The research included patients enrolled in the institutional Spine Registry (SpineReg; ClinicalTrials.gov number: NCT03644407), which is a prospective observational registry recruiting patients undergoing spine surgery incepted in 2015 by our hospital IRCCS Orthopedic Institute Galeazzi of Milan (Italy). To answer the research question, we extracted from the registry the patients who met the following eligibility criteria: ≥18 years of age, enrolment between 2016 and 2019, the presence of at least one ODI assessment at 6-, 12-, or 24-month follow-up. The extraction excluded data of patients with a diagnosis of tumors, admission for complications, and surgical procedures involving the cervical spine. A 30% reduction from baseline was considered as the minimum clinically important difference (MCID) in the ODI score in order to categorize the outcomes (17). A secondary analysis was planned using the raw reduction of 12.7 points as classification threshold, which is more restrictive in categorizing successful surgeries (18). Patients who had a preoperative ODI < 12.7 were excluded from the extraction query. After data extraction and integration with routine parameters, the study sample comprised 1,392 patients with seventeen variables: gender, age, red blood cells (RBCs), hematocrit (Ht), serum concentration of hemoglobin (Hb), mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), mean corpuscular hemoglobin concentration (MCH), C-reactive protein (CRP), type of diagnosis, American society of anesthesiologists physical status classification system (ASA), duration of surgery (DS), length of hospital stay (LOS), preoperative ODI (PREOP ODI), 6-month ODI, 12-month ODI, and 24-month ODI. The number of missing values counted 85 CRP, 14 DS, 555 6-month ODI, 422 12-month ODI, and 731 24-month ODI.

The simple imputation technique of the last observation carried forward (LOCF) was used to include patients with incomplete 24-month ODI, with the last reported scores being used in place of the missing values. The months of follow-up were then weighed on the imputations, thus obtaining the ODI scores at 17 months (661 24-month ODI + 576 12-month ODI + 155 6-month ODI). In Table 1 is reported the structure of the dataset. Subsequently, three new variables were imputed. The first variable was the difference between the baseline ODI and the last ODI at 17 months (ΔODI PRE vs. last 17). The second variable was the presence or absence (1,0) of clinical improvement at 17 months (17-month progress 30%), calculated as a 30% decrease from baseline ODI to the last ODI at 17 months. The third variable was the presence or absence (1,0) of clinical improvement at 17 months (17-month progress 12.7), calculated as a raw reduction in the ODI score≥12.7 from baseline ODI to the last ODI at 17 months. Two new sets classified the sample by gender code (males = 0, females = 1) and diagnosis (spine deformities: 4, disc diseases: 5; back surgeries: 6). Specifically, the group of spine deformities included kyphosis and scoliosis, and the group of back surgeries included spondylosis, spondylolisthesis, stenosis, and elective treatment of fractures. The dataset was explored for what concerned the presence of outliers among the primary variables, and a new dataset for regression analysis was created after the elimination of outliers. The following number of outliers were excluded based on the interquartile range rule of three: 4 RBCs, 27 MCV, 36 MCH, 2 MCHC, 96 CRP, 2 DS, and 21 LOS.

The IBM SPSS 22 statistics package was used for all statistical analysis. The descriptive variables were reported as means, standard deviation, minimum and maximum values to be reported in Tables 2, 3 (baseline examination), regardless of the type of distribution. In Table 4 (outcome exploration) it was planned to report the most significant biochemical descriptors against the outcomes. Based on the results from the Shapiro-Wilk test on the dataset without outliers, Ht (p = 0.989), Hb (p = 0.281), and MCHC (p = 0.078) were assumed to have normal distribution. Age (p < 0.05), RBCs (p < 0.05), MCV (p < 0.05), MCH (p < 0.05), CRP (p < 0.05), DS (p < 0.05), LOS (p < 0.05), and baseline ODI (p < 0.05) were assumed to be skewed. The newly created dataset without outliers was used for running descriptive statistics, whereas the raw dataset was planned to be used for inferential statistics. The existence of a difference in the biochemical parameters between males and females was planned to be investigated through the independent t-test or the Mann-Whitney U-test for normally or not normally distributed values, respectively, and controlling for the homogeneity of variance by Levene's test for equality of variances (adjusted degree of freedom). The existence, strength, and direction of the association between the biochemical parameters and the demographic variable of age were examined using the Pearson product-moment correlation for continuous normally distributed variables or the Spearman rank-order correlation coefficient for skewed data. Regardless of data distribution, blood values and years of age were planned to be reported in scatter plots against the baseline ODI together with the Pearson's correlation and linear regression coefficients (unstandardized B). The difference between males and females in baseline ODI was investigated likewise through the Mann-Whitney U-test.

Concerning outcome exploration, the Chi-Square test was used to investigate the differences in gender between outcome groups at 17 months using both 30% reduction and the raw 12.7 points reduction. Similarly, it was planned the Mann-Whitney U-test for the years of age and the biochemical parameters, taking into account the result of Levene's test for equality of variances based on median (adjusted degree of freedom). The Chi-Square test was also used to investigate the different outcomes according to ASA, diagnosis, DS, and LOS. Subsequently, the probe of two prediction regression models was planned; the first model (PRE_BIO) would be based on the seven preoperative biochemical markers, while the second model (PERI_BIODEMCLI) would have included the biochemical, the demographic (gender and age), and the clinical (diagnosis, ASA, baseline ODI, DS, and LOS) variables. The prediction potential of each of the two models on the last ODI was explored through multiple regression analysis on the dataset without outliers. The models were planned to be based on the stepwise method to serially add the next strongest predictor feasibly removing the previously entered predictor not significant. The most significant predictors would be chosen to report the predictive equations. The Wilcoxon signed-rank test was run to match the regression predicted values from the estimated regression equation with the real values of the dataset. The main predictors of each model were tested for the clinically significant outcomes (1,0) by using binary logistic regression (enter method). Neural Networks (NN) analysis was planned to observe the forecasting outcome as a function of each variable-specific model: PRE_BIO(NN) and PERI_BIODEMCLI(NN). Given the non-linear nature of this tool, the authentications between inputs and outputs have been run on the raw dataset through the supervised learning technique of Multilayer Perceptron (MLP) procedure to produce a predictive model for clinical success based on the values of the demographic, biochemical, and clinical predictors. After data whitening (the distributions were rescaled so that the mean was zero and the standard deviation was one), the training sample was set at 70%, the testing sample to track prediction at 20%, and the holdout sample to assess the final NN at 10%. The NN architecture was planned to be based on two hidden layers with Sigmoid activation function (real-valued arguments are transformed to the range 0, 1) and on Softmax activation for the output layer (the vector of real-valued arguments is transformed to a vector whose elements fall in the range 0, 1 and sum to 1). The Receiver Operating Characteristic (ROC) curve evaluated the Area Under the Curve (AUC), the sensitivity (true positive outcome), specificity (true negative outcome), and 1–specificity (false positive rate) of model-specific predictors in three successive run of NN, with the normalized importance of the independent predictors independent being reported for the most significant multivariate model.

The demographic and preoperative biochemical variables are reported in Table 2. The study cohort showed a prevalence of about 41% of males and 59% of females, with men showing higher values than females of RBCs (05.02 ± 00.46 10⁶/μl vs. 04.58 ± 00.42 10⁶/μl; U = 104,835.00, Z = −17.389, p < 0.00001), Ht (44.53 ± 03.17% vs. 40.79 ± 03.12%; equalvariancest_{(1, 390)} = 21.833, p < 0.00001), Hb (14.93 ± 01.20 g/dl vs. 13.43 ± 01.14 g/dl; equalvariancest_{(1, 390)} = 23.722, p < 0.00001), MCH (29.84 ± 02.15 pg/cell vs. 29.40 ± 02.21 pg/cell; U = 182,475.00, Z = −5.633, p < 0.00001), and MCHC (33.53 ± 00.99 g/dl vs. 32.91 ± 00.96 g/dl; equalvariancest_{(1, 388)} = 11.909, p < 0.00001). No sex differences for MCV (88.98 ± 05.67 fl/cell in males vs. 89.28 ± 05.71 fl/cell in females; U = 219,466.00, Z = −0.742, p = 0.458) and CRP (00.34 ± 00.70 mg/dl in males vs. 00.35 ± 00.65 mg/dl in females; U = 173,124.00, Z = −0.665, p = 0.506).

Males had a mean age of 55.15 ± 15.63 years old and females had 57.28 ± 14.92 years old. A negative association was found between age and RBCs (Rho = −00.184, p < 0.00001), Ht (Rho = −00.116, p = 0.00001), Hb (Rho = −0.164, p < 0.00001), and MCHC (Rho = −00.207, p < 0.00001). Conversely, age positively associated with MCV (Rho = +00.203, p < 0.00001), MCH (Rho = +00.068, p = 0.012), and CRP (Rho = +00.198, p < 0.00001). The variables concerning surgical and anesthetic parameters are reported in Table 3, indicating data for each of the three clusters of spine diagnosis.

The association of sex, the years of age, and the biochemical markers with the ODI score at baseline are reported in Figure 1. There was found a positive association between the preoperative disability with the years of age (B = +0.197, p < 0.00001, 95% CI = +1.142: +0.253) and CRP (B = +10.985, p < 0.00001, 95% CI = +6.162: +15.807). An inverse association was observed for RBCs (B = −4.117, p < 0.00001, 95% CI = −5.931: −2.302), Ht (B = −0.579, p < 0.00001, 95% CI = −0.814: −0.343), Hb (B = −1.736, p < 0.00001, 95% CI = −2.355: −1.117), and MCHC (B = −1.829, p = 0.00003, 95% CI = −2.686: −0.972). No association were found with circulating MCV (B = 0.121, p = 0.219, 95% CI = −0.072: +0.314) or MCH (B = −0.176, p = 0.511, 95% CI = −0.701: +0.349). Men showed lower values of disability against women (42.42 ± 16.22% vs. 49.88 ± 15.86%; U = 172,804.50, Z = −8.294, p < 0.00001).

In the whole cohort, 1,022 patients recovered at least 30% from baseline ODI at 17 months, while the reduction of 12.7 points counted 1,019 successful outcomes. The recovery from disability considering 30% reduction showed an association with gender [χ₍₁₎ = 5.339, p = 0.021], with about 76.72% of males and 71.15% of females encountering a recovery. However, the gender association was not confirmed [χ₍₁₎ = 0.017, p = 0.895] after considering the reduction of 12.7 points. Patients with a unsuccessful recovery of at least 30% reduction were older at baseline (U = 156,017.50, Z = −4.990, p < 0.00001) with lower values of RBCs (U = 165,980.50, Z = −3.385, p = 0.001), Ht (U = 170331.50, Z = −2.828, p = 0.005), Hb (U = 163,994.50, Z = −3.786, p = 0.0001), MCHC (U = 158,815.00, Z = −4.521, p < 0.00001), but higher values of MCV (U = 164,810.00, Z = −2.603, p = 0.009). No differences for baseline MCH (U = 178,818.50, Z = −0.051, p = 0.960) and CRP (U = 130,854.50, Z = −1.711, p = 0.087). Considering the reduction of 12.7 points, the results were confirmed for age (p = 0.002), MCH (p = 0.920), MCHC (p = 0.026), and CRP (p = 0.540), but no differences were found for RBCs (p = 0.098), Ht (p = 0.122), Hb (p = 0.059), and MCV (p = 0.147). There was found a significant association between the 30% reduction and ASA [successful outcome in 81.07% with ASA 1, 72.55% with ASA 2, and 61.23% with ASA 3; χ₍₂₎ = 36.381, p = 0.00002], diagnosis [successful outcome in 61.11% of spine deformities, 80.57% of disc disease, and 70.07% of back surgeries; χ₍₂₎ = 36.381, p < 0.00001], DS (209.83 ± 137.15 vs. 248.13 ± 152.25 min; U = 156,271.50, Z = −4.339, p = 0.00001), and LOS (4.58 ± 3.35 vs. 5.53 ± 4.17 days; U = 155,719.00, Z = −4.077, p = 0.00004). Considering the reduction of 12.7 points, the results were confirmed for ASA (p = 0.016), diagnosis (p = 0.00001), DS (p = 0.002), and LOS (p = 0.005), with baseline ODI resulting different between groups (p < 0.00001).