Those anxieties materialized almost immediately. At the Colloquium’s first required session, held at the APA National Conference, she arrived late because her son had woken in the middle of the night with a fever and vomiting. She describes arriving bleary-eyed, monitoring every wave of nausea, and worrying that peers and mentors would dismiss her for her tardiness or fatigue, or worse, exclude her from the rest of the program. What she did not realize in that frantic morning, she later wrote, was that the episode marked the beginning of a longer process, one that would push her beyond the familiar language of “balancing” two lives and toward something more demanding and, ultimately, more sustainable: integrating them.

That process is now the subject of a first-person reflective article published in the journal Academic Psychiatry. The author, Melisa D. Granoff of Cambridge Health Alliance and Harvard Medical School, is a psychiatry resident pursuing research in perinatal psychiatry, the subspecialty focused on the mental health of people during pregnancy and the postpartum period. Her paper, part of the journal’s “Learner’s Voice” series, offers a rare, granular account of what it actually feels like to inhabit the roles of trainee, researcher, and mother simultaneously, and it argues that the prevailing metaphor of work-life balance may be fundamentally inadequate for describing the experience of physicians who are raising children while building careers in academic medicine.

The setting for her most vivid illustration was the annual meeting of the American College of Neuropsychopharmacology, the second of the three conferences required by the Colloquium. Granoff attended just three months after giving birth to her family’s third child, with her infant and husband in tow. She was there to present and discuss her own research on postpartum depression, a fitting assignment given her circumstances, but the trip became a live experiment in the collision of identities. Throughout the meeting, she writes, she grappled with the tension between her roles as academic psychiatrist and mother, eventually concluding that, despite her best efforts, inhabiting just one role at a time is not always possible.

The collision was sometimes startlingly physiological. In one session, she became engrossed in a peer’s presentation on the dysphoric milk ejection reflex, an understudied phenomenon in which lactating women experience a wave of dysphoria when milk lets down. This is precisely the kind of science, she notes, that draws her to research conferences in the first place: hearing peers present interesting and important work renews her sense of gratitude and excitement for the field. But the talk also triggered her own let-down reflex, physically pulling her out of the presentation and into a rapid-fire mental calculus. If she stayed, her shirt might be stained by the end. If she left, she would be disruptive. Did she have a spare shirt? Could she find her husband and daughter for an extra feeding, and would that mean the baby had eaten less earlier? She texted what she calls a nonsensical version of these worries to her husband under the table; he had wisely stayed close and was already en route with a replacement shirt.

The episode, she writes, delivered a stark physiologic reminder that the role of mother could not simply be checked at the door of a scientific meeting. For lactating attendees, the demands of the body do not pause for a plenary session, and the mental load of managing them, clothing, feeding schedules, logistics, runs concurrently with the cognitive work of attending to a talk. The anecdote is small, but it captures something that surveys of physician-parents have long suggested in aggregate: the infrastructure of professional life, from conference schedules to presentation norms, has largely been built around an assumption that participants are unencumbered by caregiving, and that assumption quietly shapes who can fully participate.

A second encounter at the same meeting, however, pointed toward what integration might look like when the environment supports it. The next morning, Granoff stood with her stroller in a carpeted area between meeting rooms, scanning for a familiar face while trying to appear casually interested in breakfast pastries and wall decor. She made eye contact with the chair of her own department. As a resident she had had little face time with him, though she knew his reputation as friendly and welcoming, and she also knew she was attending the conference while on maternity leave, a leave whose negotiation with her residency program had been challenging. She tentatively walked over. He greeted her and her daughter warmly, and then, despite her anxieties about how she might be perceived as a mother at the meeting, the baby did not remain the topic of conversation. They discussed which talks they each wanted to attend, and then her research on postpartum depression. He expressed gratitude for her work and suggested people she should talk to.

That brief exchange, Granoff argues, was substantively different from mere tolerance. It focused on her contributions as a researcher and served to validate her emerging professional identity as it exists alongside, rather than secondary to, her identity as a mother. In institutional terms, the moment illustrates a principle that researchers studying physician wellbeing have emphasized for years: supportive mentorship is not just about scheduling flexibility but about signaling that caregiving responsibilities and scholarly ambition are not in competition. A department chair who engages a postpartum resident as a scientist first, without erasing or ignoring the stroller beside her, performs a kind of cultural work that formal policies alone cannot accomplish.

The article also raises a subtler professional question that Granoff confronts head-on: the boundary between interest in a topic and self-involvement. By choosing to train to treat pregnant and postpartum patients, and to research how to better serve that population, while being a pregnant and postpartum person herself, she occupies one of the most delicate positions in psychiatry. Clinicians who share lived experience with their patients must constantly calibrate how much of themselves they bring into the room and into the research design. Her resolution is not to police the boundary more tightly but to reframe it: her decision to continue this work, she writes, is ultimately an expression of love for it, and proximity to the subject is part of what makes her scholarship authentic.

The broader significance of the piece lies in its argument about language and norms. “Balance” implies two things held apart on a scale, forever trading weight against each other; “integration” implies a single life in which professional and personal identities coexist, sometimes messily, in the same rooms and the same moments. By choosing integration over division, Granoff writes, her presence at that conference and at many others, with the three children she has had during medical training, was a vital step toward becoming an authentic and effective leader, and toward normalizing the full, complex integration of life and scholarship. For the institutions that train physicians, the lesson is concrete: when learners bring their whole selves to scientific meetings, the response they receive, dismissal or genuine professional engagement, may shape not only one career but the culture of academic medicine itself.

Subject of Research: Negotiating maternal and professional identities among physician-trainees in academic psychiatry

Article Title: Choosing Integration: Negotiating Professional and Maternal Identities in Academic Psychiatry

Article References: Granoff, M. D. (2026). Choosing Integration: Negotiating Professional and Maternal Identities in Academic Psychiatry. Academic Psychiatry. https://doi.org/10.1007/s40596-026-02428-3

Image Credits: AI Generated

DOI: 10.1007/s40596-026-02428-3

Keywords: academic psychiatry, perinatal psychiatry, physician mothers, work-life integration, maternity leave, medical training, postpartum depression, mentorship, professional identity, residency, APA Research Colloquium, gender in medicine

The peg transfer task is deceptively simple to describe. Using a pair of laparoscopic graspers, a trainee must pick up small objects, transfer them between the left and right instruments, and place them on a pegboard, all while viewing the field only through a camera that removes natural depth perception. Speed and precision both matter, and expert raters have long used the task to distinguish novices from seasoned minimally invasive surgeons. Previous research has established that simulator performance on FLS tasks predicts intraoperative laparoscopic skill, which is precisely why the program carries such weight in certification. But the same research literature has also documented how resource-intensive human assessment can be, motivating a decades-long search for automated, objective measures of surgical motion, from early motion-analysis studies to modern deep learning approaches that interpret surgical video directly.

To build their dataset, the researchers recorded general surgery residents and medical students at an academic medical center performing the peg transfer task on camera. In total, 132 videos were captured. Two adjudicators then independently scored each recording as beginner, intermediate, or expert, basing their judgments on task duration and the perceived technical quality of the performance. This human labeling step is crucial: in supervised machine learning, the algorithm can only be as good as the ground truth it learns from, and the use of two independent adjudicators helps ensure the labels reflect genuine consensus about skill level rather than one rater’s idiosyncrasies. Of the 132 recordings, 100 were ultimately used for analysis, while 32 were excluded because of tracking dropout, a reminder that even mature computer vision systems can lose track of instruments when visibility degrades or movements become ambiguous.

Technically, the pipeline rests on several components that have become standard tools in modern computer vision. The team used Ultralytics YOLOv8 for object detection, identifying and localizing the laparoscopic instruments frame by frame, and paired it with ByteTrack, a multi-object tracking algorithm that associates detection boxes across consecutive frames to maintain consistent identities for each instrument through time. From these tracked trajectories, the system extracted three quantitative input features: task duration, instrument path length, and peg displacement. These features distill an entire performance into the quantities that surgical educators have long recognized as meaningful. Shorter completion times and shorter instrument travel distances have historically correlated with higher technical skill, while peg displacement captures the physical consequences of the surgeon’s actions on the training board itself. A gradient boosting classifier, LightGBM, then mapped these features to skill level labels.

The model was trained under five-fold cross-validation, a rigorous scheme in which the data are split into five subsets and the model is repeatedly trained on four while being tested on the fifth, so that every recording serves as an unseen test case. The results were strong. Overall classification accuracy reached 84 percent, and, notably, the model made almost no beginner-to-expert misclassifications, meaning it essentially never confused the least skilled performers with the most skilled ones. The macro-averaged area under the curve, a measure of the model’s ability to discriminate across classes, came in at 0.907 plus or minus 0.061. Broken down by class, the AUC was 0.971 for beginners, 0.850 for intermediates, and 0.900 for experts, indicating that the extremes of the skill spectrum were the easiest to identify while the middle category, as is often the case in ordinal classification problems, posed the greatest challenge.

A threshold-based variant of the classifier, which converts the model’s probability outputs into hard class assignments, achieved a macro F1-score of 0.83 and, strikingly, a precision of 0.96 when identifying experts. In practical terms, when the system declares a performance expert-level, it is right nearly every time. That property matters for real-world deployment in surgical education. A tool that occasionally under-recognizes an intermediate performer but almost never inflates a novice to expert status is far safer for high-stakes feedback than one with symmetric error rates. The authors suggest that their AI-enabled computer vision model may offer a scalable supplement to traditional expert-based evaluation, potentially increasing opportunities for trainee feedback without adding to faculty workload.

The significance of that scalability claim becomes clear when considering the structure of American surgical training. Because successful FLS completion is a prerequisite for board qualification, residents across the country must prepare for and pass the exam, and studies have shown that doing so improves operative performance and autonomy while boosting junior residents’ self-efficacy. Yet feedback during preparation typically requires a faculty surgeon to watch practice runs, an expensive use of attending physician time that caps the frequency of assessment. A vision-based system that can watch unlimited repetitions and deliver consistent, quantified scores could allow residents to practice more deliberately, tracking their trajectory from beginner toward expert using objective metrics rather than intermittent impressions. The authors argue that implementing such AI-enabled assessment systems may enhance the accessibility of feedback and promote technical skill development across training programs, not just at well-resourced academic centers.

The study also situates itself within a rapidly expanding body of work on artificial intelligence in surgery. A 2024 review in Nature Medicine charted the broad scope of AI applications across the surgical lifecycle, and recent projects have applied deep learning to simulated laparoscopic skill assessment, video-based formative and summative evaluation of surgical tasks, and competency gauging on novel laparoscopic training systems. Earlier efforts demonstrated that 3D convolutional neural networks could assess skill directly from raw video, while other teams built software-based motion tracking tools for the surgical skills assessment landscape. What distinguishes the new UCLA approach is its deliberate parsimony: rather than feeding entire video streams into a heavyweight neural network, the researchers reduced each performance to three interpretable features derived from instrument tracking. This design choice makes the model’s decisions easier to audit and explain to educators, an important consideration as AI tools move closer to credentialing processes.

The choice of features also connects the work to foundational research in surgical education. Landmark studies by Datta and colleagues at Imperial College showed decades ago that motion analysis metrics correlate strongly with expert technical assessments, and randomized trials demonstrated that FLS simulator training to proficiency translates into improved laparoscopic performance in the operating room. By automating the extraction of duration, path length, and displacement, the new system operationalizes those validated constructs at scale, converting what once required laboratory motion-tracking equipment into something achievable with a standard camera and open-source detection and tracking software. The exclusions for tracking dropout, however, highlight remaining engineering challenges: lighting, camera angle, occlusion, and instrument visibility all still influence whether the pipeline can reliably follow tools through a complete performance.

The research team, led by corresponding author Terrance Peng of UCLA and including collaborators from Cedars-Sinai Medical Center, reports no conflicts of interest related to the project. The authors caution that their model was developed and validated on recordings from a single academic medical center, and broader validation across institutions, camera setups, and trainee populations will be needed before such systems can assume a formal role in summative assessment. Privacy considerations also shape the field: the video recordings generated for the study are not publicly available, with additional data available only on reasonable request. Still, the trajectory of the results, 84 percent accuracy, near-zero confusion between skill extremes, and 96 percent expert precision, suggests that AI-assisted surgical assessment is moving from proof-of-concept toward practical tool. If future systems match this performance in everyday training environments, the hours faculty spend watching peg transfers could be redirected toward higher-value teaching, while residents gain the luxury of feedback after every single repetition, a shift that could quietly reshape how the next generation of surgeons learns to operate.

Subject of Research: Artificial intelligence-based computer vision assessment of laparoscopic surgical skill on the FLS peg transfer task

Article Title: Artificial intelligence-enabled evaluation of laparoscopic peg transfer performance

Article References: Peng, T., Alipour, A., Desai, K., Chen, D., Huang, G., Rosenthal, R. J., Barmparas, G., Chen, Y., & Benharash, P. (2026). Artificial intelligence-enabled evaluation of laparoscopic peg transfer performance. Global Surgical Education – Journal of the Association for Surgical Education, 5(1), Article 173. https://doi.org/10.1007/s44186-026-00580-w

Image Credits: AI Generated

DOI: 10.1007/s44186-026-00580-w

Keywords: artificial intelligence, computer vision, laparoscopic surgery, surgical education, FLS, peg transfer, skills assessment, machine learning, surgical training, object detection, YOLOv8, residency