Machine learning outperforms clinical experts in classification of hip fractures.

Hip fractures are a major cause of morbidity and mortality in the elderly, and incur high health and social care costs. Given projected population ageing, the number of incident hip fractures is predicted to increase globally. As fracture classification strongly determines the chosen surgical treatment, differences in fracture classification influence patient outcomes and treatment costs. We aimed to create a machine learning method for identifying and classifying hip fractures, and to compare its performance to experienced human observers. We used 3659 hip radiographs, classified by at least two expert clinicians. The machine learning method was able to classify hip fractures with 19% greater accuracy than humans, achieving overall accuracy of 92%.

Rate of blood loss over 48 hours following total knee replacement.

The purpose of this study was to determine the rate of blood loss after total knee arthroplasty and assess the efficacy of drains using autologous blood transfusion. A prospective study was undertaken of 100 consecutive patients undergoing routine total knee arthroplasty. The diagnosis was osteoarthritis in 85% of patients and rheumatoid arthritis in 12% of cases. The rate of blood loss was recorded hourly for the first 12 h, 4 hourly for the subsequent 12 h and 6 hourly for the following 24 h. Autologous blood was reinfused within 12 h of surgery according to the protocol. Eighty-four percent of the total blood drained, was collected in the first 12 h and 94% in the first 24 h. 69% of the total blood which was drained was reinfused. The mean preoperative haemoglobin was 13.18 gm/dl and 10.23 gm/dl on the 5th day. A mean volume of 70-80 ml of homologous blood was reinfused in addition to the autologous transfusion in 11 of the 100 cases. There were no cases of deep or superficial sepsis, nor any identifiable complications related to the autologous blood transfusion. This study suggests it is safe to remove the postoperative joint drain after the 12-h period.

The risk of anterior cruciate ligament rupture with generalised joint laxity.

We assessed hyperextension of the knee and joint laxity in 169 consecutive patients who underwent an anterior cruciate ligament reconstruction between 2000 and 2002 and correlated this with a selected number of age- and gender-matched controls. In addition, the mechanism of injury in the majority of patients was documented. Joint laxity was present in 42.6% (72 of 169) of the patients and hyperextension of the knee in 78.7% (133 of 169). All patients with joint laxity had hyperextension of their knee. In the control group only 21.5% (14 of 65) had joint laxity and 37% (24 of 65) had hyperextension of the knee. Statistical analysis showed a significant correlation for these associations. We conclude that anterior cruciate ligament injury is more common in those with joint laxity and particularly so for those with hyperextension of the knee.

Driving whilst plastered: is it safe, is it legal? A survey of advice to patients given by orthopaedic surgeons, insurance companies and the police.

Many patients, immobilised in a plaster cast after a fracture of the upper or lower limb, wish to drive. They frequently ask permission to do so from the treating surgeon. Insurance companies are apparently willing to insure these patients to drive if they obtain their doctors permission. The DVLA guidelines are unhelpful in these circumstances. We therefore established current practice within the south west region by canvassing 126 consultant orthopaedic surgeons, 27 insurance companies and the 6 regional police constabularies, sending them specific clinical scenarios and asking how they would advise these patients regarding safety to drive. The results were as follows: sixty-seven (53%) of surgeons responded of which 97% gave specific advice regarding safety to drive. The insurance companies were generally unwilling to respond and a national response was received from the Association of Chief Constables, which specifically stated that safety to drive was for the individual patient to decide and the doctor should not give advice. We consider this to be unsatisfactory for all parties and suggest how this situation could be improved for both the patient and other road users welfare.