A note on the use of multiple linear regression in molecular ecology

Comparison of Diagnosis Accuracy between a Backpropagation Artificial Neural Network Model and Linear Regression in Digestive Disease Patients: an Empirical Research

Introduction

A Noninvasive diagnosis model for digestive diseases is the vital issue for the current clinical research. Our systematic review is aimed at demonstrating diagnosis accuracy between the BP-ANN algorithm and linear regression in digestive disease patients, including their activation function and data structure.

Methods

We reported the systematic review according to the PRISMA guidelines. We searched related articles from seven electronic scholarly databases for comparison of the diagnosis accuracy focusing on BP-ANN and linear regression. The characteristics, patient number, input/output marker, diagnosis accuracy, and results/conclusions related to comparison were extracted independently based on inclusion criteria.

Results

Nine articles met all the criteria and were enrolled in our review. Of those enrolled articles, the publishing year ranged from 1991 to 2017. The sample size ranged from 42 to 3222 digestive disease patients, and all of the patients showed comparable biomarkers between the BP-ANN algorithm and linear regression. According to our study, 8 literature demonstrated that the BP-ANN model is superior to linear regression in predicting the disease outcome based on AUROC results. One literature reported linear regression to be superior to BP-ANN for the early diagnosis of colorectal cancer.

Conclusion

The BP-ANN algorithm and linear regression both had high capacity in fitting the diagnostic model and BP-ANN displayed more prediction accuracy for the noninvasive diagnosis model of digestive diseases. We compared the activation functions and data structure between BP-ANN and linear regression for fitting the diagnosis model, and the data suggested that BP-ANN was a comprehensive recommendation algorithm.

Does spirituality reduce the impact of somatic symptoms on distress in cancer patients? Cross-sectional and longitudinal findings

RATIONALE

When diagnosed with cancer, a patient has to cope with stressors such as pain, fatigue, and the experience of life-threat that can cause great distress. Spirituality may be a resource for coping with these problems, thereby reducing distress.

OBJECTIVE

Two questionnaire studies-the first a cross-sectional (Study 1; N = 216) and the second a one-year longitudinal (Study 2; N = 383)-investigated among Dutch cancer patients whether spirituality lessens the impact of pain, fatigue, and perceived life-threat on distress.

METHOD

Data for Study 1 were gathered in 2006-2007 and for Study 2 in 2009-2010. Spirituality was measured with the Spiritual Attitude and Involvement List, which assesses six distinct but related aspects of spirituality. Linear regression analysis and marginal effect plots were applied.

RESULTS

Limited evidence appeared for the hypothesis that spirituality reduces the impact of pain, fatigue, or perceived life threat on distress. Meaningfulness and acceptance might reduce a negative impact of increases in fatigue during the first year after the start of cancer treatment. In contrast, spirituality might enhance a negative impact of increases in perceived life threat.

CONCLUSIONS

Processes of appraisal might explain the findings. Experiences of meaningfulness and acceptance might help to reappraise fatigue in a less threatening way, thereby reducing distress. Conversely, appraising the cancer as life-threatening might conflict with spiritual experiences of meaning, acceptance, and awe about life. Future studies should focus on the processes by which the various aspects of spirituality influence the adjustment of cancer patients and use other outcome variables than non-specific distress. Such studies may provide further clues as to how the spirituality of patients can be harnessed to help them adjust to a serious life event such as the occurrence of cancer.

Symbiosis limits establishment of legumes outside their native range at a global scale

Microbial symbiosis is integral to plant growth and reproduction, but its contribution to global patterns of plant distribution is unknown. Legumes (Fabaceae) are a diverse and widely distributed plant family largely dependent on symbiosis with nitrogen-fixing rhizobia, which are acquired from soil after germination. This dependency is predicted to limit establishment in new geographic areas, owing to a disruption of compatible host-symbiont associations. Here we compare non-native establishment patterns of symbiotic and non-symbiotic legumes across over 3,500 species, covering multiple independent gains and losses of rhizobial symbiosis. We find that symbiotic legume species have spread to fewer non-native regions compared to non-symbiotic legumes, providing strong support for the hypothesis that lack of suitable symbionts or environmental conditions required for effective nitrogen-fixation are driving these global introduction patterns. These results highlight the importance of mutualisms in predicting non-native species establishment and the potential impacts of microbial biogeography on global plant distributions.