scholarly journals Bioinformatic and Machine Learning Applications in Melanoma Risk Assessment and Prognosis: A Literature Review

Genes ◽  
2021 ◽  
Vol 12 (11) ◽  
pp. 1751
Author(s):  
Emily Z. Ma ◽  
Karl M. Hoegler ◽  
Albert E. Zhou
Keyword(s):  
Machine Learning ◽  
Literature Review ◽  
Risk Stratification ◽  
Metastatic Melanoma ◽  
The United States ◽  
Clinical Staging ◽  
Machine Learning Applications ◽  
Risk Stratification Tool ◽  
Melanoma Treatment ◽  
Melanoma Patients

Over 100,000 people are diagnosed with cutaneous melanoma each year in the United States. Despite recent advancements in metastatic melanoma treatment, such as immunotherapy, there are still over 7,000 melanoma-related deaths each year. Melanoma is a highly heterogenous disease, and many underlying genetic drivers have been identified since the introduction of next-generation sequencing. Despite clinical staging guidelines, the prognosis of metastatic melanoma is variable and difficult to predict. Bioinformatic and machine learning analyses relying on genetic, clinical, and histopathologic inputs have been increasingly used to risk stratify melanoma patients with high accuracy. This literature review summarizes the key genetic drivers of melanoma and recent applications of bioinformatic and machine learning models in the risk stratification of melanoma patients. A robustly validated risk stratification tool can potentially guide the physician management of melanoma patients and ultimately improve patient outcomes.

The current role of systemic therapy in the management of Malignant Melanoma of the skin: a literature review

2004 ◽  
Vol 4 (4) ◽  
pp. 161-175 ◽  
Author(s):  
Elizabeth Reeves ◽  
P. Bridge ◽  
R. M. Appleyard
Keyword(s):  
Clinical Trials ◽  
Literature Review ◽  
Metastatic Melanoma ◽  
Systemic Therapy ◽  
Survival Rates ◽  
Success Rates ◽  
Systemic Treatments ◽  
Melanoma Patients ◽  
Disease Free

Melanoma patients can be split into two main categories that have different aims for treatment; localised disease with either intermediate or high-risk of recurrence after surgery, and metastatic disease. Over the past decade, there have been many clinical trials looking at improving the success rates for localised and metastatic melanoma with alternative systemic treatments, namely immunotherapy, biochemotherapy and vaccines. This literature review summarises the clinical trials for each form of systemic treatment in localised and metastatic melanoma and assesses the effectiveness of each by an evaluation and comparison of relevant clinical trials for each systemic modality. The main objective was to assess whether alternative forms of systemic therapy have improved the disease free and overall survival rates achieved with chemotherapy.

scholarly journals Open Data Based Machine Learning Applications in Smart Cities: A Systematic Literature Review

Electronics ◽  
2021 ◽  
Vol 10 (23) ◽  
pp. 2997
Author(s):  
Luminita Hurbean ◽  
Doina Danaiata ◽  
Florin Militaru ◽  
Andrei-Mihail Dodea ◽  
Ana-Maria Negovan
Keyword(s):  
Machine Learning ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Smart City ◽  
Smart Cities ◽  
Open Data ◽  
Quality Of Data ◽  
Data Movement ◽  
Depth Analysis ◽  
Machine Learning Applications

Machine learning (ML) has already gained the attention of the researchers involved in smart city (SC) initiatives, along with other advanced technologies such as IoT, big data, cloud computing, or analytics. In this context, researchers also realized that data can help in making the SC happen but also, the open data movement has encouraged more research works using machine learning. Based on this line of reasoning, the aim of this paper is to conduct a systematic literature review to investigate open data-based machine learning applications in the six different areas of smart cities. The results of this research reveal that: (a) machine learning applications using open data came out in all the SC areas and specific ML techniques are discovered for each area, with deep learning and supervised learning being the first choices. (b) Open data platforms represent the most frequently used source of data. (c) The challenges associated with open data utilization vary from quality of data, to frequency of data collection, to consistency of data, and data format. Overall, the data synopsis as well as the in-depth analysis may be a valuable support and inspiration for the future smart city projects.

scholarly journals Clinical Categorization Algorithm (CLICAL) and Machine Learning Approach (SRF-CLICAL) to Predict Clinical Benefit to Immunotherapy in Metastatic Melanoma Patients: Real-World Evidence from the Istituto Nazionale Tumori IRCCS Fondazione Pascale, Napoli, Italy

Cancers ◽  
2021 ◽  
Vol 13 (16) ◽  
pp. 4164
Author(s):  
Gabriele Madonna ◽  
Giuseppe V. Masucci ◽  
Mariaelena Capone ◽  
Domenico Mallardo ◽  
Antonio Maria Grimaldi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Metastatic Melanoma ◽  
Learning Algorithm ◽  
Checkpoint Inhibitors ◽  
Real Life ◽  
Previous Treatment ◽  
Clinical Decision ◽  
Neutrophil Lymphocyte Ratio ◽  
Real World Evidence ◽  
Melanoma Patients

The real-life application of immune checkpoint inhibitors (ICIs) may yield different outcomes compared to the benefit presented in clinical trials. For this reason, there is a need to define the group of patients that may benefit from treatment. We retrospectively investigated 578 metastatic melanoma patients treated with ICIs at the Istituto Nazionale Tumori IRCCS Fondazione “G. Pascale” of Napoli, Italy (INT-NA). To compare patients’ clinical variables (i.e., age, lactate dehydrogenase (LDH), neutrophil–lymphocyte ratio (NLR), eosinophil, BRAF status, previous treatment) and their predictive and prognostic power in a comprehensive, non-hierarchical manner, a clinical categorization algorithm (CLICAL) was defined and validated by the application of a machine learning algorithm—survival random forest (SRF-CLICAL). The comprehensive analysis of the clinical parameters by log risk-based algorithms resulted in predictive signatures that could identify groups of patients with great benefit or not, regardless of the ICI received. From a real-life retrospective analysis of metastatic melanoma patients, we generated and validated an algorithm based on machine learning that could assist with the clinical decision of whether or not to apply ICI therapy by defining five signatures of predictability with 95% accuracy.

Survival trends among patients with metastatic melanoma in the United States: A population based study.

2017 ◽  
Vol 35 (15_suppl) ◽  
pp. 9555-9555 ◽  
Author(s):  
Ranju Kunwor ◽  
Mahesh Nepal ◽  
Dominic Ho ◽  
Krishna Bilas Ghimire
Keyword(s):  
United States ◽  
Metastatic Melanoma ◽  
Relative Survival ◽  
The United States ◽  
Population Based ◽  
Age Group ◽  
Significant Survival ◽  
Melanoma Patients ◽  
And Gender ◽  
Registry Database

9555 Background: Ipilimumab was approved by FDA in March 2011 for the treatment of Metastatic Melanoma. We conducted this study to compare survival outcome in patients with Metastatic Melanoma in pre- (1973-2010) and post- (2011-2013) ipilimumab era in the United States using U.S. Surveillance, Epidemiology, and End Result (SEER) registry database. Methods: We selected patients with metastatic melanoma age ≥ 20 years from the SEER database. We used SEER 18 registry database to evaluate relative survival (RS) rate during 1973-2010 and 2011-2013. The RS rate at 1year and 2 year were analyzed for cohorts by age (20-49 years, 50-74 and ≥75 years), race [White, African American (AA), and others] and gender. The RS rates (%) accompany standard error (SE). We used SEER Stat software for statistical analysis. Results: There were a total of 129,362 (106,516 and 22,846 in pre and post ipilimumab era) metastatic melanoma patients, male (n = 71,220), female (n = 58,142), white (n = 121,843), AA (n = 854) other (n = 1,315) reported in the registry. RS in pre vs post-ipilimumab era for age group 20-49 was: 96.50 ± 0.1% vs 97.20 ±0.3%, P = 0.013; and 94.10 ± 0.1% to 95.60 ±0.40, P = 0.0009; for age group 50-74 was: 94.10 ± 0.1% vs 95.30 ± 0.2%, P = 0.0001; and 90.70 ± 0.1%vs 92.90 ± 0.3%, P = 0.0001; and for age group ≥75 was 90.80 ± 0.3% vs 91.40 ± 0.7%, P = 0.23; and 85.0 ± 0.4% vs 88.10 ± 1.0%, P = 0.011 at 1 and 2 years respectively. Overall RS in pre and post ipilimumab era for white population was: 93.83 ± 0.16% vs 94.567 ± 0.4%, P = 0.017; and 90.0 ± 0.2% vs 92.033 ± 0.6%, P = 0.0008 at 1 and 2 years respectively. Similarly RS for AA was: 78.07 ± 2.93% vs 73.33 ± 8.23%, P = 0.37; and 65.87 ± 3.47% vs 65.33 ± 9.73%, P = 0.94; and for other race was: 85.2 ± 2.13% vs 77.97 ± 5.6%, P = 0.04; and 74.43 ± 5.2% vs 69.67 ± 6.7%, P = 0.1 at 1 year and 2 years. Conclusions: Our study showed that younger (20-74 years) patients with metastatic melanoma have improvement in 1 and 2-year RS rates in post ipilimumab era. Subgroup analysis by race showed no improvement in RS in AA and other races patients during this period. There was also no significant survival benefit seen in older (≥ 75 years) patients of all races and gender in post ipilimumab era.

scholarly journals Risk Stratification for Early Detection of Diabetes and Hypertension in Resource-Limited Settings: Machine Learning Analysis

10.2196/20123 ◽  
2021 ◽  
Vol 23 (1) ◽  
pp. e20123
Author(s):  
Justin J Boutilier ◽  
Timothy C Y Chan ◽  
Manish Ranjan ◽  
Sarang Deo
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Risk Stratification ◽  
Prediction Accuracy ◽  
The United States ◽  
Disease Screening ◽  
Noncommunicable Disease ◽  
Risk Scores ◽  
False Negatives ◽  
Screening Programs

Background The impending scale up of noncommunicable disease screening programs in low- and middle-income countries coupled with limited health resources require that such programs be as accurate as possible at identifying patients at high risk. Objective The aim of this study was to develop machine learning–based risk stratification algorithms for diabetes and hypertension that are tailored for the at-risk population served by community-based screening programs in low-resource settings. Methods We trained and tested our models by using data from 2278 patients collected by community health workers through door-to-door and camp-based screenings in the urban slums of Hyderabad, India between July 14, 2015 and April 21, 2018. We determined the best models for predicting short-term (2-month) risk of diabetes and hypertension (a model for diabetes and a model for hypertension) and compared these models to previously developed risk scores from the United States and the United Kingdom by using prediction accuracy as characterized by the area under the receiver operating characteristic curve (AUC) and the number of false negatives. Results We found that models based on random forest had the highest prediction accuracy for both diseases and were able to outperform the US and UK risk scores in terms of AUC by 35.5% for diabetes (improvement of 0.239 from 0.671 to 0.910) and 13.5% for hypertension (improvement of 0.094 from 0.698 to 0.792). For a fixed screening specificity of 0.9, the random forest model was able to reduce the expected number of false negatives by 620 patients per 1000 screenings for diabetes and 220 patients per 1000 screenings for hypertension. This improvement reduces the cost of incorrect risk stratification by US $1.99 (or 35%) per screening for diabetes and US $1.60 (or 21%) per screening for hypertension. Conclusions In the next decade, health systems in many countries are planning to spend significant resources on noncommunicable disease screening programs and our study demonstrates that machine learning models can be leveraged by these programs to effectively utilize limited resources by improving risk stratification.

scholarly journals REPEATED USE OF BRAF AND MEK INHIBITORS IN METASTATIC MELANOMA PATIENTS AFTER PROFRESSION ON BRAF AND МЕК INHIBITORS. LITERATURE REVIEW AND CLINICAL OBSERVATION

2017 ◽  
pp. 6-10 ◽  
Author(s):  
I. V. Samoylenko ◽  
Y. A. Zhulikov ◽  
L. V. Demidov
Keyword(s):  
Literature Review ◽  
Metastatic Melanoma ◽  
Clinical Settings ◽  
Optimal Sequence ◽  
Mek Inhibitors ◽  
Clinical Observations ◽  
Repeated Use ◽  
Melanoma Patients ◽  
Effective Drugs ◽  
Potential Use

Development of new effective drugs for therapy of metastatic melanoma (BRAF/MEK inhibitors, PD1/CTLA4 blockers) requires additional studies of the optimal sequence of their use. But in many cases the duration of the effect of these medicinal products is limited by time even in their sequential use. This literature review considers a possibility of repeated indication of BRAF/ MEK inhibitors after progression on them in various clinical settings. The potential use of such approach is illustrated by two own clinical observations.

scholarly journals Risk Stratification for Early Detection of Diabetes and Hypertension in Resource-Limited Settings: Machine Learning Analysis (Preprint)

2020 ◽  
Author(s):  
Justin J Boutilier ◽  
Timothy C Y Chan ◽  
Manish Ranjan ◽  
Sarang Deo
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Risk Stratification ◽  
Prediction Accuracy ◽  
The United States ◽  
Disease Screening ◽  
Noncommunicable Disease ◽  
Risk Scores ◽  
False Negatives ◽  
Screening Programs

BACKGROUND The impending scale up of noncommunicable disease screening programs in low- and middle-income countries coupled with limited health resources require that such programs be as accurate as possible at identifying patients at high risk. OBJECTIVE The aim of this study was to develop machine learning–based risk stratification algorithms for diabetes and hypertension that are tailored for the at-risk population served by community-based screening programs in low-resource settings. METHODS We trained and tested our models by using data from 2278 patients collected by community health workers through door-to-door and camp-based screenings in the urban slums of Hyderabad, India between July 14, 2015 and April 21, 2018. We determined the best models for predicting short-term (2-month) risk of diabetes and hypertension (a model for diabetes and a model for hypertension) and compared these models to previously developed risk scores from the United States and the United Kingdom by using prediction accuracy as characterized by the area under the receiver operating characteristic curve (AUC) and the number of false negatives. RESULTS We found that models based on random forest had the highest prediction accuracy for both diseases and were able to outperform the US and UK risk scores in terms of AUC by 35.5% for diabetes (improvement of 0.239 from 0.671 to 0.910) and 13.5% for hypertension (improvement of 0.094 from 0.698 to 0.792). For a fixed screening specificity of 0.9, the random forest model was able to reduce the expected number of false negatives by 620 patients per 1000 screenings for diabetes and 220 patients per 1000 screenings for hypertension. This improvement reduces the cost of incorrect risk stratification by US $1.99 (or 35%) per screening for diabetes and US $1.60 (or 21%) per screening for hypertension. CONCLUSIONS In the next decade, health systems in many countries are planning to spend significant resources on noncommunicable disease screening programs and our study demonstrates that machine learning models can be leveraged by these programs to effectively utilize limited resources by improving risk stratification.

Sign in / Sign up

Export Citation Format

Share Document