OBJECTIVE: Phase-contrast MRI allows detailed measurements of various parameters of CSF motion. This examination is technically demanding and machine dependent. The literature on this topic is ambiguous. Machine learning (ML) approaches have already been successfully utilized in medical research, but none have yet been applied to enhance the results of CSF flowmetry. The aim of this study was to evaluate the possible contribution of ML algorithms in enhancing the utilization and results of MRI flowmetry in idiopathic normal pressure hydrocephalus (iNPH) diagnostics. METHODS: The study cohort consisted of 30 iNPH patients and 15 healthy controls examined on one MRI machine. All major phase-contrast parameters were inspected: peak positive, peak negative, and average velocities; peak amplitude; positive, negative, and average flow rates; and aqueductal area. The authors applied ML algorithms to 85 complex features calculated from a phase-contrast study. RESULTS: The most distinctive parameters with p < 0.005 were the peak negative velocity, peak amplitude, and negative flow. From the ML algorithms, the Adaptive Boosting classifier showed the highest specificity and best discrimination potential overall, with 80.4% ± 2.9% accuracy, 72.0% ± 5.6% sensitivity, 84.7% ± 3.8% specificity, and 0.812 ± 0.047 area under the receiver operating characteristic curve (AUC). The highest sensitivity was 85.7% ± 5.6%, reached by the Gaussian Naive Bayes model, and the best AUC was 0.854 ± 0.028 by the Extra Trees classifier. CONCLUSIONS: Feature extraction algorithms combined with ML approaches simplify the utilization of phase-contrast MRI. The highest-performing ML algorithm was Adaptive Boosting, which showed good calibration and discrimination on the testing data, with 80.4% accuracy, 72.0% sensitivity, 84.7% specificity, and 0.812 AUC. Phase-contrast MRI boosted by the ML approach can help to determine shunt-responsive iNPH patients.
To assess automated volumetric analysis as a potential presurgical diagnostic tool or as a method to potentially shed light on normal pressure hydrocephalus (NPH) pathophysiology. MRI imaging according to our protocol was performed in 29 NPH patients, 45 non-NPH (but suspected) patients and 15 controls. Twenty patients underwent a second MRI 3 months after ventriculoperitoneal (VP) shunt surgery. All structures relevant to NPH diagnosis were automatically segmented using commercial software. The results were subsequently tested using ANOVA analysis. Significant differences in the volumes of the corpus callosum, left hippocampus, internal globus pallidus, grey and white matter and ventricular volumes were observed between NPH group and healthy controls. However, the differences between NPH and non-NPH groups were non-significant. Three months after, VP shunt insertion decreased ventricular volume was the only clearly significant result (p value 0.0001). Even though a detailed volumetric study shows several significant differences, volumetric analysis as a standalone method does not provide a simple diagnostic biomarker, nor does it shed a light on an unknown NPH aetiology.
- MeSH
- kohortové studie MeSH
- lidé středního věku MeSH
- lidé MeSH
- magnetická rezonanční tomografie MeSH
- normotenzní hydrocefalus diagnóza patofyziologie chirurgie MeSH
- senioři MeSH
- velikost orgánu MeSH
- ventrikuloperitoneální zkrat MeSH
- výsledek terapie MeSH
- Check Tag
- lidé středního věku MeSH
- lidé MeSH
- mužské pohlaví MeSH
- senioři MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND: Ventriculoperitoneal shunt (VPS) placement is one of the most common neurosurgical procedures. VPSs are associated with high costs, which predominantly arise from relatively high complication and revision rates. It is reasonable to assume that revision rates in developing countries would be higher. In this study we report the single-institution revision rates and costs from a high-volume department in sub-Saharan Africa. METHODS: A pediatric neurosurgical database was studied in the extent of 5 years. The 30-day shunt failure rate, overall revision rate, and costs were calculated, and results were compared with previously published studies from developed countries. RESULTS: In the selected time period 1840 VPS surgeries were performed, of which 592 were shunt revisions (32.14%). The majority of revision surgeries was performed in the first year- 501 (representing 84.63%); second year, 64; third year, 21; fourth year, 6; and fifth year, 2. The overall shunt revision rate was 28.94% with a 30-day revision rate of 14.58%. During the course of the study, costs of VPS surgery, the shunt, and daily ward charges did not change significantly. The average total charge for VPS insertion was 60,000 KES (586 USD), VPS removal 30,000 KES (293 USD), and VPS revision 50,000 KES (489 USD). CONCLUSIONS: This retrospective study proves that VPSs, with their known complication risks, can be performed in a sub-Saharan missionary hospital with acceptable costs and results that are comparable with those achieved in some Western hospitals. Keys to those outcomes include high volume and a highly experienced team.
- MeSH
- délka pobytu trendy MeSH
- dítě MeSH
- lidé MeSH
- následné studie MeSH
- nemocnice - náklady * trendy MeSH
- neurochirurgické výkony ekonomika trendy MeSH
- pediatrie ekonomika trendy MeSH
- reoperace ekonomika trendy MeSH
- retrospektivní studie MeSH
- ventrikuloperitoneální zkrat ekonomika trendy MeSH
- Check Tag
- dítě MeSH
- lidé MeSH
- mužské pohlaví MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- Geografické názvy
- subsaharská Afrika MeSH
- MeSH
- dítě MeSH
- lékařské mise * MeSH
- lidé MeSH
- malformace nervového systému chirurgie MeSH
- neurochirurgické výkony * metody MeSH
- Check Tag
- dítě MeSH
- lidé MeSH
- Publikační typ
- novinové články MeSH
- Geografické názvy
- Keňa MeSH
- MeSH
- degenerace meziobratlové ploténky radiografie chirurgie MeSH
- diskektomie metody MeSH
- kohortové studie MeSH
- krční obratle radiografie MeSH
- kyfóza radiografie MeSH
- lidé MeSH
- lordóza radiografie MeSH
- retrospektivní studie MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- dopisy MeSH
- práce podpořená grantem MeSH
