Digital Phenotyping, Wearables, and Outcomes

There is a significant need for robust and objective outcome assessments in spine surgery. Constant monitoring via smartphones and wearable devices has the potential to fill this role by providing an in-depth picture of human well-being, creating an unprecedented amount of objective data to augment clinical decision-making. The metrics obtained from continuous patient monitoring increase the amount and ecological validity of data relevant to spine surgery. This can provide physicians with patient and disease-specific medical information, facilitating personalized patient care.

Lumbar Spinal Canal Segmentation in Cases with Lumbar Stenosis Using Deep-U-Net Ensembles

BACKGROUND

Narrowing of the lumbar spinal canal, or lumbar stenosis (LS), may cause debilitating radicular pain or muscle weakness. It is the most frequent indication for spinal surgery in the elderly population. Modern diagnosis relies on magnetic resonance imaging and its inherently subjective interpretation. Diagnostic rigor, accuracy, and speed may be improved by automation. In this work, we aimed to determine whether a deep-U-Net ensemble trained to segment spinal canals on a heterogeneous mix of clinical data is comparable to radiologists' segmentation of these canals in patients with LS.

METHODS

The deep U-nets were trained on spinal canals segmented by physicians on 100 axial T2 lumbar magnetic resonance imaging selected randomly from our institutional database. Test data included a total of 279 elderly patients with LS that were separate from the training set.

RESULTS

Machine-generated segmentations (MA) were qualitatively similar to expert-generated segmentations (ME1, ME2). Machine- and expert-generated segmentations were quantitatively similar, as evidenced by Dice scores (MA vs. ME1: 0.88 ± 0.04, MA vs. ME2: 0.89 ± 0.04), the Hausdorff distance (MA vs. ME1: 11.7 mm ± 13.8, MA vs. ME2: 13.1 mm ± 16.3), and average surface distance (MAvs. ME1: 0.18 mm ± 0.13, MA vs. ME2 0.18 mm ± 0.16) metrics. These metrics are comparable to inter-rater variation (ME1 vs. ME2 Dice scores: 0.94 ± 0.02, the Hausdorff distances: 9.3 mm ± 15.6, average surface distances: 0.08 mm ± 0.09).

CONCLUSION

We conclude that machine learning algorithms can segment lumbar spinal canals in LS patients, and automatic delineations are both qualitatively and quantitatively comparable to expert-generated segmentations.

Predictors of Operative Duration and Complications in Single-Level Posterior Interbody Fusions for Degenerative Spondylolisthesis

BACKGROUND

The goal of this study was to identify predictors of prolonged operative time (OT) in patients receiving posterior/transforaminal lumbar interbody fusion (P/TLIF) and examine the relationship between prolonged OT and perioperative outcomes in this population.

METHODS

The American College of Surgeons National Surgical Quality Improvement Program database was queried for patients undergoing single-level P/TLIF (Common Procedural Terminology code) between 2012 and 2018. Multivariable linear regression models were constructed to identify factors independently associated with changes in OT and examine the relationship between prolonged OT and perioperative outcomes (overall complications, surgical complications, medical complications, 30-day readmission, 30-day reoperation, and length of stay). All models were adjusted for sociodemographic variables, comorbidities, and procedure-specific variables.

RESULTS

Our cohort included 6260 patients. After adjusting for baseline covariates, age between 19 and 39 years increased OT by 15.14 minutes, male sex increased OT by 12.91 minutes, African American race increased OT by 17.82 minutes, other race increased OT by 18.13 minutes, obesity class III increased OT by 27.80 minutes, and the use of navigation increased OT by 10.83 minutes. Our multivariate logistic regression also found that after 2 hours, each additional hour of OT was associated with an increased risk of any complication (3-3.99 hours, odds ratio [OR], 1.68; 4-4.99 hours, OR, 2.33; and >5 hours, OR, 4.65). Incremental increases in OT were also associated with an increased risk of extended length of stay, readmission, and return to the operating room.

CONCLUSIONS

The results of this study highlight several factors associated with prolonged OT and underscore its association with poorer perioperative outcomes. These data can be used to risk stratify patients before single-level P/TLIF.

Predicting Spinal Surgery Candidacy From Imaging Data Using Machine Learning

BACKGROUND

The referral process for consultation with a spine surgeon remains inefficient, given a substantial proportion of referrals to spine surgeons are nonoperative.

OBJECTIVE

To develop a machine-learning-based algorithm which accurately identifies patients as candidates for consultation with a spine surgeon, using only magnetic resonance imaging (MRI).

METHODS

We trained a deep U-Net machine learning model to delineate spinal canals on axial slices of 100 normal lumbar MRI scans which were previously delineated by expert radiologists and neurosurgeons. We then tested the model against lumbar MRI scans for 140 patients who had undergone lumbar spine MRI at our institution (60 of whom ultimately underwent surgery, and 80 of whom did not). The model generated automated segmentations of the lumbar spinal canals and calculated a maximum degree of spinal stenosis for each patient, which served as our biomarker for surgical pathology warranting expert consultation.

RESULTS

The machine learning model correctly predicted surgical candidacy (ie, whether patients ultimately underwent lumbar spinal decompression) with high accuracy (area under the curve = 0.88), using only imaging data from lumbar MRI scans.

CONCLUSION

Automated interpretation of lumbar MRI scans was sufficient to correctly determine surgical candidacy in nearly 90% of cases. Given that a significant proportion of referrals placed for spine surgery evaluation fail to meet criteria for surgical intervention, our model could serve as a valuable tool for patient triage and thereby address some of the inefficiencies within the outpatient surgical referral process.

Eigenrank by committee: Von-Neumann entropy based data subset selection and failure prediction for deep learning based medical image segmentation

Manual delineation of anatomy on existing images is the basis of developing deep learning algorithms for medical image segmentation. However, manual segmentation is tedious. It is also expensive because clinician effort is necessary to ensure correctness of delineation. Consequently most algorithm development is based on a tiny fraction of the vast amount of imaging data collected at a medical center. Thus, selection of a subset of images from hospital databases for manual delineation - so that algorithms trained on such data are accurate and tolerant to variation, becomes an important challenge. We address this challenge using a novel algorithm. The proposed algorithm named 'Eigenrank by Committee' (EBC) first computes the degree of disagreement between segmentations generated by each DL model in a committee. Then, it iteratively adds to the committee, a DL model trained on cases where the disagreement is maximal. The disagreement between segmentations is quantified by the maximum eigenvalue of a Dice coefficient disagreement matrix a measure closely related to the Von Neumann entropy. We use EBC for selecting data subsets for manual labeling from a larger database of spinal canal segmentations as well as intervertebral disk segmentations. U-Nets trained on these subsets are used to generate segmentations on the remaining data. Similar sized data subsets are also randomly sampled from the respective databases, and U-Nets are trained on these random subsets as well. We found that U-Nets trained using data subsets selected by EBC, generate segmentations with higher average Dice coefficients on the rest of the database than U-Nets trained using random sampling (p < 0.05 using t-tests comparing averages). Furthermore, U-Nets trained using data subsets selected by EBC generate segmentations with a distribution of Dice coefficients that demonstrate significantly (p < 0.05 using Bartlett's test) lower variance in comparison to U-Nets trained using random sampling for all datasets. We believe that this lower variance indicates that U-Nets trained with EBC are more robust than U-Nets trained with random sampling.

Quantitative Analysis of Spinal Canal Areas in the Lumbar Spine: An Imaging Informatics and Machine Learning Study

BACKGROUND AND PURPOSE

Quantitative imaging biomarkers have not been established for the diagnosis of spinal canal stenosis. This work aimed to lay the groundwork to establish such biomarkers by leveraging the developments in machine learning and medical imaging informatics.

MATERIALS AND METHODS

Machine learning algorithms were trained to segment lumbar spinal canal areas on axial views and intervertebral discs on sagittal views of lumbar MRIs. These were used to measure spinal canal areas at each lumbar level (L1 through L5). Machine-generated delineations were compared with 2 sets of human-generated delineations to validate the proposed techniques. Then, we use these machine learning methods to delineate and measure lumbar spinal canal areas in a normative cohort and to analyze their variation with respect to age, sex, and height using a variable-intercept mixed model.

RESULTS

We established that machine-generated delineations are comparable with human-generated segmentations. Spinal canal areas as measured by machine are statistically significantly correlated with height (P < .05) but not with age or sex.

CONCLUSIONS

Our machine learning methodology demonstrates that this important anatomic structure can be accurately detected and quantitatively measured without human input in a manner comparable with that of human raters. Anatomic deviations measured against the normative model established here could be used to flag spinal stenosis in the future.

Natural history of the aging spine: a cross-sectional analysis of spinopelvic parameters in the asymptomatic population

OBJECTIVE

There have been numerous studies demonstrating increased pain and disability when patients' spinopelvic parameters fall outside of certain accepted ranges. However, these values were established based on patients suffering from spinal deformities. It remains unknown how these parameters change over a lifetime in asymptomatic individuals. The goal of this study was to define a range of spinopelvic parameters from asymptomatic individuals.

METHODS

Sagittal scoliosis radiographs of 210 asymptomatic patients were evaluated. All measurements were reviewed by 2 trained observers, supervised by a trained clinician. The following parameters and relationships were measured or calculated: cervical lordosis (CL), thoracic kyphosis (TK), lumbar lordosis (LL), pelvic incidence (PI), sagittal vertical axis (SVA), cervical SVA (cSVA), and T1 slope, TK/LL, truncal inclination, pelvic tilt (PT), LL-PI, LL/PI, and T1 slope/PI. Patients were stratified by decade of life, and regression analysis was performed to delineate the relationship between each consecutive age group and the aforementioned parameters.

RESULTS

Cervical lordosis (R2 = 0.61), thoracic kyphosis (R2 = 0.84), SVA (R2 = 0.88), cSVA (R2 = 0.51), and T1 slope (R2 = 0.77) all increase with age. Truncal inclination (R2 = 0.36) and T1 slope/CL remain stable over all decades (R2 = 0.01). LL starts greater than PI, but in the 6th decade of life, LL becomes equal to PI and in the 7th decade becomes smaller than PI (R2 = 0.96). The ratio of TK/LL is stable until the 7th decade of life (R2 = 0.81), whereas PT is stable until the 6th decade (R2 = 0.92).

CONCLUSIONS

This study further refines the generally accepted LL = PI + 10° by showing that patients under the age of 50 years should have more LL compared to PI, whereas after the 5th decade the relationship is reversed. SVA was not as sensitive across age groups, exhibiting a marked increase only in the 7th decade of life. Given the reliable increase of CL with age, and the stability of T1 slope/CL, this represents another important relationship that should be maintained when performing cervical deformity/fusion surgery. This study has important implications for evaluating adult patients with spinal deformities and for establishing corrective surgical goals.

Quantitative Analysis of Neural Foramina in the Lumbar Spine: An Imaging Informatics and Machine Learning Study

Purpose

To use machine learning tools and leverage big data informatics to statistically model the variation in the area of lumbar neural foramina in a large asymptomatic population.

Materials and Methods

By using an electronic health record and imaging archive, lumbar MRI studies in 645 male (mean age, 50.07 years) and 511 female (mean age, 48.23 years) patients between 20 and 80 years old were identified. Machine learning algorithms were used to delineate lumbar neural foramina autonomously and measure their areas. The relationship between neural foraminal area and patient age, sex, and height was studied by using multivariable linear regression.

Results

Neural foraminal areas correlated directly with patient height and inversely with patient age. The associations involved were statistically significant (P < .01).

Conclusion

By using machine learning and big data techniques, a linear model encoding variation in lumbar neural foraminal areas in asymptomatic individuals has been established. This model can be used to make quantitative assessments of neural foraminal areas in patients by comparing them to the age-, sex-, and height-adjusted population averages.© RSNA, 2019Supplemental material is available for this article.

Critical care usage after major gastrointestinal and liver surgery: a prospective, multicentre observational study

BACKGROUND

Patient selection for critical care admission must balance patient safety with optimal resource allocation. This study aimed to determine the relationship between critical care admission, and postoperative mortality after abdominal surgery.

METHODS

This prespecified secondary analysis of a multicentre, prospective, observational study included consecutive patients enrolled in the DISCOVER study from UK and Republic of Ireland undergoing major gastrointestinal and liver surgery between October and December 2014. The primary outcome was 30-day mortality. Multivariate logistic regression was used to explore associations between critical care admission (planned and unplanned) and mortality, and inter-centre variation in critical care admission after emergency laparotomy.

RESULTS

Of 4529 patients included, 37.8% (n=1713) underwent planned critical care admissions from theatre. Some 3.1% (n=86/2816) admitted to ward-level care subsequently underwent unplanned critical care admission. Overall 30-day mortality was 2.9% (n=133/4519), and the risk-adjusted association between 30-day mortality and critical care admission was higher in unplanned [odds ratio (OR): 8.65, 95% confidence interval (CI): 3.51-19.97) than planned admissions (OR: 2.32, 95% CI: 1.43-3.85). Some 26.7% of patients (n=1210/4529) underwent emergency laparotomies. After adjustment, 49.3% (95% CI: 46.8-51.9%, P<0.001) were predicted to have planned critical care admissions, with 7% (n=10/145) of centres outside the 95% CI.

CONCLUSIONS

After risk adjustment, no 30-day survival benefit was identified for either planned or unplanned postoperative admissions to critical care within this cohort. This likely represents appropriate admission of the highest-risk patients. Planned admissions in selected, intermediate-risk patients may present a strategy to mitigate the risk of unplanned admission. Substantial inter-centre variation exists in planned critical care admissions after emergency laparotomies.

Decision-making and Management of Ulnar Polydactyly of the Newborn: Outcomes and Satisfaction

BACKGROUND

Polydactyly is the most common congenital hand deformity. There is currently no consensus among pediatricians or hand surgeons regarding optimal management of ulnar (post-axial) type B polydactyly leading to uncertainty in initial treatment decisions for infants with this type of deformity.

METHODS

Parents of newborns with type B ulnar polydactyly were enrolled in a prospective, nonrandomized trial from 2010 to 2012. At enrollment they were offered: 1) no treatment, 2) suture ligature, 3) immediate excision under local anesthesia, and 4) delayed excision at four months of age under general anesthesia. After choosing a treatment option, parents were asked to complete an initial survey on their motivation for choosing a particular option, and then additional surveys at one and three month follow-up visits regarding outcomes and satisfaction.

RESULTS

Fourteen newborns were enrolled in the study. Eleven patients had bilateral polydactyly for a total of 25 hands involved in the study. With statistical significance, parents chose an immediate bedside excision over all options. No surgical complications were noted and satisfaction scores were 9.8 or higher in all groups.

CONCLUSIONS

A majority of parents whose children are born with type B post-axial polydactyly prefer to have the deformity addressed immediately with excision under local anesthesia at the bedside. This can be accomplished safely, with a satisfaction score of 9.8 out of 10 and no appreciable residual deformity. This may reduce emotional distress or embarrassment in parents who would otherwise have to deal with the deformity for at least a four-month period.

Olive Oil Polyphenols Differentially Inhibit Smooth Muscle Cell Proliferation through a G1/S Cell Cycle Block Regulated by ERK1/2

We hypothesized that polyphenols contained in olive oil play a role in reducing the risk of atherosclerosis. The aim of this study was to determine if the polyphenols in olive oil, oleuropein (Ole), hydroxytyrosol (HT), and tyrosol (Tyr) could inhibit smooth muscle cell (SMC) proliferation through its influence on cell cycle regulation. Bovine vascular SMC were cultured in the presence of Ole, HT, or Tyr at concentration of 1, 10, or 100 μmol/L. On days 1, 3, and 5, numbers of cells were counted. Cell cycle analysis was performed by flow cytometry on day 1 after SMC were stained with propidium iodide. Cell populations grown in the presence of Ole or HT at 100 μmol/L concentration were significantly inhibited after 5 days of exposure. Tyr had a similar tendency but it did not attain significance. Cell cycle analysis revealed that 66% of cells were in G1 phase in Ole group, compared with 48% in control group. To examine the cell cycle block between G1 and S phases, we performed Western blotting and found that ERK1/2 activation was inhibited by Ole or HT. We conclude that olive oil polyphenols could inhibit SMC proliferation through a cell cycle block between G1 and S phases which may be regulated by ERK1/2. These results demonstrate a mechanism by which olive oil consumption may be atheroprotective by inhibiting SMC proliferation.

Psychogenic mania and bereavement

Early notions of mania invoked a combination of psychogenic and organic factors, but psychogenic mania has not endured as a concept. We present a 37-year-old woman with an acute manic episode precipitated by the prolonged death of her husband from cancer. To our knowledge this is the first published account of 'maniacal grief' in the absence of pre-existing affective disorder, and with clear causal relations. Mania was clearly induced by the bereavement and we argue that the loss represented more than a non-specific life event. This case supports a re-examination of mania as potentially a 'reactive' or psychogenic phenomenon.

Treatment of resistant CAPD peritonitis by temporary discontinuation of peritoneal dialysis

Resistant continuous ambulatory peritoneal dialysis (CAPD) peritonitis (recurrent or persistent infection) is traditionally treated by removal of the CAPD catheter and a period off peritoneal dialysis. In a pilot study we have treated 8 patients with recurrent staphylococcal peritonitis and 3 patients with persistent staphylococcal peritonitis by stopping CAPD for a 2-week period, the CAPD catheter being left in-situ. All 8 patients with recurrent peritonitis and 2 of the 3 patients with persistent peritonitis had resolution of their infection; the third patient required catheter removal to clear the infection. There were no acute problems associated with stopping CAPD, and there was no evidence of loss of peritoneal filtration capacity on restarting CAPD. This novel approach to the treatment of resistant CAPD peritonitis should reduce the number of CAPD catheters replaced and therefore diminish the risks and inconvenience to patients that such replacements entail.

Localization of X-linked dominant Charcot-Marie-Tooth disease (CMT 2) to Xq13

A family is described in which Charcot-Marie-Tooth disease is inherited as an X-linked dominant mutation (CMT2). Ten DNA marker loci on the X chromosome were used to map the disease locus by linkage analysis. The DXYS1 sequence at Xq13 was found to be linked to the CMT2 locus at an estimated distance of 6 cM (Zmax = 2.87 at theta max = 0.06). The data also suggested close linkage of the CMT2 locus to PGK1 (Zmax = 1.51 at theta max = 0) which has also been mapped to Xq13. Another DNA locus (DXS3), in the Xq21.3----Xq22 region, did not show close linkage (Zmax = -2.231 at theta max = 0.01). We conclude that the CMT2 locus is probably in or close to band Xq13.

Effect of prostacyclin on the circulatory histamine during cardiopulmonary bypass

Changes in plasma histamine levels were studied in sixteen dogs under cardiopulmonary bypass (CPB) or bypass with the addition of prostacyclin (PGI2) infusion. In both groups, plasma histamine rose immediately after anaesthetic induction (median above pre-induction: 0.4 ng/ml) and following heparin infusion (median above pre-induction: 0.7 ng/ml). During CPB, plasma histamine levels were elevated throughout the 90 minute period of perfusion (median above pre-induction: 0.5-1.2 ng/ml). PGI2 infusion reduced the elevation in plasma histamine levels (median above preinduction: 0-0.7 ng/ml). These data support the hypothesis that histamine release occurs during CPB. Platelet aggregation in the extracorporeal circuit may be contributory since prostacyclin premedication reduces histamine release.

Regional localization of 18 human X-linked DNA sequences

A series of human probes with unique sequences has been isolated from a recombinant phage library constructed with DNA obtained from a human-hamster hybrid cell line. This cell line contained the X chromosome as the only human component. For 18 of these probes, a human X-chromosome origin has been confirmed and they have been regionally assigned by a combination of techniques: dosage studies utilizing DNA from human fibroblasts carrying X-chromosome duplications and deletions; the presence or absence of hybridization to digested DNA from hybrid lines carrying fragments of the X chromosome; and in situ hybridization to metaphase chromosomes. The use of dosage as a means to regionally assign probes significantly improves resolution of the X chromosome.