Citations

Abstract Background: Spatial Reasoning AI (SRAI) systems are emerging as a transformative class of clinical artificial intelligence, enabling real-time interpretation of complex anatomy in imaging, surgery, and chronic disease management. Unlike traditional AI approaches constrained to tabular or 2D inputs, SRAI models incorporate geometric priors, multimodal fusion, and 3D anatomical reasoning to support high-impact tasks such as volumetric segmentation, lesion localization, intraoperative guidance, and prognostic modeling. Objective: This scoping review aimed to (1) map the emerging landscape of SRAI in healthcare, (2) assess its clinical performance across diagnostic, prognostic, and workflow applications, and (3) identify opportunities and barriers for safe translation into practice. Methods: Following PRISMA 2020 guidelines, we systematically searched PubMed, Springer Nature, and IEEE Xplore (including CVPR, ICCV, ISBI, and EMBC) for original studies implementing spatially aware AI models with clinical validation or workflow relevance. Data extraction captured model architecture, input modality, anatomical scope, application domain, and performance outcomes. Results: We identified eligible studies spanning oncology, neurology, cardiology, surgery, and infectious diseases. SRAI systems consistently outperformed conventional methods in segmentation, lesion classification, and risk stratification. A paradigm shift is underway from task-specific CNNs to foundation-level models, including MedSAM and MedCLIP for zero-shot segmentation and retrieval, and NeRF-based pipelines for anatomically faithful 3D reconstruction. Randomized evidence shows that SRAI can improve workflow efficiency without compromising diagnostic accuracy. Conclusion: SRAI models demonstrate strong potential to advance diagnostic precision, prognostic accuracy, and workflow integration across multiple clinical domains. Their safe adoption will require standardized evaluation metrics, prospective multi-institutional validation, and interpretable outputs. As foundation models evolve to better encode spatial priors, SRAI is poised to become a cornerstone of workflow-integrated precision medicine.

Objectives: Current standard of care after a First-Time patellar instability event is non-operative management, with exceptions for patients with osteochondral fracture or loose body requiring immediate surgical intervention, patients with significant pathoanatomy, or contralateral patellar instability. For recurrent patellar instability, there is controversy as to when isolated medial patellofemoral ligament reconstruction (MPFL-R) is enough. The purpose of this study is to determine (1) the comparative outcomes of isolated MPFL-R after first-time patellar instability (FTPI) and recurrent patellar instability (RPI) and (2) the impact of osteochondral injury on outcomes after surgical treatment of FTPI. Methods: A prospective, multicenter cohort study (JUPITER: Justifying Patellar Instability Treatment by Results) database was queried for patients who underwent patellar stabilization surgery (PSS) between December 2016 and September 2022. Patients were included if they underwent a medial patellofemoral ligament reconstruction (MPFL-R) for FTPI or RPI. Those with less than 2 years of clinical follow-up, revision PSS, or concomitant bony procedures at the time of MPFL-R were excluded. Independent t-tests were performed to compare means for continuous variables, and chi-squared tests were performed to compare frequency for categorical variables, between groups. Results: A total of 739 patients met inclusion criteria with a mean age of 15.6 ± 3.3 years, and 59.9% female sex. FTPI occurred in 216 (27.2%) patients, and of these 104 (48.1%) sustained an operative chondral or osteochondral lesion. Those with FTPI had a significantly greater trochlear depth (2.9 mm vs. 2.6 mm; P = .048), but a significantly lower rate of pathological trochlear bump > 5 mm (52.3% vs. 67.8%; P = .008) than those with RPI (Table 1). Among the FTPI cohort, those with treatment of a chondral lesion were less likely to have patella alta (Caton-Deschamps Index > 1.3) (14.9% vs. 41.3%, P = .006), and less frequently had a mild or severe J-sign (25.0% vs. 42.7%, p = .016) than those without a chondral intervention (Table 2). Postoperatively, there were no differences with rates of recurrent instability (8.3% vs. 12.3%; P = .130) or return to sport (90.4% vs. 94.5%; P = .182) between FTPI and RPI, respectively (Table 3). There were no differences with rates of recurrent instability (7.6% vs. 9.1%; P = .807) or return to sport (89.1% vs. 91.7%; P = .755) between those with or without a chondral intervention, respectively (Table 4). Conclusions: This study demonstrates no difference in rates of recurrent post-operative instability between FTPI and RPI with rates consistent with the current literature. MPFL reconstruction remains as a durable surgical treatment option for patients presenting with either FTPI or RPI with relatively low rates of recurrent instability. In this patient population, patella alta was found to be protective of osteochondral injury which is also consistent with existing literature. Continued, long-term investigation is needed to understand outcomes for First-Time patellar instability and to better define the indications for surgical interventions in this population.

Objectives: To evaluate return-to-sport (RTS) rates and patient reported outcome measures (PROMs) following hip arthroscopy for femoroacetabular impingement (FAI) in active football players with a minimum of 5-years follow-up. Methods: All active football players who underwent hip arthroscopy for FAI from 2010-2019 were identified. Preoperative radiographic measures including lateral center edge angle, Tönnis angle, alpha angle, and acetabular depth were obtained. Patients were evaluated for post-operative RTS and revision surgery data at final follow-up. Modified Harris Hip Score (mHHS), Hip Outcome Score (HOS), HOS Activities of Daily Living (HOS-ADL), HOS Sports Specific Subscale (HOS-Sports), Tegner Activity Scores, Visual Analogue Scale (VAS) for pain, and surgery satisfaction were collected at a minimum 5-year follow-up. Descriptive and comparative statistical analysis was performed using R software (version 4.4.1). Results: Sixty-six hips from 53 male patients were included. The mean age was 20.4 ± 6.4 years and mean BMI was 27.3 ± 6.6 kg/m² (Table 1). Mean follow-up was 8.7 ± 2.8 years. The majority (60%) were high school players and 19% were college players. Figure 1 displays the most commonly affected positions which included wide receiver (32%), defensive lineman (26%), and tight end or offensive lineman (16%). There were 11 bilateral cases and 2 revisions. The mean lateral center edge angle was 31.6º ± 6.4, the mean Tönnis angle was 5.0º ± 5, and the mean alpha angle was 63.2º ± 12.7. There was significant improvement in all PROMs from baseline to a minimum 5-year follow-up (p<0.04). Fifty-four percent of athletes returned to football postoperatively and the average overall surgery satisfaction rating was 8.1/10. Among those who didn’t return, 14% cited hip-related reasons, while 67% cited non-hip related reasons such as priorities changing or graduating (Figure 2). Athletes who returned to football had significantly higher mean HOS-ADL (p=0.049), HOS-Sport (p=0.042), and Tegner level before surgery (p=0.023) compared to those who did not return (Table 2). Conclusions: Football players undergoing hip arthroscopy for FAI demonstrate significant improvements in outcome scores at a minimum 5-year follow-up with a moderate return-to-sport rate. Athletes who are able to return to football report higher patient reported outcomes compared to those who do not. Player position may also influence incidence and outcomes. Although football players demonstrate significant improvements following hip arthroscopy, the moderate RTS rates highlights the demanding nature of the sport and need for improved perioperative counseling.

Objectives: Periacetabular osteotomy (PAO) is utilized for the treatment of hip dysplasia, with a growing trend towards hip arthroscopy at the time of PAO or in a planned, staged manner prior to PAO in order to address intra-articular pathology such as labral tears. For patients with persistent or new pain following isolated PAO, a subset undergo unplanned, primary hip arthroscopy. To date, there is a paucity of available evidence regarding the risk factors for and outcomes of unplanned hip arthroscopy for persistent or new pain after PAO. The purpose of this study was to determine demographic and radiographic characteristics of patients undergoing hip arthroscopy for persistent pain after PAO and also to compare radiographic parameters, surgical characteristics, and postoperative PROMs between patients that underwent hip arthroscopy following PAO and a demographically similar group of controls without acetabular dysplasia that underwent primary hip arthroscopy. Methods: An institutional database of 3014 hip arthroscopies performed between 1988 and 2022 was reviewed for patients having undergone unplanned (i.e. non-staged) first-time hip arthroscopy after PAO. These patients were propensity-matched on a 1:2 ratio with demographically similar, non-dysplastic patients undergoing primary hip arthroscopy with labral repair. All patients were contacted at final-follow-up to collect outcomes including subsequent procedures, progression to THA, and patient-reported outcome measures (PROMs), including modified Harris Hip Score (mHHS), Hip Outcome Score (HOS), International Hip Outcome Tool (iHOT), Tegner Activity Scores, Visual Analogue Scale (VAS) for pain, and surgery satisfaction. Demographics, radiographic characteristics, and postoperative outcomes were compared. All statistical analysis and Kaplan-Meier survival curve analysis was performed using R software (version 4.4.1). Results: We identified 22 hips in 21 patients (17 female, 4 male; age: 24.6 ± 8.5 years; BMI: 29.3 ± 7.4 kg/m²) who underwent first-time arthroscopy after ipsilateral PAO and were followed for a mean of 7.2 ± 2.8 years (Table 1). The median post-PAO LCEA was 28° (IQR: 24.6 – 31.7) and the mean Tönnis angle was 4.2° ± 5.9. The median time from the date of PAO to date of subsequent hip arthroscopy was 1.6 years (IQR: 1.1 - 3.4). Compared to the control group, there was a significantly lower rate of femoral osteochondroplasty (50% vs, 86%, p < 0.01), as well as trends towards lower rate of labral repair (77% vs. 95% p = 0.11), and higher rate of capsular repair (64% vs. 75%, p = 0.34). No differences were found between the PAO and control groups in any of the postoperative PROMs (Table 2). Among the PAO patients, 3 (20%) progressed to total hip arthroplasty (THA) compared to 1 (9%) in the control group (p=0.62). Conclusions: Hip arthroscopy after prior PAO was associated with postoperative improvements in pain and moderate rates of conversion to THA. When patients undergoing hip arthroscopy following PAO were compared to a demographically similar matched cohort of nondysplastic hips who underwent primary hip arthroscopy without a prior PAO, similar postoperative outcome scores were observed. This data provides valuable counselling information for clinicians discussing hip arthroscopy in the setting of patients with persistent pain following PAO.

Objectives: Historically, horizontal cleavage meniscus tears have been debrided with single leaflet preservation, but more recently this has been challenged by repair of these tear types. While circumferential meniscus repair with all-inside and inside-out instrumentation has been described, there remains a paucity of literature regarding the clinical outcomes of this technique. Our purpose was to assess clinical outcomes and reoperation rates of circumferential meniscus repair for horizontal cleavage tears at minimum 2-year follow-up. Methods: Patients with isolated horizontal cleavage tears of the meniscus (Fig. 1a) undergoing primary circumferential meniscus repair (Fig. 1b), including both inside-out and all-inside suturing techniques, at a single institution between 2015 and 2022 were eligible for inclusion and analyzed retrospectively. Arthroscopic images and operative notes were examined to confirm circumferential meniscal repair. Patient demographics, surgery details, and clinical findings were extracted from the institutional electronic medical records. Exclusion criteria consisted of patients not consenting for research, less than 2-years of clinical follow-up, and concurrent ipsilateral repair of a non-horizontal cleavage tear. Patients were not excluded if they had a concomitant anterior cruciate ligament reconstruction (ACLR). Thirty-seven patients met the criteria for inclusion in this study. Knees were analyzed for laterality, number of sutures, suturing technique, concurrent injuries, concurrent procedures, and surgical history. Visual Analogue Scale (VAS) for pain, Tegner, and International Knee Documentation Committee (IKDC) scores were collected at minimum 2-year follow-up and analyzed. Return to sport (RTS) and revision surgery were analyzed. Results: Thirty-seven patients (25 male, 12 female; mean age, 29.4 ± 12.4 years) who underwent circumferential meniscal repair of a horizontal cleavage tear were included in the study and followed for a mean of 6.2 years (range, 2.2-9.3 years, Table 1). There was a total of 38 knees (23 right, 15 left). One patient (3%) had bilateral circumferential meniscal repair surgeries done at separate times. Three (16%) patients failed primary repair and had secondary partial meniscectomy. Similar numbers of circumferential meniscal repairs were performed on lateral and medial menisci, 21 (55%) and 17 (45%), respectively. An average number of 3 ± 2 sutures were used at the time or repair with one of 38 menisci (3%) having a hybrid combination of both all-inside and inside-out suture technique, 24 menisci (63%) had all-inside technique, and 13 menisci (34%) had inside-out technique. Concurrent procedures included 4 ACL reconstructions (3 autograft, 1 allograft), and 8 chondroplasties (4 patella, 2 trochlea, 1 medial femoral condyle, and 1 unspecified, Table 2). At the time of final follow-up, patients reported mean Tegner activity scores of 6.2 ± 2.3, VAS pain with rest of 1.0 ± 2.0, VAS pain with use of 2.5 ± 2.7, and IKDC of 81.6 ± 18.6. When asked, using a VAS Five Point scale, how their knee is currently compared to before their surgery, 14 (74%) feel much better than before surgery, 2 (11%) feel slightly better than before surgery, 1 (5%) feels no change when compared to before their surgery, 2 (11%) feel slightly worse than before surgery, and no one felt much worse than before surgery. Sixteen patients were involved in sports before their surgery. Of those that played sports before their surgery, 14 (88%) returned to sport (Table 3). The most common sports played were hockey (19%), volleyball (19%), tennis (13%), and football (13%). Levels of sport played before surgery included 7 (44%) recreational, 6 (38%) high school, 2 (13%) college, and 1 (6%) club. Levels of sport played after surgery for those who returned to sport included 6 (43%) recreational, 2 (14%) high school, 5 (36%) college, and 1 (7%) club with a significant increase in levels of sport played after surgery ( p ≤ 0.006) compared to before surgery. Conclusions: At an average of 6-years of follow up, there was an 84% success rate of circumferential meniscal repair for horizontal cleavage tears. Most patients who play sports, return to sport and do so at the same or higher level and report successful PROMs. Circumferential meniscal repairs should be considered for patients with horizontal cleavage tears.

Objectives: Soccer is one of the most popular youth sports in the United States and worldwide. Due to growing concerns regarding repeated head trauma, in 2015 the United States Soccer Federation (USSF) banned headers for athletes aged 10 and under and limited athletes aged 11 to 13 to practicing headers for 30 minutes per week. The purpose of this study was to assess whether the USSF header policy was associated with fewer soccer-related concussions that presented to emergency departments following the 2015 season. Methods: A retrospective cohort from the National Electronic Injury Surveillance System database was assessed. Age, sex, and injury type were extracted for all soccer-related emergency department visits between January 1st, 2012, and December 31st, 2023. Univariate and multivariable regression analyses were conducted to assess concussions as a percentage of all soccer-related injuries based on sex, age, and year. Results: The number of concussions as a percentage of all soccer-related injuries decreased from 8.2% in 2012-2015 to 6.1% in 2020-2023 (p<0.01). From 2012-2023, the concussion rate among 14-17-year-olds and 10-13-year-olds was higher than 6-9-year-olds (8.9% and 6.6% compared to 4.9%, p<0.01). Despite a lower soccer-related injury rate overall, females were diagnosed with a greater proportion of concussions than males (9.6% compared to 6.2%, p<0.01). In a multivariable regression analysis, injuries that occurred in the years 2020-2023 were associated with lower odds of concussion compared to 2012-2015 (OR: 0.75, 95% CI: 0.69- 0.81). The 10-13-year-old age group, 14-17-year-old age group, and female sex were associated with higher odds of concussion compared to the 6-9-year-old age group and male sex respectively (OR: 1.30, 95% CI: 1.16- 1.45; OR: 1.79, 95% CI: 1.61- 1.99; OR: 1.53, 95% CI: 1.43- 1.63). Conclusions: The USSF youth soccer header policy introduced in 2015 was associated with a 25.6% relative risk reduction to sustain a soccer-related concussion and present to the emergency department in 2020-2023 compared to 2012-2015. A header ban in players under 10 years old and limitation to 30 minutes of header practice a week in players under 13 years old may improve player safety by reducing head impacts in the youth population.

Objectives: There is a paucity of research comparing the outcomes of medial ulnar collateral ligament (MUCL) repair with internal bracing to isolated MUCL reconstruction in professional baseball players. Further, the practice of supplementing a MUCL reconstruction with an internal brace, a "hybrid" reconstruction, has increased in the surgical treatment of MUCL injuries for professional baseball players, without any currently known published research defining the clinical outcomes of this modification. We sought to investigate the trends and outcomes of MUCL repair with internal bracing and "hybrid" MUCL reconstruction with internal bracing. Using a matched cohort analysis, we also sought to compare the clinical outcomes of both MUCL repair with internal bracing and "hybrid" MUCL reconstruction with internal bracing to isolated MUCL reconstructions, without internal bracing, in professional baseball players. Methods: The MLB Health and Injury Tracking System was used to identify all professional baseball players who underwent MUCL surgery, regardless of surgery technique, from 2010 to 2023. Professional players of all levels (MLB and MiLB) and players of all positions were included. Player demographics, injury characteristics, surgical details, and postoperative outcomes were obtained. Player demographics included age at surgery, position of play, professional level of play and surgical technique. Outcomes assessed were return to play (RTP) status, time to RTP, return to same level of play (RTSL), time to RTSL, revision MUCL surgery, and time to revision MUCL surgery, with a minimum of 2 years of follow up. Players were considered to have RTP if they participated in at least one game at any professional level. RTSL was defined as returning to the same league of professional play or higher. Patients undergoing MUCL repair and "hybrid" MUCL reconstruction with internal bracing were independently compared to propensity matched patients undergoing isolated MUCL reconstruction, without internal bracing, to assess for a difference in postoperative outcomes. Four subgroup analyses were conducted by further categorizing patients to MLB players, MiLB players, pitchers, and position players. Results: 76 patients underwent MUCL repair with internal bracing from 2016-2021 and were successfully propensity matched to 76 patients undergoing isolated MUCL reconstructions. Baseline patient demographic variables of MUCL repairs were statistically similar to those of controls except for age at time of surgery (24.5 vs 21.8; p<0.001). 81 patients underwent "hybrid" MUCL reconstructions with internal bracing from 2016-2021 and were successfully propensity matched to 81 patients undergoing isolated MUCL reconstructions. Baseline demographic variables of "hybrid" MUCL reconstructions were statistically similar to those of controls except for age at time of surgery (24.3 vs. 23.3; p=0.006). Compared to isolated MUCL reconstruction controls, all patients undergoing MUCL repair demonstrated significantly shorter time to RTP (mean 421.2 vs. 546.2 days; p<0.001), shorter time to RTSL (mean 436.2 vs. 558.8 days; p<0.001), and shorter time to revision (mean 465.2 vs.1648 days; p=0.036). The number of patients who RTP at any level, RTSL, and number of revision surgeries were not significantly different. Compared to isolated MUCL reconstruction controls, all patients undergoing "hybrid" MUCL reconstructions demonstrated no significant differences with respect to the number of patients who RTP, time to RTP, number of patients who RTSL, days to RTSL, number of revision surgeries, and time to revision surgery. In MLB players only, compared to isolated MUCL reconstruction controls, patients who underwent MUCL repairs demonstrated significantly shorter time to RTP (mean 282.8 vs 507.3 days; p=0.008) and shorter time to RTSL (mean 299.7 vs. 598.0 days; p = 0.024). No other outcomes were significant. In MLB players only, compared to isolated MUCL reconstruction controls, patients who underwent "hybrid" MUCL reconstructions demonstrated significantly shorter time to RTP (mean 436.2 vs. 525.3 days; p=0.026). No other outcomes were significant. In MiLB players only, compared to isolated MUCL reconstruction controls, patients who underwent MUCL repairs demonstrated significantly shorter time to RTP (mean 444.3 vs 550.7 days; p<0.001) and shorter time to RTSL (mean 451.7 vs. 556.5 days; p<0.001). No other outcomes were significant. In MiLB players only, compared to isolated MUCL reconstruction controls, patients who underwent "hybrid" MUCL reconstructions demonstrated no significant differences in outcomes. In evaluating pitchers only, compared to isolated MUCL reconstruction controls, patients undergoing MUCL repair demonstrated significantly shorter time to RTP (mean 421.7 vs. 578.6 days; p<0.001), shorter time to RTSL (mean 434.8 vs. 591.6 days; p <0.001), and shorter time to revision surgery (mean 465.2 vs.1648 days; p=0.036). No other outcomes were significant. In pitchers only, compared to isolated MUCL reconstruction controls, patients undergoing "hybrid" MUCL reconstructions demonstrated significantly shorter time to RTP (mean 488.1 vs. 549.0 days; p=0.013) and shorter time to RTSL (mean 505.7 days vs. 577.0 days, respectively; p=0.021). No other outcomes were significant. Notably, all revision surgeries in occurred in pitchers only. Conclusions: Based on a matched cohort anaylsis of professional baseball players undergoing MUCL surgery, when compared to an isolated MUCL reconstruction, MUCL repair with internal bracing may allow for a shorter time to RTP and RTSL, with a shorter time to revision surgery. For pitchers, "hybrid" MUCL reconstruction may allow for a shorter time to RTP and RTSL. For MLB players, "hybrid" MUCL reconstruction may allow for a shorter RTP.

Objectives: The number of medial ulnar collateral ligament (MUCL) reconstructions are increasing. The epidemiology surrounding revision MUCL reconstructions in professional baseball players has not been well defined. The purpose of this study was to report the epidemiology of revision MUCL reconstruction in professional baseball players. The authors hypothesized that the number of revision MUCL reconstructions would increase over time and that the return to sport rate at the same level of play would be less than 70%. Methods: All professional baseball pitchers who underwent revision MUCL reconstruction between 2010-2023 were identified using the MLB Health and Injury Tracking System (HITS). Rate of return and time to return to play (RTP) and return to same level of play (RTSL) was recorded and analyzed for pitchers with a minimum follow up of 2 years. Surgical variables including technique and graft choice were also recorded. Results: Overall, 191 pitchers (avg age 26.0 years), underwent revision MUCL reconstruction. The average time between primary and revision surgery was 1,381 days (45 months). 130 (68%) of these players were MLB pitchers and the other 61 (32%) were MiLB pitchers. 59% of pitchers were able to RTSL at an average of 604 ± 250 days after surgery. 2023 was the year with most revision MUCL reconstructions (n = 27) and the fewest reconstructions were performed in 2010 and 2011 (n = 4). Monthly distribution demonstrates the highest surgery months to be May (17%), June (20%), and July (17%). Hamstring tendon autograft was found to be the most commonly used graft source (n = 90, 47%), compared to palmaris longus autograft (n = 67, 35%). No significant differences were found in the types of grafts used over time ( P = .238 for palmaris and P = .133 for hamstring). In terms of tunnel configuration, both the Modified Jobe and Docking techniques were used in equal occurrence (n = 70, 37%) Conclusions: Following revision MUCL reconstruction, only 72% of professional baseball pitchers were able to return to play at any level at an average of 556 days (18 months), and only 59% were able to return to the same level of play at an average of 604 days (20 months). The average time between primary and revision MUCL reconstruction was 45 months (3.75 years). Pitchers should be counseled on the relatively low RTSL rate and the prolonged time to RTSL.