United States

The Impact of Concomitant Pathologies on Patient Outcomes in Acute vs. Chronic ACL Reconstruction

Authors: Blake Padgett BS, Jonathan Brutti BS, Camila Torres-Caiaffa BA, Alexandra Moutafis BS, David Vasserman BS, Mendel Shloush BS, Jose Lima BS, Carlos Simon BS, Carlos Bermudez BS, Carolina Carrandi BS, Anshul Saxena BDS PhD, Matthias R. Schurhoff MD, Luis A. Vargas MD PhD, Gautam P. Yagnik MD, John E. Hechtman MD, John E. Zvijac MD, John W. Uribe MD

Background: ACL reconstruction (ACLR), a prevalent orthopedic procedure, often involves concomitant meniscal and chondral damage. Current literature lacks consistent differentiation between acute and chronic ACLR regarding short-term outcomes and their relationship with concomitant pathologies. This study compares the impact of surgical timing and the presence of meniscal and chondral pathologies on patient-reported outcomes (PROs).

Methods: This study used a historical cohort with prospectively collected PROs following ACLR. Inclusion criteria required complete pre-operative and 2-year follow-up data. Patients were categorized as acute if the injury-to-surgery interval was less than 60 days, and chronic if over 60 days. Dependent variables included IKDC, EuroQol, PROMIS Global Mental and Physical Health, KOOS, and VAS Pain scores, with time as the primary fixed effect. Intraoperative data included the location of chondral lesions and detailed meniscal injuries. A mixed linear model regression analysis examined the effect of time on outcome variables using REML across two groups (acute and chronic). Data was analyzed using Python 3.8 with pandas and statsmodels packages.

Results: Of 1235 patients, 97 met the inclusion criteria (54 chronic, 43 acute). Of these, 73 (75.3%) had an ACL tear with concomitant pathology (72.1% acute, 77.8% chronic). Medial meniscal tears were found in 45.4%, lateral tears in 60.8% with partial tears most frequently associated with the posterior horn (73.9% medial, 47.5% lateral). Medial chondral lesions were found in 22.7%, lateral in 18.6%, and patellofemoral in 41.2%. Among acute patients, 53.5% had meniscal injuries, 25.6% had chondromalacia, and 20.1% had both. Among chronic patients, 31.5% had meniscal injuries, 5.6% had chondromalacia, and 44.4% had both. Acute injuries had more meniscal tears (p &lt; 0.048), while chronic injuries had significantly more combined meniscal and chondral pathology (p &lt; 0.027). Chondral lesions showed no significant difference between timing of intervention. Overall, partial meniscectomies were performed in 55.6% (20.6% acute, 35% chronic) and meniscal repairs in 46.4% (23.7% acute, 22.7% chronic). Linear mixed model analysis showed a significant positive effect of time on IKDC scores (p &lt; 0.001). Random effects analysis indicated a group variance of 2.355, highlighting variability in IKDC scores between acute and chronic groups.

Conclusion: Combined chondral lesions and meniscus pathologies were more prevalent in chronic ACL reconstruction. Acute intervention showed greater improvement in median PROs compared to delayed reconstruction. Earlier treatment plans may reduce the occurrence of combined meniscal injury and cartilage damage in ACLR and may improve patient outcomes.

AMA Research Challenge 2024 

The Impact of Concomitant Pathologies on Patient Outcomes in Acute vs. Chronic ACL Reconstructions

The Impact of Concomitant Pathologies on Patient Outcomes in Acute vs. Chronic ACL Reconstruction

Authors: Blake Padgett BS, Jonathan Brutti BS, Camila Torres-Caiaffa BA, Alexandra Moutafis BS, David Vasserman BS, Mendel Shloush BS, Jose Lima BS, Carlos Simon BS, Carlos Bermudez BS, Carolina Carrandi BS, Anshul Saxena BDS PhD, Matthias R. Schurhoff MD, Luis A. Vargas MD PhD, Gautam P. Yagnik MD, John E. Hechtman MD, John E. Zvijac MD, John W. Uribe MD

Background: ACL reconstruction (ACLR), a prevalent orthopedic procedure, often involves concomitant meniscal and chondral damage. Current literature lacks consistent differentiation between acute and chronic ACLR regarding short-term outcomes and their relationship with concomitant pathologies. This study compares the impact of surgical timing and the presence of meniscal and chondral pathologies on patient-reported outcomes (PROs).

Methods: This study used a historical cohort with prospectively collected PROs following ACLR. Inclusion criteria required complete pre-operative and 2-year follow-up data. Patients were categorized as acute if the injury-to-surgery interval was less than 60 days, and chronic if over 60 days. Dependent variables included IKDC, EuroQol, PROMIS Global Mental and Physical Health, KOOS, and VAS Pain scores, with time as the primary fixed effect. Intraoperative data included the location of chondral lesions and detailed meniscal injuries. A mixed linear model regression analysis examined the effect of time on outcome variables using REML across two groups (acute and chronic). Data was analyzed using Python 3.8 with pandas and statsmodels packages.

Results: Of 1235 patients, 97 met the inclusion criteria (54 chronic, 43 acute). Of these, 73 (75.3%) had an ACL tear with concomitant pathology (72.1% acute, 77.8% chronic). Medial meniscal tears were found in 45.4%, lateral tears in 60.8% with partial tears most frequently associated with the posterior horn (73.9% medial, 47.5% lateral). Medial chondral lesions were found in 22.7%, lateral in 18.6%, and patellofemoral in 41.2%. Among acute patients, 53.5% had meniscal injuries, 25.6% had chondromalacia, and 20.1% had both. Among chronic patients, 31.5% had meniscal injuries, 5.6% had chondromalacia, and 44.4% had both. Acute injuries had more meniscal tears (p < 0.048), while chronic injuries had significantly more combined meniscal and chondral pathology (p < 0.027). Chondral lesions showed no significant difference between timing of intervention. Overall, partial meniscectomies were performed in 55.6% (20.6% acute, 35% chronic) and meniscal repairs in 46.4% (23.7% acute, 22.7% chronic). Linear mixed model analysis showed a significant positive effect of time on IKDC scores (p < 0.001). Random effects analysis indicated a group variance of 2.355, highlighting variability in IKDC scores between acute and chronic groups.

Conclusion: Combined chondral lesions and meniscus pathologies were more prevalent in chronic ACL reconstruction. Acute intervention showed greater improvement in median PROs compared to delayed reconstruction. Earlier treatment plans may reduce the occurrence of combined meniscal injury and cartilage damage in ACLR and may improve patient outcomes.

poster

Welcome to the **largest national, multi-specialty research** event featuring research from more than 750 medical students, residents, fellows, and international medical graduates.

Use the buttons below or navigation menu to access the event.
 

[![](https://assets.underline.io/markdown_image/1/image/20e1e77aa954efeac7a15d84c85eb383.jpg)](https://underline.io/events/468/sessions?searchGroup=all)
 
[![](https://assets.underline.io/markdown_image/1/image/068522d81aca0b68a369787c7dfccd1b.jpg)](https://underline.io/events/468/posters?searchGroup=all)
 
[![](https://assets.underline.io/markdown_image/1/image/d3971ece79d5e5575b178bdc2c8bbfae.jpg)](https://underline.io/events/468/help-desk)
 

#### Event Details

The 2024 American Medical Association Research Challenge includes a poster symposium hall and a semifinals hall with the top scored research. **Log in at any time throughout the event to:**

* **View posters and presentations** on a variety of topics and specialties
* **Score posters in the semifinals** to help decide the top five finalists (AMA member exclusive opportunity)
* **Connect with participants** and provide feedback to help advance their research

At the conclusion of this event, the AMA will announce the top five finalists who will advance to the AMA Research Challenge finals, present their research to an elite panel of judges, and compete to win a $10,000 grand prize presented by Laurel Road. 

### Grand Prize Sponsor

AMA would like to thank Laurel Road for sponsoring a $10,000 grand prize for the winner of the AMA Research Challenge. Laurel Road is not involved in winner selection process. The winner will be announced on February 20, 2025 during the AMA Research Challenge finals. Payment of the grand prize will be directly from Laurel Road. See the AMA Research Challenge Official Rules for terms and conditions.

[![](https://assets.underline.io/uploads/markdown_image/1/image/611e331d4a0eba0920f240cfc04b4d77.png)](https://www.laurelroad.com/)

You need to log in with the email address you registered with. Access credentials have been sent to your email. 

Please be sure to check your spam and other email folders if you do not see an email confirmation right away.

Please log in to explore this event.

**There is no registration fee for this event! **

If you have used the AMA Research Challenge platform previously, please click the ‘Log-in’ button below. If you do not remember your password, please click “forgot password” and follow prompts to reset your password. After resetting your password, please refresh your webpage to access the platform.

Register to explore research in a variety of topics. AMA members get exclusive access to score posters in the semifinals. 

**Please use this link [here](https://www.ama-assn.org/member-benefits/events/ama-research-challenge) to register for free.**

Registration Is Required

Join the AMA Research Challenge poster symposium and semifinals to explore top research posters and score posters in the semifinals (an AMA member exclusive opportunity).

Abstract Title: TKA Femoral Flexion Angle Distribution and Range of Motion

Background: Femoral implant flexion angle (FF) is an underutilized metric with wide reported ranges. Increased understanding of current FF use may establish specific sagittal alignment targets. 

Methods: Demographics, knee ROM, and implant alignment parameters were collected for patients undergoing TKA with a CT-based robotic knee replacement system. The range and distribution of FF angles was determined. “High-FF” and “Low-FF” groups were divided at the FF mean. ROM measurements were taken in four windows: Preoperative, Early postoperative (7- 42 days), Middle postoperative (43-135 days), and Late postoperative (>136 days). ROM was compared between groups. 

Results: 976 patients of age 66.3±8.74 years, BMI 32.9±10.9, and 56.6% female. Average FF was 4.04°±2.10° flexion [0°-9°]. The Low-FF group [0.0°-4.0°] had 528 patients. The High-FF group [4.5°-9.0°] had 448 patients. There were no differences in preoperative knee parameters: varus/valgus alignment, flexion/extension ROM (p>0.2). High-FF patients were often female (Low-FF 53.0%; High-FF 62.5%; p=0.006) and more frequently cemented implants (Low-FF 14.4%; High-FF 20.4%; p=0.020). High-FF patients had smaller femoral implants (Size 4 or lower: Low-FF 52.2%; High-FF 68.7%; p<0.001), smaller tibial implants (Size 4 or lower: Low- FF 50.1%; High-FF 63.9%; p<0.001), and lower tibial slope (Low-FF 3.2°; High-FF 3.0°; p<0.001). There were no differences in patient size (p>0.1) or femur-tibia size mismatch frequency (p=0.539). 193 patients had measurements in all four windows. Repeated measures found no ROM differences between groups at any timepoint. 

Conclusion: The observed femoral implant flexion angles assumed a normal distribution ranging from 0° to 9° flexion, centered at 4° flexion. Patients receiving a femoral flexion angle above 4° were more often female, cemented, had lower tibial slope angle, and smaller femur and tibia implant sizes. Patients with larger femoral flexion angles showed no difference in flexion or extension range of motion at any timepoint when compared to patients with smaller femoral flexion angles.

TKA Femoral Flexion Angle Distribution and Range of Motion

Background:
Approximately 400,000 ACL reconstructions are performed each year in the United States. Effective ACL injury prevention programs may be paramount in reducing this significant injury burden. 
Objective: To determine the effectiveness of ACL injury prevention programs and generate updated guidelines that can be implemented to protect athletes from these injuries.

Methods:
Embase, PubMed, and Ovid (MEDLINE) were searched in accordance with PRISMA guidelines. Included studies focused on ACL injury prevention as opposed to treatment and provided data on ACL injury rates after intervention implementation. Using random-effects models, the pooled risk ratio (RR) was generated for all data. Sub-analyses were completed for female-only, high school vs. collegiate/professional, handball, soccer, and balance board data.

Results:
A total of 18 articles were identified (9 randomized control trials, 9 prospective cohort studies). The 25,166 studied athletes played handball, soccer, basketball, or volleyball (mean age = 19.3, SD = 3.6 years; >85% female). All interventions were studied for a minimum of one season (mean = 1.3, SD = 0.59). Athletes who participated in an ACL injury prevention program were significantly less likely to sustain an ACL rupture with a pooled RR of 0.46 (95% CI, 0.36-0.57; P < 0.01; I2 = 49%). When analyzed by age, there was a significant risk reduction in ACL rupture for collegiate/professional athletes over age 18 (RR = 0.50; 95% CI, 0.38-0.64; P < 0.01; I2 = 66%) but no significant change for players under age 18 (RR = 0.35; 95% CI, 0.22-0.55; P = 0.47; I2 = 0%). Of the 12 studies including female players, the pooled RR was 0.57 and not statistically significant (95% CI, 0.43-0.74; P = 0.13; I2 = 32%). There was no significant RR for athletes playing soccer (RR = 0.30; 95% CI, 0.19-0.46; P = 0.06; I2 = 47%) or handball (RR = 0.66; 95% CI, 0.46-0.96; P = 0.38; I2 = 5%). Players who participated in programs including balance boards exhibited a significantly lower risk of ACL rupture (RR = 0.49; 95% CI, 0.35-0.67; P < 0.01; I2 = 74%).

Conclusion:
Athletes who did not partake in an ACL injury prevention program were nearly twice as likely to sustain an ACL rupture compared to those who did, with particular ACL injury risk reduction in collegiate/professional athletes and those who used balance boards. This study provides strong support for using neuromuscular training programs to significantly reduce the risk of ACL rupture among athletes.

Training to Stay in the Game: A Systematic Review and Meta-Analysis of ACL Injury Prevention Programs

Gonzalo F. Del Rio Montesinos 
Abstract Title : Unveiling the Risks: A Deep Dive into Vertebral Artery Injuries Post Cervical Disc Arthroplasty 
Background
Cervical Disc Arthroplasty (CDA) treats cervical disc degeneration and spinal compression, offering a high success rate and improved neck disability index. During CDA, the vertebral artery (VA), a major blood vessel branching from the subclavian artery, is at risk. This courses the transverse foramen of C2-C6 vertebrae, exits at C2, and enters the skull via the foramen magnum. Injuries are often due to anatomical variations, though rare, can cause severe complications. The objective of this narrative review is to analyze variables such as Normal Anatomy, FDA-approved Devices, increase CDA, the prevalence of VAI in the anterior approach, case reports regarding the injury, preventative measures, and treatment were considered. 

Methods
The articles chosen were from June 30th, 2000, to June 30th, 2024, and sourced from PubMed, Science Direct, and Web of Science. The keywords were cervical, cervical disc, vertebral artery, vertebral artery injury, disc arthroplasty, and degenerative disc. 

Results 
Extensive literature exists regarding the anatomic variations such as a 7.6% occurrence among 250 individuals. The anterior approach of CDA has a 0.4% occurrence of VAI. Pre-operative MRI and post-operative advanced imaging techniques such as MRI must be implemented with more frequency to determine artery course and health outcomes. Physician experience has significant effects upon possible injuries. Surgeons with < 300 procedure experience had a 0.33% possibility of injuring the artery and those with > 300 had 0.06%. CDA has been implemented in Europe since the 1960s however it wasn’t until 2007 where the FDA approved the first CDA device for the USA. Among 11 FDA-approved devices, eight reported blood loss, two Vascular Intra op, and one cerebrovascular bleeding, however no device indicated to have a VAI as a complication. Two case reports were found regarding VAI following CDA. In VAI, a stent has 97% success rate, however one must consider long term re-stenting and symptom reappearance. Two case reports regarding VAI following CDA indicated the lack of literature of the injury and the possible complication when approaching the procedure. In the years 2007-2013 there has been a nonlinear 190% increase in the use of CDA, exponentially replacing anterior cervical fusion and one must consider that this continuous implementation will bring about increased case reports regarding complications. 

Conclusion
VAI must be considered when approaching a CDA due the higher prevalence of these procedures being implemented. Anatomic variations, Physician Experience, preventative and treatment management are factors to consider in VAI.

Unveiling the Risks: A Deep Dive into Vertebral Artery Injuries Post Cervical Disc Arthroplasty

Background: Revision total joint arthroplasty (TJA) becomes necessary when a primary TJA fails, leading to worse patient outcomes, higher complication rates, and increased economic burdens on the healthcare system. With the global aging population, the demand for revision TJA’s are projected to rise significantly by 2030 which highlights the need for effective machine learning (ML) models to improve outcomes in revision TJA. Although prior systematic reviews have evaluated the utility of ML in predicting outcomes for primary TJA, there is a notable gap in assessing ML’s potential in the context of revision TJA . This study aims to systematically review the application of ML for predicting outcomes following revision total hip arthroplasty (THA) and revision total knee arthroplasty (TKA).

Methods: A comprehensive literature search was conducted to May 2024 in Ovid MEDLINE, Ovid Embase, and Web of Science. Studies were imported into Covidence for screening. The exclusion criteria were: (1) other systematic reviews; (2) animal models; (3) studies not utilizing artificial intelligence; (4) studies not involving revision arthroplasty; (5) case reports; (6) technical notes; (7) editorial notes; (8) studies on joints other than the hip and knee; and (9) studies without full-text availability. The search strategy yielded 1289 articles, of which 19 were assessed as eligible for this review.

Results: Search criteria yielded 19 relevant studies. Topics of study included patient complications (n = 12), readmissions (n = 2), discharge dispositions (n = 2), patient-reported outcome measures (n = 0), inpatient status and length of stay (LOS) (n = 4), and patient function (n = 1). Studies involved revision TKA (n = 8), revision THA (n = 7), or a combination (n = 5). Studies were of solely revision arthroplasty (n = 16) or included primary and revision arthroplasty (n = 4). Of reported AUC, greater than 71% of predictive outcomes for at least one model had an area under the receiver operating characteristic curve (AUC) in the excellent or outstanding range (AUC > 0.8). Additionally, 14 studies were internally validated and only 3 studies were externally validated.

Discussion/Conclusion: Machine learning algorithms are being increasingly used to predict patient outcomes after revision THA and TKA. Machine learning has shown utility in clinical settings in the context of risk stratification and prediction of complications, patient reported outcome scores, and readmissions. While machine learning algorithms have been received with considerable interest, they should be critically assessed and externally validated prior to clinical adoption.


Using Machine Learning to Enhance Predictive Outcomes in Revision Total Joint Arthroplasty: A Systematic Review

Background
Otolaryngologists utilize drug-induced sleep endoscopy (DISE) to evaluate the anatomic location and pattern of upper airway collapse in patients with obstructive sleep apnea (OSA). The cardiovascular consequences of OSA are due to intermittent hypoxia and negative intrathoracic pressure swings, leading to sympathetic activation. It is challenging, however, to assess these physiologic pressure swings during natural sleep; therefore, we applied objective measures of airflow and respiratory effort during DISE to measure pharyngeal pressure changes. We hypothesized greater retroepiglottic pressure changes during respiratory events from DISE to correlate with reduced nocturnal blood pressure “dipping” during 24-hour ambulatory blood pressure monitoring (ABPM), thereby enhancing surgical management of OSA by linking intraoperative findings to cardiovascular outcomes.

Methods
Patients with untreated OSA prospectively underwent ABPM and DISE with pharyngeal manometry. Retroepiglottic pressure (cm H2O) was calculated as the mean pressure differential for each obstructed breath between the start of inspiration and the nadir of negative pressure during inspiration. ABPM recorded blood pressure every 30 minutes while awake and hourly while asleep. Pearson’s correlation evaluated associations between retroepiglottic pressure changes and ABPM values. 

Results
Twenty patients were included for analysis. Patients, on average, were middle-aged (48.7±16.3 years), overweight (body-mass index [BMI] 29.5±3.46 kg/m2), male (65%), White (60%), with moderate-severe OSA at baseline (AHI 40.0±21.2 events/hour), normotensive (24-hour systolic & diastolic pressure 121±13.5 and 72.3±8.24 mmHg), and taking anti-hypertensive medications (45%). Correlational analysis showed greater retroepiglottic pressure swings were correlated with higher nocturnal, diurnal, and 24-hour ABPM values: 24-hour mean arterial pressure (MAP) (r=0.48, p=0.03), 24-hour systolic blood pressure (SBP) (r=0.46, p=0.04), 
higher 24-hour diastolic blood pressure (DBP) (r=0.39, p=0.09).

Conclusion
In this study, a relationship between nocturnal blood pressure and retroepiglottic pressure swings during DISE was identified. These findings underscore the importance of intraoperative physiologic assessments in predicting cardiovascular risk in patients with OSA and highlight Otolaryngologists’ role in managing these risks. Future directions involve expanding the sample size and comparing these pharyngeal pressures against conventional polysomnographic OSA measures of cardiovascular risk.

Association Between Retroepiglottic Pressure During Drug-Induced Sleep Endoscopy & Nocturnal Blood Pressure: A Pilot Study

Subglottic stenosis (SGS) is a narrowing of the airway distal to the vocal cords. It is a common post-intubation complication treated by otolaryngologists. The narrowing is typically due to a band of fibrotic scar tissue, with few cases reporting calcification of this band in the post-cricoid region. To date, there have been fewer than 5 reports of calcified SGS, each treated with a unique surgical approach. In this case report, we describe our technique for the removal of a calcified subglottic stenotic band at the level of the cricoid in a 46 year-old female. We also review the current literature to compare outcomes and complications of the various surgical techniques implemented for this unique pathology. The technique utilized in this report adds to the previous literature and offers a viable treatment alternative for calcified SGS.

Diagnosis and Surgical Management of a Patient with Calcified Subglottic Stenosis

Introduction: The objective is to develop a proof-of-concept smartphone-based eye-tracking algorithm to assess non-pathologic optokinetic (OKN) nystagmus in healthy participants. Current videonystagmography (VNG) is typically restricted to in-office use, and advances in ambulatory or portable vestibular diagnostic devices would yield immense public health benefits.

Methods: Healthy participants (n=39) without a history of dizziness or vertigo were recruited for this prospective comparison study. A smartphone attached to a custom head stabilization device illuminated by a white LED circuit was used to record nystagmus induced with a 30 frames/sec OKN stimulus over a 30-second period. A centroid tracking algorithm ("VertiScope") was created and optimized to detect slow-phase velocity (SPV) of horizontal nystagmus in a diverse subject cohort in a variety of lighting conditions. A cohort of subjects measured in ideal lighting conditions (n=16) underwent standard VNG for comparison of nystagmus recordings with our novel VertiScope algorithm. 

Results: Non-pathologic nystagmus was measured across multiple lighting conditions, with high signal-to-noise ratios (SNR) and mean SPV of 22.53+/-5.16 deg/sec. Nystagmus SPV was not significantly different between the device and standard VNG system (t= -0.5, p=0.6). Lighting conditions produced SNRs of 49.28 (dark), 48.90 (backlit), 51.33 (side-lit), 55.65 (outdoor lighting), and 58.42 (ideal). VertiScope SPV was not significantly different when compared against quantitative facial metrics for all participants. 

Conclusions: Here, we demonstrate the feasibility of a novel oculography device and in the detection of non-pathologic nystagmus in healthy subjects. Future applications of this device include: obtaining real-time measurements of nystagmus during an acute vertigo attack in patients with vestibular disorders; testing patients unable or unwilling to present to a specialized vestibular laboratory; efficiently repeating testing overtime; and improving accessibility of vestibular testing.

Novel Ambulatory Event Capture Device: Characterization of Non-Pathologic Nystagmus

Abstract Title:
Predicting 30-Day Outcomes in Head and Neck Cancer Surgery Using Machine Learning

Background:
Readmission following surgical resection of head and neck squamous cell carcinoma (HNSCC) has been reported to range from 7.7% to 26.5%, with worse outcomes and cost increase of $15,123 for care of patients with unplanned readmission. While previous studies have shown correlations between various clinical factors and hospital readmission risk, they have not provided actionable clinical predictions leveraging these factors to impact clinical decisions. This study aims to fill this gap by developing and validating a machine learning model to predict 30-day mortality and hospital readmission likelihood following definitive surgical resection for HNSCC using a large-scale, well-curated dataset. This model may serve as an actionable, transparent, and highly accurate clinical decision support tool to identify high-risk patients and redirect preventative resources effectively.

Methods:
This prognostic predictive modeling study utilized retrospective data from the 2006 to 2018 National Cancer Database (NCDB), including 103,891 patients with HNSCC undergoing surgical resection. Predictors included comprehensive pre-treatment demographic and clinical variables available in the NCDB. A combination of five machine learning models was trained on 80% of the data and tested on the remaining 20% to predict the primary outcomes of 30-day mortality and 30-day readmission.

Results:
Among the 103,891 patients satisfying the inclusion criteria, 5,838 (5.6%) were readmitted, and 829 (0.8%) died within 30 days. The models achieved an AUC of 0.80 (95% CI: 0.77-0.83) for mortality prediction and an AUC of 0.66 (95% CI: 0.65-0.68) for readmission prediction. SHAP value analysis identified sex and urban-rural index as the most predictive variables for mortality and readmission, respectively.

Conclusion:
The machine learning model demonstrated high sensitivity and specificity in predicting 30-day mortality and readmission risks in a large-scale dataset. This model highlights critical features influencing predictions, providing key clinical insights supporting clinical decision-making. With further validation in prospective datasets, this model can serve as an effective clinical decision support tool, guiding resource allocation and follow-up care for patients undergoing surgical resection of HNSCC. This study presents a significant advancement in large-scale validation of a potential clinical decision support tool that is poised to enhance patient outcomes by providing transparent and actionable predictions on patient outcomes.

Predicting 30-Day Outcomes in Head and Neck Cancer Surgery Using Machine Learning

Authors: Lucy Nguyen, Michelle Alder, Natoshia Cunningham 

Michigan State University, College of Human Medicine, Department of Family Medicine 

Abstract Title: Assessing the Influence of ADAPT on Comorbid Anxiety and Depressive Disorders. 

Background: Functional abdominal pain disorders (FAPD) are common chronic pain conditions impacting more than 10% of youth and are associated with adverse outcomes. A tailored approach to care addressing both pain and comorbid anxiety called the Aim to Decrease Anxiety and Pain Treatment (ADAPT) has been shown to improve pain-related impairment in youth with FAPD. In this secondary analysis of the ADAPT RCT, we explored how specific mental health diagnoses MDD, GAD, social anxiety, separation anxiety, panic disorder, and OCD responded following ADAPT. 

Methods: Participants, between the ages of 9-14 diagnosed with FAPD, underwent a diagnostic interview (ADIS for DSM-IV, Child Version [ADIS-IV]). Participants were then randomized to continue treatment as usual with additional tailored cognitive behavioral therapy (ADAPT +TAU), or TAU alone. A post-assessment to assess the outcomes was done 8 weeks later. This secondary analysis is focused on participants who completed ADAPT (n=39). SPSS was utilized for data analysis. Chi-squares using Fischer’s exact tests were used to assess significant differences between the incidence of anxiety diagnoses before and after receiving ADAPT. 

Results: The number of people with GAD diagnoses significantly decreased from 20 to 10 individuals after ADAPT treatment (p < 0.001). The number of people with social anxiety diagnosis prior to ADAPT treatment was 20, which decreased significantly to 10 at the post-assessment (p<0.001). The number of people with a SAD diagnosis pretreatment was 13 which then dropped to 4 (p = 0.009). The number of people with a panic disorder diagnosis dropped from 4 to 2 (not significant). The number of OCD diagnosis from pre- to post-assessment significantly decreased from 7 to 3 (p = 0.004). 

For each depressive disorder, dysthymia and MDD, the number of depressive diagnoses in the treatment as usual group increased at the end of assessment. For those diagnosed with dysthymia in the ADAPT group, the number did not change (not significant). The number of people with MDD diagnoses dropped from 5 to 2 after ADAPT treatment (p = 0.013). 

Conclusion: Youths with FAPD and who received ADAPT demonstrated statistically significant improvement in mental health diagnoses including, major depression, dysthymia, generalized anxiety, social anxiety, separation anxiety, and OCD. CBT is often underutilized in the treatment of youth with chronic medical conditions. When addressing pain, co-occurring anxiety and depression is often overlooked although it is common and associated with poor outcomes. CBT should continue to be researched and promoted for symptom management for chronic medical issues with co-occurring psychological disorders.

Assessing the Influence of ADAPT, a Tailored Cognitive Behavioral Treatment for Youth with Functional Abdominal Pain Disorders, on Comorbid Anxiety and Depressive Disorders.​

Background
Recurring lab studies in the form of ABG, VBG, CBC, electrolytes, renal function panels and coagulation measurements are commonplace in PCICU. This practice pattern provides an element of safety by providing surveillance of patient’s volatile physiologies. This practice has unintended negative consequences including expense, laboratory “alarm fatigue” for providers, and increased risk of CLABSI. These consequences are intensified when recurring lab studies occur indefinitely and when lab draws are poorly synchronized so that the vascular catheter is accessed more frequently than necessary. 

Methods
The investigators worked with EPIC software professionals to construct a lab order set that speeds order entry, provides a comprehensive, individualized menu of lab tests most commonly ordered in the PCICU, enforces synchronization of blood draws, caps the number of days the selected labs will be drawn, and notifies the care team when slates of recurring lab tests are expiring. We wish to examine the effect of this intervention on the total number of labs drawn per patient per day, the daily cost, the number of times vascular catheters are accessed, and the number of patient resuscitations observed. Our lab order set is currently under construction by EPIC.

Results
We are currently receiving via automated EPIC electronic database a daily report of the number of each type of lab test performed per patient during each 24-hour period for one month. From this data we will tabulate a) the total number of each type of lab test performed per patient per day, b) the estimated total cost and charge for all lab testing per patient per day, and c) the number of times per day that blood is drawn from a vascular catheter per patient per day. 

As surrogates of potential negative consequences of lab reduction, we will monitor number of patient resuscitations that occur during the pre-intervention and post-intervention phases and number of times per patient per day that vascular catheters are accessed. We will compare these outcomes before and after implementation. Finally, to assess compliance, we will express the percentage of the average daily census who have an active laboratory order set in use with a specified expiration date. 

Conclusion
It is our hope that the convenience and simplicity of the PCICU order set will result in a) regular utilization by our providers, b) reduced overall lab testing, c) reduced cost and patient charges, d) fewer accessions of the indwelling vascular catheters, and e) no increase in resuscitation events in our intensive care unit.


Premium content

The Impact of Concomitant Pathologies on Patient Outcomes in Acute vs. Chronic ACL Reconstructions

Next from AMA Research Challenge 2024

TKA Femoral Flexion Angle Distribution and Range of Motion

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES