Category Archives: Surgical Training

Schematic of process for classifier design

Guest blog: 21st century surgery is digital

Ronan Cahill, Digital Surgery Unit, Mater Misericordiae University Hospital, Dublin, Ireland and UCD Centre for Precision Surgery, Dublin, Ireland.

Niall Hardy, UCD Centre for Precision Surgery, Dublin, Ireland.

Pol MacAonghusa, IBM Research, Dublin, Ireland.

Twitter @matersurgery Email: ronan.cahill@ucd.ie

Cancerous tissue behaves differently from non-cancerous tissue. Every academic oncology paper ever written tells us this. The appearances of any cancer primary (or indeed secondary lesion) result from biological and molecular processes that are the hallmarks of malignancy including dysregulated cell function and composition, host-cancer stromal and inflammatory response and angiogenesis. However, we surgeons haven’t really yet been able to exploit this knowledge during surgery in a way that helps us make a better operation. Instead, our learning and research about oncological cellular processes has predominantly advanced through basic science geared more towards perioperative prognostication and/or adjuvant therapy stratification. Wouldn’t it be great if realisation of cancer microprocesses could usefully inform decision-making intraoperatively?

We’ve just published an initial report in the BJS showing this very thing – that it is indeed possible to ‘see’ cancer by its behaviour in real-time intraoperatively. We’ve used Artificial Intelligence (AI) methods in combination with near-infrared fluorescence laparoendoscopy to judge and classify neoplastic tissue nature through the observation of differential dye diffusion through the region of interest in comparison with that happening in normal tissue being viewed alongside it. Through our understanding of biophysics (flow parameters and light/dye interaction properties), a lot of information can be drawn out over short periods of times via advanced computer vision methodology. With surgical video recording in the region of 30 frames per second, big data generates over the time frame of a few minutes.  While the gross signal shifts are discernible even without AI, smart machine learning capabilities certainly mean their interrogation becomes really usable in the provision of classification data within moments. What’s more, while we’ve focused initially on colorectal cancer, the processes we are exploiting seem common across other solid cancers and using other camera-based imaging systems. By combining with the considerable amount of knowledge we already have accrued regarding tissue biology, chemistry, physics as relate and indeed surgery, our AI methods are giving explainable and more importantly interpretable recommendations with confidence using a smaller dataset than that demanded by deep learning methodologies.

This though is just an early exemplar of what’s becoming possible through ‘Digital Surgery’, a concept that seems far more likely to transform contemporary surgical practice than our current general surgery “robotic” systems, hulking electromechanical tools entirely dependent on the user – a rather 20th century concept! Indeed, there is sophisticated technology everywhere in today’s operating theatres – surgeons sure don’t lack technical capability. Yet often despite vaulting costs, advance of real, value-based outcomes has been disappointingly marginal in comparison over the last two decades. The key bit for evolved surgery is instead going to be assisting surgeons to make the best decision possible for each individual patient by providing useful, discerning information regarding the surgery happening right now, and somehow plugging this case circumstances directly into the broad knowledge bank of expertise we have accrued as a profession (and not just be dependent on any single surgeon’s own experience).

To do this we need to realise the importance of visualisation in surgical procedures versus manual dexterity.  All surgery is performed through the visual interpretation of tissue appearances and proceeds via the perception-action cycle (‘sense, predict, act, adjust’). This is most evident during minimally invasive operations where a camera is used to display internal images on a screen but applies of course to open procedures as well. As all intraoperative decisions are made by the surgeon, the entire purpose of surgical imaging has been to present the best (‘most visually appealing’) picture to the surgeon for this purpose. Experiential surgical training is for the purpose of developing the ‘surgical eye’, that is learning how to make qualitative intraoperative judgments reliably to a reasonable standard. We haven’t however gotten the most out of the computer attached to the camera beyond image processing where we have concerned ourselves with display resolutions and widths. 

Imagine instead if some useful added interpretations of images could be made without adding extra cognitive burden to the surgeon, perhaps with straightforward on-screen prompts to better personalise decisions? This would be particularly exciting if these data were not otherwise easily realisable by human cognition alone and could be immediately and directly relevant to the person undergoing the operation. Every operation is in effect a unique undertaking, informed by probabilities accruing through individual and collected prior experience for sure but a new thing in and of itself for which the outcome at the time of its performance is unknown. How this individual patient differs from others and most especially how might an adverse outcome be avoided is a crucial thing to flag before any irreversible surgical step that commits an inevitable future. 

Right now, we are in a golden age of imaging. This is intricately linked to advances in computer processing and sharing power along with AI methods. This means we can harvest great additional information from the natural world around us across the spectrum of enormous (radio waves spanning the universe) to tiny (high resolution atomic imaging) distances and apply methods to help crystalise what this means to the observer. While a lot of AI is being directed at the easier and safer areas of standard patient cohort datasets, increasingly it’s possible to apply computer intelligence to the data rich surgical video feeds being generated routinely during operations to present insights to the surgeon. While early first steps at the moment relate to rather bread and butter applications such as instrument or lesion recognition and tracking as well as digital subtraction of smoke or anonymization protocols to prevent inadvertent capture of operating rooms teams when the camera is outside the patient, soon the capability to parse, segment and foretell likely best next operative steps will be possible at scale.

At present, the biggest limitation is that surgery lacks large warehoused archives of annotated imagery because operative video is a more complex dataset to scrutinise than the narrower image datasets available in specialities such as radiology, pathology and ophthalmology. Thanks to advances in computing, this is changing. Surgical video aggregation to enable building of representative cohorts is increasingly possible and, by combining with metadata and surgical insights, its full value can begin to be realised. GDPR frameworks provide structure and surgeons are increasingly understanding of the value of collaborating in research, education and practice development. However, while certain siloed sites focused around specific industry projects are already manifesting, the key area for greatest general advance lies within the surgical community combining broadly to construct appropriately developed and secured, curated video banks of procedures that can then be made accessible to entities from regulators and standard bodies, academia and indeed corporations capable of advancing surgery. This gives by far the greatest chance of the best of surgical traditions carrying through the 21st century while our weak spots are fortified for better surgery in the public interest.

Further reading: 
Artificial intelligence indocyanine green (ICG) perfusion for colorectal cancer intra-operative tissue classification.
 Cahill RA, O’Shea DF, Khan MF, Khokhar HA, Epperlein JP, Mac Aonghusa PG, Nair R, Zhuk SM.Br J Surg. 2021 Jan 27;108(1):5-9. https://doi.org/10.1093/bjs/znaa004 PMID: 33640921 

The age of surgical operative video big data – My bicycle or our park? Cahill RA, MacAonghusa P, Mortensen N. The Surgeon 2021 Epub ahead of press https://doi.org/10.1016/j.surge.2021.03.006

Ways of seeing – it’s all in the image. Cahill RA. Colorectal Dis. 2018 Jun;20(6):467-468. https://doi.org/10.1111/codi.14265 PMID: 29864253

Senior surgeon training junior surgeon in laparoscopy

Guest post: The Great Danes? Surgical training on a 37-hour week

By Mr Henry G Smith MBBS MRCS PhD, specialist registrar at The Digestive Disease Center, Bispebjerg Hospital, University of Copenhagen

The number of hours in training that it takes for a surgical trainee to achieve both clinical and technical competence is a seemingly endless topic of debate. The significant global
variation in a surgical trainee’s average hourly week begs the question as to why such variation exists and to what extent all training programmes are created equal (1). Given the increasing recognition of burnout amongst medical professionals, and its association with excessive workloads, it is reasonable to think a shorter working week may benefit the surgical trainee’s wellbeing (2). However, any potential benefits much be weighed against the risk of reducing training opportunities and clinical exposure. Having personal experience of both British, with its nominal 48-hour working week, and Danish general surgical training, where surgeons work a 37-hour week, it is clear that whilst these countries have very similar healthcare systems, they differ markedly in their approach to training. Whilst neither training programme is without its limitations, their differences highlight potential ways in which the efficiency of surgical training may be improved.

The most striking difference between the British and Danish programmes is the absence of the ‘firm’ structure in Denmark. Trainees belong to the department rather than to subspeciality specific teams. The same is true of acutely admitted patients, who whilst broadly divided into those with upper and lower gastrointestinal conditions are not ‘owned’ by the consultant who was on call at the time of admission. As a consequence, there are no ward rounds, post-take or otherwise. Instead, the acute and elective inpatients are divided more or less equally between consultants and trainees alike, with a typical ratio of 2-3 patients to be seen by a single doctor each day. The lack of a rigid structure dictated by a team-based ward round leads to much greater flexibility in all other aspects of the working day. These days are thematic, with trainees having 4 major functions: elective operations, endoscopy, outpatient clinics and on-calls. When a trainee is not assigned to one of these functions, they have zero hours to be used as they see fit.

The flexibility of the Danish system brings two major advantages. The first is that the structure leaves the trainee with the feeling that the majority of time spent at work is spent training. That feeling is emphasised by the organisation of the operating days in particular.

Whilst the trainee spends undoubtedly fewer days in an elective theatre than in the British system, these days are almost exclusively spent attending training lists. Attended by a single trainee and a consultant, comprising repeated exposure to the same operation and booked on the presumption that the trainee will be the primary surgeon, these lists maximise training opportunities. The same is more or less true in endoscopy, where the trainee has their own full day list, with a supervisor on hand if needed. The second advantage is that the planning of absence from work for annual leave, courses or conferences is far less complicated. The minimum number of trainees required at work is determined at a departmental level, avoiding the need to organise cross cover between firms. As such, denied requests to attend conferences are very much the exception rather than the rule and it is almost unheard of that a trainee would be unable to take all of their allocated leave during a rotation.

These structural differences are accompanied by an in-house culture that not only prioritises training but is also ferocious in its defence of working conditions. There is a greater expectation for trainees to be actively involved, at least in part, in the majority of operations, and independent operating is encouraged at a much earlier stage. Senior house officers are expected to be capable of independently performing common acute operations, such as appendicectomies, and whilst consultants are often present for laparotomies, their presence is not compulsory. ‘Service provision’ is rarely mentioned, perhaps a reflection of a healthcare system that is better resourced to match the demands of its population. With regard to the working environment, trainees hold a structured monthly meeting for both positive and negative feedback on issues ranging from training opportunities and supervision to the frequency of on-call duties and conditions of the on-call rooms. The vocal complaints in a recent meeting of the comfiness of the on-call beds are not only a far cry from trying to catch some rest on an old sofa in a British hospital mess but also give an insight into how seriously the Danes take their working conditions.

However, not all the differences are positive. The greater flexibility in the Danish system
places greater demands on the discipline of its trainees. Although there are still dedicated
rotations in trauma and tertiary centres, the lack of other subspecialty specific rotations
means that the trainee must take more responsibility for ensuring that they meet the specific requirements of the training programme. Whilst focused trainees may turn this to their advantage, allowing them to focus on their preferred subspecialty at an earlier stage of training, those who are as of yet undecided may be at risk of drifting in a less structured system. In a similar vein, for a trainee raised in the British system, the absence of the firm structure is accompanied by a sense of a lack of belonging, at least at the beginning of a new placement, although this is somewhat lessened by the daily morning conferences, attended by the whole department. A further concern is the consequences a more flexible system has on the quality and continuity of care. It is not uncommon for acutely admitted patients to be seen by a different doctor each day, a situation commonly thought to increase the risk of delays in discharge or investigations. However, this does not appear to have an adverse effect on patient outcomes, with a 30-day mortality following high-risk laparotomies of approximately 20% in Denmark, mirroring the reports from the National Emergency Laparotomy Audit (NELA) in Britain (3-5). Finally, one must remember that achieving competence as a surgeon is not only about developing technical skills. As the old saying goes “good surgeons know how to operate, better surgeons know when to operate, and the best surgeons know when not to operate”. Although the Danes may have a more efficient approach to the technical aspects of training, it is undeniable that the clinical exposure of British trainees is far greater. The cumulative clinical experience of following both elective and acute patients from admission to discharge is difficult to replicate and whilst any differences in decision-making seem to have disappeared by the end of training, these skills appear to develop more rapidly in the British systems. Disruptions to the continuity of care present another barrier for clinical exposure in the Danish system, with the following up of the patients seen on-call or in the operating theatre left to the trainee’s own initiative.

The hourly week occupies much of the debate on surgical training and, in doing so,
prioritises quantity over quality of training. With a focus on maximising the efficacy of
training opportunities, the Danish surgical training system demonstrates how surgeons can be effectively trained on a shorter working week. Whilst this system has its own limitations, the organisation of a trainee’s operative commitments in particular provides an example for other systems to follow. Surgical training faces major challenges ahead, with a global pandemic that has not only limited training opportunities but also taken an inevitable toll on workforce morale (6). Furthermore, the backlog of operations cancelled since the beginning of the pandemic is likely to place a huge emphasis on efficiency in operating theatres, which may have further negative effects on training opportunities (7-8). However, the return of some degree of normality will also offer the opportunity to reconsider the structure of training and perhaps in doing so, the best aspects of these respective training systems could be combined, shifting the focus away from the number of hours spent at work to the amount of time spent training.

References

  1. Jackson GP, Tarpley J. How long does it take to train a surgeon? British Medical
    Journal. 2009, 5;339:b4260.
  2. Galaiya R, Kinross J, Arulampalam T. Factors associated with burnout syndromes in
    surgeons: a systematic review. Annals of the Royal College of Surgeons of England.
    2020, 102(6):401-407.
  3. Cihoric M, Tengberg LT, Foss NB, et al. Functional performance and 30-day post-
    operative mortality after emergency laparotomy – a retrospective, multicenter,
    observational cohort study of 1084 patients. Perioperative Medicine. 2020, 9(13).
  4. Peacock O , Bassett M G, Kuryba A, et al., National Emergency Laparotomy Audit (NELA) Project Team. Thirty-day mortality in patients undergoing laparotomy for small bowel obstruction. Br J Sur. 2018 Jul;105(8):1006-1013. doi: 10.1002/bjs.10812. Epub 2018 Mar 30
  5. Boyd-Carson H, Doleman B, Herrod P J J, et al., on behalf of the NELA Collaboration, Association between surgeon special interest and mortality after emergency laparotomy, British Journal of Surgery, Volume 106, Issue 7, June 2019, Pages 940–948, https://doi.org/10.1002/bjs.11146
  6. COVIDSurg Collaborative. Elective surgery cancellations due to the COVID-19 pandemic: global predictive modelling to inform surgical recovery plans. Br J Surg. 2020;107(11):1440-1449. doi:10.1002/bjs.11746
  7. Rai O, Fernandes R. COVID-19 and the reintroduction of surgical training. British Journal of Surgery, Volume 108, Issue 1, January 2021, Page e6, https://doi.org/10.1093/bjs/znaa003
  8. Hennessy O, Fowler A L, Hennessy C, et al. Covid 19 and Surgical training: Carpe Diem. British Journal of Surgery, Volume 107, Issue 12, November 2020, Page e591, https://doi.org/10.1002/bjs.12032