Browsing by Author "Mohanty, Sarthak"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Machine learning clustering of adult spinal deformity patients identifies four prognostic phenotypes: a multicenter prospective cohort analysis with single surgeon external validation.
    (The spine journal : official journal of the North American Spine Society, 2024-02) Mohanty, Sarthak; Hassan, Fthimnir M; Lenke, Lawrence G; Lewerenz, Erik; Passias, Peter G; Klineberg, Eric O; Lafage, Virginie; Smith, Justin S; Hamilton, D Kojo; Gum, Jeffrey L; Lafage, Renaud; Mullin, Jeffrey; Diebo, Bassel; Buell, Thomas J; Kim, Han Jo; Kebaish, Khalid; Eastlack, Robert; Daniels, Alan H; Mundis, Gregory; Hostin, Richard; Protopsaltis, Themistocles S; Hart, Robert A; Gupta, Munish; Schwab, Frank J; Shaffrey, Christopher I; Ames, Christopher P; Burton, Douglas; Bess, Shay; International Spine Study Group

    Background context

    Among adult spinal deformity (ASD) patients, heterogeneity in patient pathology, surgical expectations, baseline impairments, and frailty complicates comparisons in clinical outcomes and research. This study aims to qualitatively segment ASD patients using machine learning-based clustering on a large, multicenter, prospectively gathered ASD cohort.

    Purpose

    To qualitatively segment adult spinal deformity patients using machine learning-based clustering on a large, multicenter, prospectively gathered cohort.

    Study design/setting

    Machine learning algorithm using patients from a prospective multicenter study and a validation cohort from a retrospective single center, single surgeon cohort with complete 2-year follow up.

    Patient sample

    About 805 ASD patients; 563 patients from a prospective multicenter study and 242 from a single center to be used as a validation cohort.

    Outcome measures

    To validate and extend the Ames-ISSG/ESSG classification using machine learning-based clustering analysis on a large, complex, multicenter, prospectively gathered ASD cohort.

    Methods

    We analyzed a training cohort of 563 ASD patients from a prospective multicenter study and a validation cohort of 242 ASD patients from a retrospective single center/surgeon cohort with complete two-year patient-reported outcomes (PROs) and clinical/radiographic follow-up. Using k-means clustering, a machine learning algorithm, we clustered patients based on baseline PROs, Edmonton frailty, age, surgical history, and overall health. Baseline differences in clusters identified using the training cohort were assessed using Chi-Squared and ANOVA with pairwise comparisons. To evaluate the classification system's ability to discern postoperative trajectories, a second machine learning algorithm assigned the single-center/surgeon patients to the same 4 clusters, and we compared the clusters' two-year PROs and clinical outcomes.

    Results

    K-means clustering revealed four distinct phenotypes from the multicenter training cohort based on age, frailty, and mental health: Old/Frail/Content (OFC, 27.7%), Old/Frail/Distressed (OFD, 33.2%), Old/Resilient/Content (ORC, 27.2%), and Young/Resilient/Content (YRC, 11.9%). OFC and OFD clusters had the highest frailty scores (OFC: 3.76, OFD: 4.72) and a higher proportion of patients with prior thoracolumbar fusion (OFC: 47.4%, OFD: 49.2%). ORC and YRC clusters exhibited lower frailty scores and fewest patients with prior thoracolumbar procedures (ORC: 2.10, 36.6%; YRC: 0.84, 19.4%). OFC had 69.9% of patients with global sagittal deformity and the highest T1PA (29.0), while YRC had 70.2% exhibiting coronal deformity, the highest mean coronal Cobb Angle (54.0), and the lowest T1PA (11.9). OFD and ORC had similar alignment phenotypes with intermediate values for Coronal Cobb Angle (OFD: 33.7; ORC: 40.0) and T1PA (OFD: 24.9; ORC: 24.6) between OFC (worst sagittal alignment) and YRC (worst coronal alignment). In the single surgeon validation cohort, the OFC cluster experienced the greatest increase in SRS Function scores (1.34 points, 95%CI 1.01-1.67) compared to OFD (0.5 points, 95%CI 0.245-0.755), ORC (0.7 points, 95%CI 0.415-0.985), and YRC (0.24 points, 95%CI -0.024-0.504) clusters. OFD cluster patients improved the least over 2 years. Multivariable Cox regression analysis demonstrated that the OFD cohort had significantly worse reoperation outcomes compared to other clusters (HR: 3.303, 95%CI: 1.085-8.390).

    Conclusion

    Machine-learning clustering found four different ASD patient qualitative phenotypes, defined by their age, frailty, physical functioning, and mental health upon presentation, which primarily determines their ability to improve their PROs following surgery. This reaffirms that these qualitative measures must be assessed in addition to the radiographic variables when counseling ASD patients regarding their expected surgical outcomes.
  • Thumbnail Image
    ItemOpen Access
    Patient and procedural risk factors for decline in lower-extremity motor scores following adult spinal deformity surgery.
    (Journal of neurosurgery. Spine, 2023-04) Mohanty, Sarthak; Hassan, Fthimnir M; Lenke, Lawrence G; Burton, Douglas; Daniels, Alan H; Gupta, Munish C; Kebaish, Khaled M; Kelly, Michael; Kim, Han Jo; Klineberg, Eric O; Passias, Peter G; Protopsaltis, Themistocles; Schwab, Frank; Shaffrey, Christopher I; Smith, Justin S; Line, Breton G; Lafage, Renaud; Lafage, Virginie; Bess, Shay

    Objective

    The purpose of this study was to discern factors that differentiate patients who experience postoperative lower-extremity motor function decline in the early postoperative period.

    Methods

    Adult spinal deformity (ASD) patients who were enrolled in a multicenter, observational, and prospectively collected study from 2018 to 2021 at 18 spinal deformity centers in North America were queried. Eligible participants met at least one of the following radiographic and/or procedural inclusion criteria: pelvic incidence minus lumbar lordosis (PI-LL) ≥ 25°, T1 pelvic angle (T1PA) ≥ 30°, sagittal vertical axis (SVA) ≥ 15 cm, thoracic scoliosis ≥ 70°, thoracolumbar scoliosis ≥ 50°, global coronal malalignment ≥ 7 cm, 3-column osteotomy, spinal fusion ≥ 12 levels, and/or age ≥ 65 years with ≥ 7 levels of instrumentation. Patients with an inflammatory or autoimmune disease and those who were incarcerated or pregnant were excluded, as were non-English speakers. Only patients with baseline and 6-week postoperative lower-extremity motor score (LEMS) were analyzed. Patient information, including demographic data, operative data, patient-reported outcomes, and radiographic parameters, were collected. Univariate and multivariable logistic regression models were built to quantify the degree to which a patient's postoperative LEMS decline was related to demographic and clinical characteristics.

    Results

    In total, 205 patients (mean age 61.5 years, mean total instrumented levels 12.6, 67.3% female, 54.2% primary cases, 79.5% with pelvic fixation) were evaluated. Of these 205 patients, 32 (15.5%) experienced LEMS decline in the perioperative period. These patients were older (p = 0.0014) and had greater BMI (p = 0.0176), higher frailty scores (p = 0.047), longer operating room times (p = 0.033), and greater estimated blood loss (p < 0.0001), and they were more frequently observed to have intraoperative neurophysiological monitoring (IONM) changes (p = 0.018). The deteriorated cohort had greater C7SVA at baseline (p = 0.0028) but were comparable in terms of all other radiographic parameters. No radiographic differences were seen between the groups at the 6-week visit; however, the deteriorated cohort experienced greater change in PI-LL (p < 0.0001), lumbar lordosis (p = 0.0461), C7SVA (p = 0.0004), and T1PA (p < 0.0001). Multivariate logistic regression demonstrated that the presence of IONM changes and each degree of negative change in T1PA conferred 3.71 (95% CI 1.01-13.42) and 1.09 (1.01-1.19) greater odds of postoperative LEMS deterioration, respectively.

    Conclusions

    In this study, 15.6% of ASD patients incurred LEMS decline in the perioperative period. The magnitude of change in global sagittal alignment, specifically T1PA, was the strongest independent predictor of LEMS decline, which has implications for surgical planning, patient counseling, and clinical research.