There is a need of ensuring machine learning models that are interpretable. Higher interpretability of the model means easier comprehension and explanation of future predictions for end-users. Further, interpretable machine learning models allow healthcare experts to make reasonable and data-driven decisions to provide personalized decisions that can ultimately lead to higher quality of service in healthcare. Generally, we can classify interpretability approaches in two groups where the first focuses on personalized interpretation (local interpretability) while the second summarizes prediction models on a population level (global interpretability). Alternatively, we can group interpretability methods into model-specific techniques, which are designed to interpret predictions generated by a specific model, such as a neural network, and model-agnostic approaches, which provide easy-to-understand explanations of predictions made by any machine learning model. Here, we give an overview of interpretability approaches and provide examples of practical interpretability of machine learning in different areas of healthcare, including prediction of health-related outcomes, optimizing treatments or improving the efficiency of screening for specific conditions. Further, we outline future directions for interpretable machine learning and highlight the importance of developing algorithmic solutions that can enable machine-learning driven decision making in high-stakes healthcare problems.

Interpretability of machine learning‐based prediction models in healthcare

COVID-19 is a newly emerging infectious disease, which is generally susceptible to human beings and has caused huge losses to people's health. Acute respiratory distress syndrome (ARDS) is one of the common clinical manifestations of severe COVID-19 and it is also responsible for the current shortage of ventilators worldwide. This study aims to analyze the clinical characteristics of COVID-19 ARDS patients and establish a diagnostic system based on artificial intelligence (AI) method to predict the probability of ARDS in COVID-19 patients. We collected clinical data of 659 COVID-19 patients from 11 regions in China. The clinical characteristics of the ARDS group and no-ARDS group of COVID-19 patients were elaborately compared and both traditional machine learning algorithms and deep learning-based method were used to build the prediction models. Results indicated that the median age of ARDS patients was 56.5 years old, which was significantly older than those with non-ARDS by 7.5 years. Male and patients with BMI > 25 were more likely to develop ARDS. The clinical features of ARDS patients included cough (80.3%), polypnea (59.2%), lung consolidation (53.9%), secondary bacterial infection (30.3%), and comorbidities such as hypertension (48.7%). Abnormal biochemical indicators such as lymphocyte count, CK, NLR, AST, LDH, and CRP were all strongly related to the aggravation of ARDS. Furthermore, through various AI methods for modeling and prediction effect evaluation based on the above risk factors, decision tree achieved the best AUC, accuracy, sensitivity and specificity in identifying the mild patients who were easy to develop ARDS, which undoubtedly helped to deliver proper care and optimize use of limited resources.

/pdf/risk-factors-analysis-of-covid-19-patients-with-ards-and-50gt38yzc3.pdf

Risk factors analysis of COVID-19 patients with ARDS and prediction based on machine learning.

Investigating known and novel biomarkers for risk stratification in cardiovascular disease

There is a need of ensuring machine learning models that are interpretable Higher interpretability of the model means easier comprehension and explanation of future predictions for end-users Further, interpretable machine learning models allow healthcare experts to make reasonable and data-driven decisions to provide personalized decisions that can ultimately lead to higher quality of service in healthcare Generally, we can classify interpretability approaches in two groups where the first focuses on personalized interpretation (local interpretability) while the second summarizes prediction models on a population level (global interpretability) Alternatively, we can group interpretability methods into model-specific techniques, which are designed to interpret predictions generated by a specific model, such as a neural network, and model-agnostic approaches, which provide easy-to-understand explanations of predictions made by any machine learning model Here, we give an overview of interpretability approaches and provide examples of practical interpretability of machine learning in different areas of healthcare, including prediction of health-related outcomes, optimizing treatments or improving the efficiency of screening for specific conditions Further, we outline future directions for interpretable machine learning and highlight the importance of developing algorithmic solutions that can enable machine-learning driven decision making in high-stakes healthcare problems

Interpretability of machine learning based prediction models in healthcare

Background The American College of Surgeons (ACS) Surgical Risk Calculator predicts postoperative risk based on preoperative variables. The ACS model was compared to an institution-specific risk calculator for pancreaticoduodenectomy (PD). Methods Observed outcomes were compared with those predicted by the ACS and institutional models. Receiver operating characteristic (ROC) analysis evaluated the models' predictive ability. Institutional models were evaluated with retrospective and prospective internal validation. Results Brier scores indicate equivalent aggregate predictive ability. ROC values for the institutional model (ROC: 0.675–0.881, P  Conclusions Identifying higher-risk patients allows for individualized care. While ACS and institutional models accurately predict average complication occurrence, the institutional models are superior at predicting individualized outcomes. Predictive metrics specific to PD center volume may more accurately predict outcomes.

Developing and validating a center-specific preoperative prediction calculator for risk of pancreaticoduodenectomy.

Deriving predictive models in medicine typically relies on a population approach where a single model is developed from a dataset of individuals. In this paper we describe and evaluate a personalized approach in which we construct a new type of decision tree model called decision-path model that takes advantage of the particular features of a given person of interest. We introduce three personalized methods that derive personalized decision-path models. We compared the performance of these methods to that of Classification And Regression Tree (CART) that is a population decision tree to predict seven different outcomes in five medical datasets. Two of the three personalized methods performed statistically significantly better on area under the ROC curve (AUC) and Brier skill score compared to CART. The personalized approach of learning decision path models is a new approach for predictive modeling that can perform better than a population approach.

Personalized Modeling for Prediction with Decision-Path Models

2016 foi um ano especialmente dificil para o Brasil, devido ao inaceitavel golpe politico e suas inumeras implicacoes economicas, politicas e sociais. O golpe, de fato, acabou determinando o clima e o ritmo do ano, ja que envolveu incansaveis e intermitentes manobras institucionais e de midia que mantiveram as relacoes politicas e sociais em um estado de convulsao prolongado, dolorido e desagregador. E como parte fundamental das manobras do golpe era a intensificacao brutal da crise economica...

/pdf/2016-ano-em-que-o-pais-sofreu-um-golpe-politico-5b794odkyt.pdf

2016, ano em que o país sofreu um golpe político-institucional, não termina

Patient-specific models are instance-based learning algorithms that take advantage of the particular features of the patient case at hand to predict an outcome. We introduce two patient-specific algorithms based on decision tree paradigm that use AUC as a metric to select an attribute. We apply the patient specific algorithms to predict outcomes in several datasets, including medical datasets. Compared to the patient-specific decision path (PSDP) entropy-based and CART methods, the AUC-based patient-specific decision path models performed equivalently on area under the ROC curve (AUC). Our results provide support for patient-specific methods being a promising approach for making clinical predictions. Keywords—Approach instance-based, area Under the ROC Curve, Patient-specific Decision Path, clinical predictions.

/pdf/patient-specific-modeling-algorithm-for-medical-data-based-3pi3gqorxy.pdf

Guilherme Ribeiro

Papers

Personalized Modeling for Prediction with Decision-Path Models

2016, ano em que o país sofreu um golpe político-institucional, não termina

Patient-Specific Modeling Algorithm for Medical Data Based on AUC

Geopolitics of Sustainable Development During the Twentieth and Twenty-First Centuries

Patient-Specific Modeling Algorithm for Medical Data Based on AUC