Machine Learning Predicts Recurrent Lumbar Disc Herniation Following Percutaneous Endoscopic Lumbar Discectomy

STUDY DESIGN

Retrospective study.

OBJECTIVES

To develop machine learning (ML) models to predict recurrent lumbar disc herniation (rLDH) following percutaneous endoscopic lumbar discectomy (PELD).

METHODS

We retrospectively analyzed 1159 patients who had undergone single-level PELD for lumbar disc herniation (LDH) between July 2014 to December 2019 at our institution. Various preoperative imaging variables and demographic metrics were brought in analysis. Student's t test and Chi-squared test were applied for univariate analysis, which were feature selection for ML models. We established ML models to predict rLDH: Artificial neural networks (ANN), Extreme Gradient Boost classifier (XGBoost), KNeighborsClassifier (KNN), Decision tree classifier (Decision Tree), Random forest classifier (Random Forest), and support vector classifier (SVC).

RESULTS

A total 130 patients (11.22%) were diagnosed as rLDH in 1159 patients. Recurrence occurred within 10.25 ± 11.05 months. Body mass index (BMI) (P = .027), facet orientation (FO) (P < .001), herniation type (P = .012), Modic changes (P = .004), and disc calcification (P = .013) are significant factors in univariate analysis (P < .05). Extreme Gradient Boost classifier, Random Forest, ANN showed fine area under the curve, .9315, .9220, and .8814 respectively.

CONCLUSION

We developed a deep learning and 2 ensemble models with fine performance in prediction of rLDH following PELD. Predicting re-herniation before surgery has the potential to optimize decision-making and meaningfully decrease the rates of rLDH following PELD. Our ML model identified higher BMI, lower FO, Modic changes, disc calcification in a non-protrusive region, and herniation type (noncontained herniation) as significant features for predicting rLDH.

High mutation rates explain low population genetic divergence at copy-number-variable loci in Homo sapiens

Copy-number-variable (CNV) loci differ from single nucleotide polymorphic (SNP) sites in size, mutation rate, and mechanisms of maintenance in natural populations. It is therefore hypothesized that population genetic divergence at CNV loci will differ from that found at SNP sites. Here, we test this hypothesis by analysing 856 CNV loci from the genomes of 1184 healthy individuals from 11 HapMap populations with a wide range of ancestry. The results show that population genetic divergence at the CNV loci is generally more than three times lower than at genome-wide SNP sites. Populations generally exhibit very small genetic divergence (G_st = 0.05 ± 0.049). The smallest divergence is among African populations (G_st = 0.0081 ± 0.0025), with increased divergence among non-African populations (G_st = 0.0217 ± 0.0109) and then among African and non-African populations (G_st = 0.0324 ± 0.0064). Genetic diversity is high in African populations (~0.13), low in Asian populations (~0.11), and intermediate in the remaining 11 populations. Few significant linkage disequilibria (LDs) occur between the genome-wide CNV loci. Patterns of gametic and zygotic LDs indicate the absence of epistasis among CNV loci. Mutation rate is about twice as large as the migration rate in the non-African populations, suggesting that the high mutation rates play dominant roles in producing the low population genetic divergence at CNV loci.

Quantification of photocyanine in human serum by high-performance liquid chromatography-tandem mass spectrometry and its application in a pharmacokinetic study

Photocyanine is a novel anticancer drug. Its pharmacokinetic study in cancer patients is therefore very important for choosing doses, and dosing intervals in clinical application. A rapid, selective and sensitive high-performance liquid chromatography-tandem mass spectrometry (HPLC-MS/MS) method was developed and validated for the determination of photocyanine in patient serum. Sample preparation involved one-step protein precipitation by adding methanol and N,N-dimethyl formamide to 0.1 mL serum. The detection was performed on a triple quadrupole tandem mass spectrometer operating in multiple reaction-monitoring (MRM) mode. Each sample was chromatographed within 7 min. Linear calibration curves were obtained for photocyanine at a concentration range of 20-2000 ng/mL (r > 0.995), with the lower limit of quantification (LLOQ) being 20 ng/mL. The intrabatch accuracy ranged from 101.98% to 107.54%, and the interbatch accuracy varied from 100.52% to 105.62%. Stability tests showed that photocyanine was stable throughout the analytical procedure. This study is the first to utilize the HPLC-MS/MS method for the pharmacokinetic study of photocyanine in six cancer patients who had received a single dose of photocyanine (0.1 mg/kg) administered intravenously.

The highly reduced genome of an enslaved algal nucleus

Chromophyte algae differ fundamentally from plants in possessing chloroplasts that contain chlorophyll c and that have a more complex bounding-membrane topology. Although chromophytes are known to be evolutionary chimaeras of a red alga and a non-photosynthetic host, which gave rise to their exceptional membrane complexity, their cell biology is poorly understood. Cryptomonads are the only chromophytes that still retain the enslaved red algal nucleus as a minute nucleomorph. Here we report complete sequences for all three nucleomorph chromosomes from the cryptomonad Guillardia theta. This tiny 551-kilobase eukaryotic genome is the most gene-dense known, with only 17 diminutive spliceosomal introns and 44 overlapping genes. Marked evolutionary compaction hundreds of millions of years ago eliminated nearly all the nucleomorph genes for metabolic functions, but left 30 for chloroplast-located proteins. To allow expression of these proteins, nucleomorphs retain hundreds of genetic-housekeeping genes. Nucleomorph DNA replication and periplastid protein synthesis require the import of many nuclear gene products across endoplasmic reticulum and periplastid membranes. The chromosomes have centromeres, but possibly only one loop domain, offering a means for studying eukaryotic chromosome replication, segregation and evolution.

HLA-DP epitope typing using monoclonal antibodies

We have made a panel of murine anti-DP monoclonal antibodies for serological typing of HLA-DP polymorphisms; they can be used in microcytotoxicity (for 7 epitopes) and binding assays (for 8 epitopes). The antibodies detect polymorphic differences in both alpha and beta chains. As immunogens we sometimes used B-lymphoblastoid lines or purified DP molecules but mostly used mouse fibroblast transfectants expressing DP molecules. The DP beta genes were made from a cloned DPB1*0201 gene by replacing its major area of polymorphism with matching stretches of DNA amplified from other alleles; cloned DPA1*01 and DPA1*02 genes were used for transfection along with the beta chain genes. The monoclonal antibodies showed reaction patterns that correlated with the presence of particular amino-acid sequence motifs; thus none of the antibodies is allele-specific. They bind instead to epitopes which are found on a number of different HLA-DP types. We have constructed frequency tables so that the epitope (motif) data can be interpreted as the most likely genotype in each case. The basic assumption to justify this work is that HLA-DP matching or mismatching will likely influence transplant outcome, particularly in bone marrow transplantation. The present challenge is to define permissive and nonpermissive combinations of HLA-DP; it may be that matching for epitopes, rather than for full alleles, will help to resolve this issue.