Although conventional laparoscopic surgery (CLS) allows more rapid postoperative recovery and has superior cosmetic outcomes compared with open laparotomy, CLS has several technical drawbacks [1] including a limited range of motion of instruments and related loss of dexterity, fixed instrument tips, and an inadequate visual field associated with an unstable camera view and assistant traction [2]. The introduction of robot-assisted laparoscopic surgery (RLS) was expected to open new avenues through its potential to overcome the drawbacks of CLS as a result of better ergonomics and enhanced dexterity with tremor filtration, numerous instrumental tips for the EndoWrist instrument, and 3D optical systems [3, 4]. Due to these advances, there is encouraging emerging evidence supporting RLS as an alternative technique to CLS.

In spite of the aforementioned advantages of RLS there are several controversial aspects of this approach, such as operative time, blood loss, conversion rate, complication rate, length of hospital stay, and operative cost. Numerous studies have reported clinical outcomes with regard to these aspects, and meta-analyses have assessed the pros and cons of robotics in various departments, including surgery, urology, and gynecology [5–14]. However, robotics is a relatively new surgical approach and RCT data have only recently become commonly available. Thus, there is a limited number of RCTs on each surgical procedure [3], and the lack of robust clinical evidence has frequently been emphasized [4, 15]. On incorporating all surgical procedures; previous statistically nonsignificant results due to limited RCT evidence for individual surgical procedure, may become statistically significant because of greater statistical power.

The scope of meta-analyses exclusively on RCTs [1, 16, 17] considers only a specific surgical procedure to convey more homogenous statistical results, compared to the that of a meta-analysis across surgical procedures [18]. However, the intrinsic properties of robotic instruments throughout overall surgical procedures could be mistakenly reported as the results of the unique properties of the particular surgical procedure. In contrast, the scope of meta-analysis [18] has been enlarged to combine RCTs across surgical procedures. Nonetheless, this regrettably omitted, among others, cholecystectomy and did not present forest plots with subgroup analyses. The forest plots with subgroup analysis of each surgical procedure intuitively would embrace the need for further floods of separate meta-analysis for each surgical procedure and encourage the combined discussion on the surgical robotics across surgical procedures. Our effort for integrating the previous individual studies and meta-analyses aims to provide the basis to statistically weigh the effectiveness and efficacy of surgical robotic instruments in controversial fields on surgical procedures both overall and on each individual surgical procedure.

This review provides a comprehensive comparison between RLS and CLS based on RCT studies in order to investigate the general trend of treatment outcomes for the controversial aspects of these approaches. Besides, the forest plots with subgroup analysis provide necessary information not only to investigate the comparison of treatment outcomes from the unique properties of the particular surgical procedure, but also to facilitate a more combined discussion from experts across various surgical procedures. From the statistical findings, it is concluded that despite its higher cost, RLS does not result in statistically improved treatment outcomes, with the exception of a lower EBL. Rather, Total-OT, Net-OT, and Total-Cx significantly favor CLS.

Because of the greater statistical power attained by integrating relevant RCT evidences, this study is able to report that, for example, Total-OT and Net-OT are significantly lower for CLS, although Liao et al. [10] and Albright et al. [16] reported that the operative time was insignificantly lower in CLS based on RCT evidence. Xiong et al. and Chuan et al. attributed the lower EBL of RLS to the use of robotic devices that provided better stability and avoided the damage caused by shaking hands in CLS and provided a greater field of view for detection of both large and small vessels [6, 57].

Clinical heterogeneity introduced by integrating various surgical procedures may contribute to the deviation from previous meta-analyses findings, presumably reflecting the intrinsic properties of each surgical procedure such as retroperitoneal involvement of prostatectomy [58]. The subgroup analyses favoring RLS on Conv on colectomy and LOHS on hysterectomy could be reasoned in association with properties of surgical robotics as follows: Lin et al. proposed that a lower Conv may be attributed to superior exposure and visualization of the operating field [3]. Ran et al. report that RLS was superior to CLS in terms of EBL and Conv, and proposed that the increased precision and dexterity of robotic platforms may contribute to these findings [7]. Chuan et al. reported that RLS was superior to CLS in terms of LOHS, and proposed that the more subtle operative technique and reduced level of invasiveness may be responsible for their findings [6]. Regarding Conv, surgeons might try a new surgical technology on a relatively less complicated surgery, which possibly distorts the outcome and results in inconsistent statistical significance. Thus, in consideration of the level of difficulties encountered in different surgeries, it may remain to be seen whether Conv would support RLS when more data are accumulated.

The present study stems from the motivation to contribute to the advancement in meta-analysis on surgical robotics by listing the limitations, followed by preliminary suggestions, if possible. Firstly, as pointed out by O’Neill et al. [4], some studies did not indicate explicitly whether the docking time for RLS was included in the operative time. The main cause of this confusion lies in the absence of standard ways of comparing operative time between the two groups. Some articles do not explicitly describe specifically how the RLS operative time—which can be broken into several pieces such as skin-to-skin, robot set-up time, etc.—was measured. Furthermore, although some original articles set strict rules for measuring operative time, unfortunately the terminology differs across studies, for example, "Operation time" [35], "Net operating time" [23], "Procedure" [25], “Dissection time” [41, 46], "skin-to-skin time" [38], "Effective operative time" [39], etc. These differences in terminology create additional difficulties in identifying the actual operative time. In this regard, for this study we chose to use “Net operative time,” which is intuitively different from “Total operative time”.

Secondly, the difference of indications across studies could have resulted in the inclusion of patients from each study variable. For example, in addition to the apparent discrepancy between the patient's conditions and clinical indications, not all the critical criteria of one study [58] could be possibly matched and compared against those of another study [47], due to insufficient information. In this regard, one study acknowledged that “[t]he different inclusion criteria and surgical techniques could potentially justify the differences between these results” [47]. Thus, please be aware of the limitation imposed by heterogeneities, which diminished the significance of the statistical results of weighing advantages and disadvantages.

Thirdly, none of the studies evaluated the degree of surgeon proficiency between RLS and CLS in the face of a new technology like robotics with an established technology like laparoscopy. According to Finkelstein et al., “to become proficient at [laparoscopic radical prostatectomy] or [robotic-assisted laparoscopic radical prostatectomy], […] a surgeon must perform anywhere from 8 to 12 cases to as many as 200 cases” [59]. In this regard, it may be worth taking into account surgeon experience, for example, number of surgeries, before comparing other aspects of a surgery.

Finally, whenever standard deviations were not available, imputations of the standard deviations were conducted. Although it is reported that “imputing missing standard deviations in meta-analyses can provide accurate results” [22], awareness of this limitation should be noted. It is proposed that future studies should be encouraged to report standard deviations whenever possible.