Flap failure prediction in microvascular tissue reconstruction using machine learning algorithms

BACKGROUND Microvascular tissue reconstruction is a well-established,commonly used technique for a wide variety of the tissue defects.However,flap failure is associated with an additional hospital stay,medical cost burden,and mental stress.Therefore,understanding of the risk factors associated with this event is of utmost importance.AIM To develop machine learning-based predictive models for flap failure to identify the potential factors and screen out high-risk patients.METHODS Using the data set of 946 consecutive patients,who underwent microvascular tissue reconstruction of free flap reconstruction for head and neck,breast,back,and extremity,we established three machine learning models including random forest classifier,support vector machine,and gradient boosting.Model performances were evaluated by the indicators such as area under the curve of receiver operating characteristic curve,accuracy,precision,recall,and F1 score.A multivariable regression analysis was performed for the most critical variables in the random forest model.RESULTS Post-surgery,the flap failure event occurred in 34 patients(3.6%).The machine learning models based on various preoperative and intraoperative variables were successfully developed.Among them,the random forest classifier reached the best performance in receiver operating characteristic curve,with an area under the curve score of 0.770 in the test set.The top 10 variables in the random forest were age,body mass index,ischemia time,smoking,diabetes,experience,prior chemotherapy,hypertension,insulin,and obesity.Interestingly,only age,body mass index, and ischemic time were statistically associated with the outcomes.CONCLUSIONMachine learning-based algorithms, especially the random forest classifier, were very important incategorizing patients at high risk of flap failure. The occurrence of flap failure was a multifactordrivenevent and was identified with numerous factors that warrant further investigation.Importantly, the successful application of machine learning models may help the clinician indecision-making, understanding the underlying pathologic mechanisms of the disease, andimproving the long-term outcome of patients.

Double-paddled pectoralis major myocutaneous flap as an alternative to microvascularized free flaps in complex orocervical defects

The authors present the double-paddled pectoralis major myocutaneous flap as a successful alternative for the reconstruction of complex orocervical defects following failure of prior microvascularized free flaps or free flap harvest is not feasible. This method was used for the reconstruction of post-ablative defect in a 36-year-old male with a T4 squamous cell carcinoma of the base of tongue with laryngeal involvement. The distal paddle was adapted to reconstruct a defect of the floor of the mouth and further sutured in two layers (muscle-basal mandible and skin paddle-oral mucosa) while the proximal skin paddle was used to close the cervical skin and the peri-tracheostomy defect.

Unusual case of a free anterolateral thigh flap partial necrosis in a COVID-19 positive young male following extremity reconstruction

Free flap procedure provides an overall success rate of 97%, which decreases to 85% in hypercoagulable states. COVID-19, as a pro-thrombotic disorder, therefore seems detrimental to free flap survival. We encountered a case of unique pattern of free flap partial failure in a young male who underwent extremity reconstruction. The patient was diagnosed as COVID-19 positive on the 3rd day post-reconstruction. The flap survived well for the first 7 days post-operatively, but gradually the skin got necrosed and the subcutaneous fat layer was preserved when debriding. To our knowledge, this is the only case in which the skin of the free flap of a COVID-19 positive patient was necrosed almost entirely subsequently, while the subcutaneous fat was relatively preserved.

The infrahyoid myocutaneous flap for reconstruction after oral cancer resection: A retrospective single-surgeon study

Objective:To review our experience with infrahyoid myocutaneous flap in reconstruction after oral cancer resection.Methods:Chart reviews were completed for all patients who underwent oral reconstruction with an infrahyoid myocutaneous flap by a single surgeon in the Department of Otolaryngology at Chonburi Cancer Hospital from 2011 to 2017.Characteristics of the patients and postoperative complications were analyzed.Results:Of the 34 patients in the study,10(29.4%)developed partial flap loss and 1(2.9%)developed total flap loss.All cases of partial flap loss resolved with conservative treatment.Apparent cancer involvement of a cervical lymph node was significantly associated with flap failure(odds ratio:5.0,95%CI:1.03e24.28).Conclusions:The infrahyoid myocutaneous flap is a fairly reliable reconstruction method.The flap should be performed with caution in cases with gross lymph node involvement.