RESUMEN

BACKGROUND: An inherent difference exists between male and female bodies, the historical under-representation of females in clinical trials widened this gap in existing healthcare data. The fairness of clinical decision-support tools is at risk when developed based on biased data. This paper aims to quantitatively assess the gender bias in risk prediction models. We aim to generalize our findings by performing this investigation on multiple use cases at different hospitals. METHODS: First, we conduct a thorough analysis of the source data to find gender-based disparities. Secondly, we assess the model performance on different gender groups at different hospitals and on different use cases. Performance evaluation is quantified using the area under the receiver-operating characteristic curve (AUROC). Lastly, we investigate the clinical implications of these biases by analyzing the underdiagnosis and overdiagnosis rate, and the decision curve analysis (DCA). We also investigate the influence of model calibration on mitigating gender-related disparities in decision-making processes. RESULTS: Our data analysis reveals notable variations in incidence rates, AUROC, and over-diagnosis rates across different genders, hospitals and clinical use cases. However, it is also observed the underdiagnosis rate is consistently higher in the female population. In general, the female population exhibits lower incidence rates and the models perform worse when applied to this group. Furthermore, the decision curve analysis demonstrates there is no statistically significant difference between the model's clinical utility across gender groups within the interested range of thresholds. CONCLUSION: The presence of gender bias within risk prediction models varies across different clinical use cases and healthcare institutions. Although inherent difference is observed between male and female populations at the data source level, this variance does not affect the parity of clinical utility. In conclusion, the evaluations conducted in this study highlight the significance of continuous monitoring of gender-based disparities in various perspectives for clinical risk prediction models.

Asunto(s)

RESUMEN

OBJECTIVES: The understanding of the role that cognitive and emotional factors play in how an individual recovers from a whiplash injury is important. Hence, we sought to evaluate whether pain-related cognitions (self-efficacy beliefs, expectation of recovery, pain catastrophizing, optimism, and pessimism) and emotions (kinesiophobia) are longitudinally associated with the transition to chronic whiplash-associated disorders in terms of perceived disability and perceived recovery at 6 and 12 months. METHODS: One hundred sixty-one participants with acute or subacute whiplash-associated disorder were included. The predictors were: self-efficacy beliefs, expectation of recovery, pain catastrophizing, optimism, pessimism, pain intensity, and kinesiophobia. The 2 outcomes were the dichotomized scores of perceived disability and recovery expectations at 6 and 12 months. Stepwise regression with bootstrap resampling was performed to identify the predictors most strongly associated with the outcomes and the stability of such selection. RESULTS: Baseline perceived disability, pain catastrophizing, and expectation of recovery were the most likely to be statistically significant, with an overage frequency of 87.2%, 84.0%, and 84.0%, respectively. CONCLUSION: Individuals with higher expectations of recovery and lower levels of pain catastrophizing and perceived disability at baseline have higher perceived recovery and perceived disability at 6 and 12 months. These results have important clinical implications as both factors are modifiable through health education approaches.

Asunto(s)

RESUMEN

BACKGROUND: Frozen shoulder (FS) is a highly disabling pathology of poorly understood etiology, which is characterized by the presence of intense pain and progressive loss of range of motion. The aim of this study was to evaluate the effect of adding a central nervous system (CNS)-focused approach to a manual therapy and home stretching program in people with FS. METHODS: A total of 34 patients with a diagnosis of primary FS were randomly allocated to receive a 12-week manual therapy and home stretching program or manual therapy and home stretching program plus a CNS-focused approach including graded motor imagery and sensory discrimination training. The Shoulder Pain and Disability Index score, self-perceived shoulder pain (visual analog scale score), shoulder range of motion, and the Patient-Specific Functional Scale score were measured at baseline, after a 2-week washout period just before starting treatment, after treatment, and at 3 months' follow-up. RESULTS: No significant between-group differences in any outcome were found either after treatment or at 3 months' follow-up. CONCLUSION: A CNS-focused approach provided no additional benefit to a manual therapy and home stretching program in terms of shoulder pain and function in people with FS.

Asunto(s)

RESUMEN

The COVID-19 pandemic has caused a profound change in health organizations at both the primary and hospital care levels. This cross-sectional study aims to investigate the impact of the COVID-19 pandemic in the annual rate of new cancer diagnosis in two university-affiliated hospitals. This study includes all the patients with a pathological diagnosis of cancer attended in two hospitals in Málaga (Spain) during the first year of pandemic. This study population was compared with the patients diagnosed during the previous year 2019. To analyze whether the possible differences in the annual rate of diagnoses were due to the pandemic or to other causes, the patients diagnosed during 2018 and 2017 were also compared. There were 2340 new cancer diagnosis compared to 2825 patients in 2019 which represented a decrease of -17.2% (p = 0.0001). Differences in the number of cancer patients diagnosed between 2018 and 2019 (2840 new cases; 0.5% increase) or 2017 and 2019 (2909 new cases; 3% increase) were not statistically significant. The highest number of patients lost from diagnosis in 2020 was in breast cancer (-26.1%), colorectal neoplasms (-16.9%), and head and neck tumors (-19.8%). The study of incidence rates throughout the first year of the COVID-19 pandemic shows that the diagnosis of new cancer patients has been significantly impaired. Health systems must take the necessary measures to restore pre-pandemic diagnostic procedures and to recover lost patients who have not been diagnosed.

RESUMEN

BACKGROUND: CDK4/6 inhibitors plus endocrine therapies are the current standard of care in the first-line treatment of HR+/HER2-negative metastatic breast cancer, but there are no well-established clinical or molecular predictive factors for patient response. In the era of personalised oncology, new approaches for developing predictive models of response are needed. MATERIALS AND METHODS: Data derived from the electronic health records (EHRs) of real-world patients with HR+/HER2-negative advanced breast cancer were used to develop predictive models for early and late progression to first-line treatment. Two machine learning approaches were used: a classic approach using a data set of manually extracted features from reviewed (EHR) patients, and a second approach using natural language processing (NLP) of free-text clinical notes recorded during medical visits. RESULTS: Of the 610 patients included, there were 473 (77.5%) progressions to first-line treatment, of which 126 (20.6%) occurred within the first 6 months. There were 152 patients (24.9%) who showed no disease progression before 28 months from the onset of first-line treatment. The best predictive model for early progression using the manually extracted dataset achieved an area under the curve (AUC) of 0.734 (95% CI 0.687-0.782). Using the NLP free-text processing approach, the best model obtained an AUC of 0.758 (95% CI 0.714-0.800). The best model to predict long responders using manually extracted data obtained an AUC of 0.669 (95% CI 0.608-0.730). With NLP free-text processing, the best model attained an AUC of 0.752 (95% CI 0.705-0.799). CONCLUSIONS: Using machine learning methods, we developed predictive models for early and late progression to first-line treatment of HR+/HER2-negative metastatic breast cancer, also finding that NLP-based machine learning models are slightly better than predictive models based on manually obtained data.

Asunto(s)

RESUMEN

The eclosion of data acquisition technologies has shifted the bottleneck in molecular biology research from data acquisition to data analysis. Such is the case in Comparative Genomics, where sequence analysis has transitioned from genes to genomes of several orders of magnitude larger. This fact has revealed the need to adapt software to work with huge experiments efficiently and to incorporate new data-analysis strategies to manage results from such studies. In previous works, we presented GECKO, a software to compare large sequences; now we address the representation, browsing, data exploration, and post-processing of the massive amount of information derived from such comparisons. GECKO-MGV is a web-based application organized as client-server architecture. It is aimed at visual analysis of the results from both pairwise and multiple sequences comparison studies combining a set of common commands for image exploration with improved state-of-the-art solutions. In addition, GECKO-MGV integrates different visualization analysis tools while exploiting the concept of layers to display multiple genome comparison datasets. Moreover, the software is endowed with capabilities for contacting external-proprietary and third-party services for further data post-processing and also presents a method to display a timeline of large-scale evolutionary events. As proof-of-concept, we present 2 exercises using bacterial and mammalian genomes which depict the capabilities of GECKO-MGV to perform in-depth, customizable analyses on the fly using web technologies. The first exercise is mainly descriptive and is carried out over bacterial genomes, whereas the second one aims to show the ability to deal with large sequence comparisons. In this case, we display results from the comparison of the first Homo sapiens chromosome against the first 5 chromosomes of Mus musculus.