone, there are over one million joint replacement procedures undertaken per year, so if 92% of those patients are receiving aspirin, the anticipated cost savings would run into hundreds of millions,’ he says. 

Furthermore, there is a whole range of additional benefits to using aspirin, including a reduction in the development of haematomas, infection risk, post-operative fever and subsequent clinical fever work-up. There is also less need for transfusions and a lower level of post-operative anaemia.

Dr Parvizi adds that the available data suggest that ‘aspirin is actually better than coumadin for the prevention of VTE.’ 

Ultimately, ‘convenience, efficacy, safety and economic benefits of aspirin are just beyond dispute now and, over time, there will be a shift towards the use of aspirin and intermittent compression devices instead of expensive anticoagulant medications,’ he concludes. 

As for the next steps, Dr Parvizi says that the combination of the publication of the guideline in a prestigious Journal of Bone and Joint Surgery and future translations of the documents into numerous languages will allow effective dissemination of the work that was generated by over 500 experts.

The guidelines are being discussed at various conferences and have been endorsed by a number of professional organisations who have published the guideline on their websites.

Finally, Dr Parvizi believes it is necessary to note that patients who require orthopaedic procedures should no longer fear the development of a blood clot. They can become better informed that the changes in surgical procedures and VTE management in recent years are designed to be safer and more convenient for them.

Recommendations from the ICM-VTE: General. The ICM-VTE General Delegates. J Bone Joint Surg 2022;104(suppl 1):4–162.