Mehul Mittal

Background/Objectives: Posterior cervical decompression and fusion (PCDF) carry perioperative risks and increases postoperative healthcare utilization (HU). Traditional prediction models emphasize comorbidities and surgical factors, yet social determinants of health (SDHs) are known to also affect clinical outcomes. We applied machine learning (ML) to integrate SDHs and clinical variables in predicting 90-day readmission and HU after PCDF. Methods: We conducted a retrospective, single-institution machine learning analysis of adult patients undergoing single or multilevel PCDF (2003–2023). Models were designed using 88 clinical variables and five census-derived Social Vulnerability Index (SVI) scores. Outcomes were 90-day readmission and HU (the unweighted sum of 18 post-discharge components including urgent visits, invasive procedures, non-routine testing, and imaging). Models were trained on 50 repeated 80/20 train–test splits with training-only preprocessing and hyperparameter tuning. Results: Among 1015 patients (mean age of 64.7, 59.0% male, 97.2% with multilevel fusions), 90-day readmission was 15.5% and mean HU score was 13.6 ± 9.0. Regarding readmission, the clinical-only logistic regression model was the best predictor (AUROC 0.65). For HU, clinical-only random forest performed best (MAE: 4.80, R²: 0.326). Adding SVI to the matched clinical-plus-SDH models did not improve prediction for either 90-day readmission or healthcare utilization. Length of stay, year of surgery, and several SVI measures were prominent contributors across both SHAP analyses. Conclusions: ML models integrating SDH and clinical factors available by index discharge modestly predicted readmission and HU after PCDF. However, adding SVI did not meaningfully increase their overall performance, and the models require external validation before clinical use.

Background: Delta large-channel endoscopic decompression is an emerging, minimally invasive approach for lumbar degenerative disease, but its comparative effectiveness and perioperative performance have not been comprehensively synthesized. We performed a systematic review and meta-analysis to evaluate clinical, functional, and safety outcomes of Delta large-channel endoscopy relative to established decompression techniques. Methods: PubMed, Embase, and Scopus were searched from database inception through July 2025 (PROSPERO #CRD420251107750). Peer-reviewed English-language studies reporting extractable outcomes after Delta large-channel endoscopic surgery in adults were included. Random-effects meta-analyses were used for pooled comparisons. Results: Nine studies met the inclusion criteria, comprising 737 patients overall, including 379 treated with Delta large-channel endoscopy and 358 treated with comparator procedures. Reported outcome assessment generally ranged from 1 week to 12 months postoperatively, or variable latest follow-up timepoints, and mean follow-up was inconsistently reported. All studies originated in China and included five retrospective cohorts, two randomized controlled trials, one prospective cohort, and one case series. The pooled mean operative time for Delta procedures was 88.28 min (95% CI, 79.24–97.31), pooled mean intraoperative blood loss was 24.58 mL (95% CI, 11.14–38.02), and pooled mean hospital stay was 4.59 days (95% CI, 2.87–6.31). Compared with microscopic, endoscopic, and open techniques, Delta large-channel endoscopy showed no statistically significant differences in operative time (MD = 6.95 min, 95% CI: −11.51–25.40 min; p = 0.4037), intraoperative blood loss (MD, −40.62 mL; 95% CI, −83.68–2.44; p = 0.0598), 3-month ODI change from baseline (MD, 1.26; 95% CI, −2.17–4.69; p = 0.3661), or complication rates (OR, 0.67; 95% CI, 0.40–1.12; p = 0.1094). Delta procedures were associated with shorter hospital stay (MD, −1.69 days; 95% CI, −2.83 to −0.56; p = 0.0122) and marginally greater improvement in six-month VAS low back pain change from baseline (MD, 0.28; 95% CI, 0.26–0.29; p = 0.0002), though clinically insignificant. The pooled complication rate for Delta procedures was 6.0% (95% CI, 4–10%) and reported rates of excellent or good MacNab outcomes ranged from 80 to 93% across Delta cohorts. Conclusions: Delta large-channel endoscopy may provide clinical and functional outcomes comparable to established decompression techniques, with similar safety and potential perioperative benefits, including shorter hospitalization. However, these findings are based on limited, low-certainty evidence with high heterogeneity and should be interpreted as exploratory rather than definitive. Additional multicenter studies with longer follow-up, broader geographic representation, and higher methodological quality are necessary before definitive conclusions regarding comparative effectiveness can be established.

Objective: Online patient education materials (OPEMs) are important resources for patients seeking health information. While the National Institutes of Health (NIH) and American Medical Association (AMA) recommend a sixth-grade readability level for OPEMs, commonly available material often exceeds such criteria. Large language models (LLMs), such as ChatGPT and Gemini, have emerged as tools for health education with potential applications in simplification of health material. This study assesses the utility of ChatGPT and Gemini in enhancing the readability of OPEMs for peripheral nerve surgeries. Methods: Eleven common peripheral nerve surgeries were used as online search terms. The first 20 unique search results were assessed; results were excluded if they did not include patient-facing material. ChatGPT and Gemini were instructed to rewrite the text of the OPEM at or below a sixth-grade reading level. Readability metrics were calculated for original OPEMs, alongside ChatGPT and Gemini rewrites. LLM responses were reviewed for accuracy/quality (five-point scale) and comprehensiveness (three-point scale) using predefined criteria. Results: A total of 220 websites were assessed. In total, 155 OPEMs met the inclusion criteria; 65 websites were excluded because they were academic journal articles or other provider-facing materials. The average Flesch–Kincaid grade level (FKGL) of OPEMs was 11.3, significantly greater than the NIH/AMA-sixth grade recommendations (p < 0.001). The average FKGL of ChatGPT rewrites was significantly lower than that of OPEMs (11.3 vs. 7.5, p < 0.001), as was the average FKGL of Gemini rewrites (11.3 vs. 5.6, p < 0.001). ChatGPT rewrites were of higher accuracy/quality (4.5/5.0 vs. 4.0/5.0, p < 0.001) and comprehensiveness (2.0/3.0 vs. 1.0/3.0, p < 0.001) relative to Gemini rewrites. Conclusions: The readability of online patient education materials for peripheral nerve surgery significantly exceeded NIH/AMA recommendations. ChatGPT and Gemini were able to significantly simplify the reading level of these OPEMs. LLMs may serve as tools to improve the readability of peripheral nerve surgery OPEMs.

Study Design: Retrospective cohort study. Objective: The aim of this study was to evaluate the association between preoperative opioid use and postoperative health care utilization following elective lumbar spine surgery, and to characterize differences in surgical indications and procedures between opioid-naive (ON) and opioid-experienced (OE) patients. Summary of Background Data: The U.S. opioid crisis continues to cause thousands of deaths yearly. Despite fewer prescriptions nationally, opioids remain common for pain control in spine surgery, where over half of the patients use them preoperatively. Methods: Adults who underwent elective lumbar decompression with or without fusion between 2013 and 2018 at a single academic center were retrospectively reviewed. Patients were classified as OE if they had at least one opioid prescription within 60 days preoperatively. Demographics, surgical details, and postoperative health care utilization within 1 year, which included imaging, urgent care visits, physical therapy, pain referrals, and neuromodulator prescriptions, were compared between the OE and ON groups. Unadjusted and adjusted multivariable regression and sensitivity analyses were conducted to assess independent associations. Results: Among 433 patients, 70.5% were OE and 29.5% were ON. On unadjusted analysis, OE patients had significantly higher rates of neuromodulator prescriptions at 180 days ( P <.0001) and total imaging studies at 1 year ( P =.0014). After multivariable adjustment, preoperative opioid use remained independently associated with increased neuromodulator prescriptions at 180 days (β=0.23, P =.0069) and higher odds of persistent opioid use at 1 year (OR: 2.35, 95% CI: 1.15–4.83, P =.0196). No significant differences were observed in total imaging, lumbar x-ray imaging, or urgent care utilization after adjustment. Conclusions: Preoperative opioid use is associated with increased postoperative neuromodulator use and a higher risk of long-term opioid persistence following lumbar spine surgery. These findings highlight the need for targeted perioperative interventions to improve surgical outcomes.