Automated robot‐assisted surgical skill evaluation: Predictive analytics approach

Background

Surgical skill assessment has predominantly been a subjective task. Recently, technological advances such as robot‐assisted surgery have created great opportunities for objective surgical evaluation. In this paper, we introduce a predictive framework for objective skill assessment based on movement trajectory data. Our aim is to build a classification framework to automatically evaluate the performance of surgeons with different levels of expertise.

Methods

Eight global movement features are extracted from movement trajectory data captured by a da Vinci robot for surgeons with two levels of expertise – novice and expert. Three classification methods – k‐nearest neighbours, logistic regression and support vector machines – are applied.

Results

The result shows that the proposed framework can classify surgeons' expertise as novice or expert with an accuracy of 82.3% for knot tying and 89.9% for a suturing task.

Conclusion

This study demonstrates and evaluates the ability of machine learning methods to automatically classify expert and novice surgeons using global movement features.     

Dry box training with three‐dimensional vision for the assistant surgeon in robot‐assisted urological surgery

We analyzed whether three‐dimensional vision, practice or previous laparoscopic experience improves the surgical performance of the bedside assistant during robot‐assisted surgery. Six experienced laparoscopic surgeons and 15 novices carried out three skills drills imitating an assistant's maneuvers in robot‐assisted surgery, and times for completing the tasks were recorded. Both the novice and experienced groups showed significantly shorter manipulation times for each drill with three‐dimensional vision compared with two‐dimensional or glassless three‐dimensional vision. The experienced group showed significantly shorter manipulation times than the novice group for all types of vision. A significant improvement was observed 14 out of 18 times in the novice group, but only one out of 18 times in the experienced group. We can conclude that the use of three‐dimensional visualization facilitates the performance of the assistant surgeon, especially if a novice, during robot‐assisted surgery. Laparoscopic experience also improves the performance, whereas training is beneficial for novice assistant surgeons before carrying out actual operations.     

Comparison of lymph node yield in robot‐assisted laparoscopic prostatectomy with that in open radical retropubic prostatectomy

Study Type – Therapy (case series)
Level of Evidence 4

OBJECTIVE

? To investigate both the feasibility and the adequacy of pelvic lymph node dissection (PLND) during robot‐assisted laparoscopic prostatectomy (RALP) by comparing lymph node yields obtained during RALP with those obtained during traditional open retropubic radical prostatectomy (RRP).

PATIENTS AND METHODS

? We retrospectively reviewed 1047 patients who underwent radical prostatectomy between 2001 and 2009. ? In all, 626 patients underwent RALP while 421 patients had traditional open RRP. All patients undergoing bilateral PLND were included in our analysis. ? Lymph node yields and lymph node involvement for each surgical approach were calculated and examined. ? PLND‐related complications were analysed.

RESULTS

? Of the 1047 patients, 816 patients underwent bilateral PLND of whom 473 underwent RALP, while 343 underwent RRP. The mean lymph node yields for the RALP cohort (7.1, interquartile range 4–10) was significantly higher (P < 0.001) than for the RRP cohort (6.0, interquartile range 3–8). ? The percentage of patients with nodal involvement was 1.1 for RALP and 2.3 for RRP (P= 0.167). ? Mean age, preoperative PSA values, and pre‐ and postoperative Gleason scores were similar between the two cohorts. ? PLND‐related complications were similar between both cohorts.

CONCLUSIONS

? In patients undergoing RALP, PLND is feasible and provides lymph node yields comparable with those of the standard open approach. ? PLND should be strongly considered in all radical prostatectomy patients when clinically indicated, regardless of surgical technique.