A clinician's guide for developing a prediction model: a case study using real-world data of patients with castration-resistant prostate cancer

Medication Prescription Policy for US Veterans With Metastatic Castration-Resistant Prostate Cancer: Causal Machine Learning Approach

BACKGROUND

Prostate cancer is the second leading cause of death among American men. If detected and treated at an early stage, prostate cancer is often curable. However, an advanced stage such as metastatic castration-resistant prostate cancer (mCRPC) has a high risk of mortality. Multiple treatment options exist, the most common included docetaxel, abiraterone, and enzalutamide. Docetaxel is a cytotoxic chemotherapy, whereas abiraterone and enzalutamide are androgen receptor pathway inhibitors (ARPI). ARPIs are preferred over docetaxel due to lower toxicity. No study has used machine learning with patients' demographics, test results, and comorbidities to identify heterogeneous treatment rules that might improve the survival duration of patients with mCRPC.

OBJECTIVE

This study aimed to measure patient-level heterogeneity in the association of medication prescribed with overall survival duration (in the form of follow-up days) and arrive at a set of medication prescription rules using patient demographics, test results, and comorbidities.

METHODS

We excluded patients with mCRPC who were on docetaxel, cabaxitaxel, mitoxantrone, and sipuleucel-T either before or after the prescription of an ARPI. We included only the African American and white populations. In total, 2886 identified veterans treated for mCRPC who were prescribed either abiraterone or enzalutamide as the first line of treatment from 2014 to 2017, with follow-up until 2020, were analyzed. We used causal survival forests for analysis. The unit level of analysis was the patient. The primary outcome of this study was follow-up days indicating survival duration while on the first-line medication. After estimating the treatment effect, a prescription policy tree was constructed.

RESULTS

For 2886 veterans, enzalutamide is associated with an average of 59.94 (95% CI 35.60-84.28) more days of survival than abiraterone. The increase in overall survival duration for the 2 drugs varied across patient demographics, test results, and comorbidities. Two data-driven subgroups of patients were identified by ranking them on their augmented inverse-propensity weighted (AIPW) scores. The average AIPW scores for the 2 subgroups were 19.36 (95% CI -16.93 to 55.65) and 100.68 (95% CI 62.46-138.89). Based on visualization and t test, the AIPW score for low and high subgroups was significant (P=.003), thereby supporting heterogeneity. The analysis resulted in a set of prescription rules for the 2 ARPIs based on a few covariates available to the physicians at the time of prescription.

CONCLUSIONS

This study of 2886 veterans showed evidence of heterogeneity and that survival days may be improved for certain patients with mCRPC based on the medication prescribed. Findings suggest that prescription rules based on the patient characteristics, laboratory test results, and comorbidities available to the physician at the time of prescription could improve survival by providing personalized treatment decisions.

An external validation of a novel predictive algorithm for male nipple areolar positioning: an improvement to current practice through a multicenter endeavor

The correct positioning of nipple-areolar complexes (NAC) during gender-affirming mastectomies remains a particular challenge. Recently, a Dutch two-step algorithm was proposed predicting the most ideal NAC-position derived from a large cisgender male cohort. We aimed to externally validate this algorithm in a Belgian cohort. The Belgian validation cohort consisted of cisgender men. Based on patient-specific anthropometry, the algorithm predicts nipple-nipple distance (NN) and sternal-notch-to-nipple distance (SNN). Predictions were externally validated using the performance measures: R2-value, means squared error (MSE) and mean absolute percentage error (MAPE). Additionally, data were collected from a Belgian and Dutch cohort of transgender men having undergone mastectomy with free nipple grafts. The observed and predicted NN and SNN were compared and the inter-center variability was assessed. A total of 51 Belgian cisgender and 25 transgender men were included, as well as 150 Dutch cisgender and 96 transgender men. Respectively, the performance measures (R2-value, MSE and MAPE) for NN were 0.315, 2.35 (95%CI:0-6.9), 4.9% (95%CI:3.8-6.1) and 0.423, 1.51 (95%CI:0-4.02), 4.73%(95%CI:3.7-5.7) for SNN. When applying the algorithm to both transgender cohorts, the predicted SNN was larger in both Dutch (17.1measured(±1.7) vs. 18.7predicted(±1.4), p= <0.001) and Belgian (16.2measured(±1.8) vs. 18.4predicted(±1.5), p= <0.001) cohorts, whereas NN was too long in the Belgian (22.0measured(±2.6) vs. 21.2predicted(±1.6), p = 0.025) and too short in the Dutch cohort (19.8measured(±1.8) vs. 20.7predicted(±1.9), p = 0.001). Both models performed well in external validation. This indicates that this two-step algorithm provides a reproducible and accurate clinical tool in determining the most ideal patient-tailored NAC-position in transgender men seeking gender-affirming chest surgery.

Inhibition of IL1R1 or CASP4 attenuates spinal cord injury through ameliorating NLRP3 inflammasome-induced pyroptosis

Spinal cord injury (SCI) is a devastating trauma characterized by serious neuroinflammation and permanent neurological dysfunction. However, the molecular mechanism of SCI remains unclear, and few effective medical therapies are available at present. In this study, multiple bioinformatics methods were used to screen out novel targets for SCI, and the mechanism of these candidates during the progression of neuroinflammation as well as the therapeutic effects were both verified in a rat model of traumatic SCI. As a result, CASP4, IGSF6 and IL1R1 were identified as the potential diagnostic and therapeutic targets for SCI by computational analysis, which were enriched in NF-κB and IL6-JAK-STATA3 signaling pathways. In the injured spinal cord, these three signatures were up-regulated and closely correlated with NLRP3 inflammasome formation and gasdermin D (GSDMD) -induced pyroptosis. Intrathecal injection of inhibitors of IL1R1 or CASP4 improved the functional recovery of SCI rats and decreased the expression of these targets and inflammasome component proteins, such as NLRP3 and GSDMD. This treatment also inhibited the pp65 activation into the nucleus and apoptosis progression. In conclusion, our findings of the three targets shed new light on the pathogenesis of SCI, and the use of immunosuppressive agents targeting these proteins exerted anti-inflammatory effects against spinal cord inflammation by inhibiting NF-kB and NLRP3 inflammasome activation, thus blocking GSDMD -induced pyroptosis and immune activation.

Promoting Prognostic Model Application: A Review Based on Gliomas

Malignant neoplasms are characterized by poor therapeutic efficacy, high recurrence rate, and extensive metastasis, leading to short survival. Previous methods for grouping prognostic risks are based on anatomic, clinical, and pathological features that exhibit lower distinguishing capability compared with genetic signatures. The update of sequencing techniques and machine learning promotes the genetic panels-based prognostic model development, especially the RNA-panel models. Gliomas harbor the most malignant features and the poorest survival among all tumors. Currently, numerous glioma prognostic models have been reported. We systematically reviewed all 138 machine-learning-based genetic models and proposed novel criteria in assessing their quality. Besides, the biological and clinical significance of some highly overlapped glioma markers in these models were discussed. This study screened out markers with strong prognostic potential and 27 models presenting high quality. Conclusively, we comprehensively reviewed 138 prognostic models combined with glioma genetic panels and presented novel criteria for the development and assessment of clinically important prognostic models. This will guide the genetic models in cancers from laboratory-based research studies to clinical applications and improve glioma patient prognostic management.

Promoting Prognostic Model Application: A Review Based on Gliomas

Malignant neoplasms are characterized by poor therapeutic efficacy, high recurrence rate, and extensive metastasis, leading to short survival. Previous methods for grouping prognostic risks are based on anatomic, clinical, and pathological features that exhibit lower distinguishing capability compared with genetic signatures. The update of sequencing techniques and machine learning promotes the genetic panels-based prognostic model development, especially the RNA-panel models. Gliomas harbor the most malignant features and the poorest survival among all tumors. Currently, numerous glioma prognostic models have been reported. We systematically reviewed all 138 machine-learning-based genetic models and proposed novel criteria in assessing their quality. Besides, the biological and clinical significance of some highly overlapped glioma markers in these models were discussed. This study screened out markers with strong prognostic potential and 27 models presenting high quality. Conclusively, we comprehensively reviewed 138 prognostic models combined with glioma genetic panels and presented novel criteria for the development and assessment of clinically important prognostic models. This will guide the genetic models in cancers from laboratory-based research studies to clinical applications and improve glioma patient prognostic management.

The ideal location of the male nipple-areolar complex: A pinpointing algorithm

Background

In the treatment of gender dysphoria, appropriate nipple-areola complex (NAC) positioning is essential for achieving a natural appearing male chest after subcutaneous mastectomy. An accurate predictive model for the ideal personalized position of the NAC is still lacking. The aim of this study is to determine the anthropometry of the male chest to create individualized guidelines for appropriate NAC positioning in the preoperative setting.

Materials and methods

Cisgender male participants were recruited. Multiple chest measurements were manually recorded. Best subset regression using linear models was used to select predictors for the horizontal coordinate (nipple-nipple distance; NN) and vertical coordinate (sternal notch-nipple distance; SNN) of the NAC. Internal validation was assessed using bootstrapping. Furthermore, a cohort of transgender men who had received a mastectomy with replantation of nipples according to current practice was identified. Comparison testing between the algorithm and standard practice was performed to test the limitations of standard practice.

Results

One hundred and fifty cis male participants were included (median age: 26, IQR: 22-34 years). Four predictors were found to predict NN (age, weight, chest circumference (CC), anterior-axillar fold to anterior-axillar fold (AUX-AUX)) and reads as follows: NN = 4.11 + 0.035*age + 0.041*weight + 0.093*CC + 0.140*AUX-AUX Two predictors were found to predict SNN (NN and weight), and reads as follows: SNN = 7.248 + 0.303*NN + 0.072*weight. Both models performed well (Bootstrapped R2: 0.63 (NN), 0.50 (SNN)) and outperformed previous models predicting NAC position. Ninety-six transgender men were eligible for evaluation of current practice and showed an average placement error of -0.9 cm for NN and +2.2 cm for SNN.

Conclusion

The non-standardized approach of NAC repositioning results in a significant error of nipple placement. We suggest that the two predictive models for NN and SNN can be used to optimize NAC positioning on the masculinized chest wall.

Supplemental data for this article is available online at https://doi.org/10.1080/26895269.2021.1884926.