Access to a large amount of high quality data is possibly the most important factor for success in advancing medicine with machine learning and data science. However, valuable healthcare data are usually distributed across isolated silos, and there are complex operational and regulatory concerns. Data on patient populations are often horizontally separated,each other across different practices and health systems. In addition, individual patient data are often vertically separated, by data type, across her sites of care, service, and testing. We train a confederated learning model in a manner to stratify elderly patients by their risk of a fall in the next two years, using diagnoses, medication claims data and clinical lab test records of patients.

A number of machine learning (ML) methods have been proposed recently to maximize model predictive accuracy while enforcing notions of group parity or fairness across sub-populations. We propose a desirable property for these procedures, slack-consistency: For any individual, the predictions of the model should be monotonic with respect to allowed slack (i.e., maximum allowed group-parity violation). Such monotonicity can be useful for individuals to understand the impact of enforcing fairness on their predictions. Surprisingly, we find that standard ML methods for enforcing fairness violate this basic property. Moreover, this undesirable behavior arises in situations agnostic to the complexity of the underlying model or approximate optimizations, suggesting that the simple act of incorporating a constraint can lead to drastically unintended behavior in ML. We present a simple theoretical method for enforcing slack-consistency, while encouraging further discussions on the unintended behaviors potentially induced when enforcing group-based parity.

Effective modeling of electronic health records presents many challenges as they contain large amounts of irregularity most of which are due to the varying procedures and diagnosis a patient may have. Despite the recent progress in machine learning, unsupervised learning remains largely at open, especially in the healthcare domain. In this work, we present a two-step unsupervised representation learning scheme to summarize the multi-modal clinical time series consisting of signals and medical codes into a patient status vector. First, an auto-encoder step is used to reduce sparse medical codes and clinical time series into a distributed representation. Subsequently, the concatenation of the distributed representations is further fine-tuned using a forecasting task. We evaluate the usefulness of the representation on two downstream tasks: mortality and readmission. Our proposed method shows improved generalization performance for both short duration ICU visits and long duration ICU visits.

Below you will read in the training and test data which are already split for you to load separately. Then use unnest() from tidytext to create the tidy version with one word per record. Now that you have train and test data loaded and tidied, you can see how many songs exist per artist/author. Since the dataset has songs and book pages, I'll refer to them each as a document. The features that you will create are based on documents and their associated metadata, so it's important to understand this concept.

This article was originally published in February 2016 and updated in August 2019. The idea of building machine learning models works on a constructive feedback principle. You build a model, get feedback from metrics, make improvements and continue until you achieve a desirable accuracy. Evaluation metrics explain the performance of a model. An important aspect of evaluation metrics is their capability to discriminate among model results. I have seen plenty of analysts and aspiring data scientists not even bothering to check how robust their model is. Once they are finished building a model, they hurriedly map predicted values on unseen data. This is an incorrect approach. Simply building a predictive model is not your motive. It's about creating and selecting a model which gives high accuracy on out of sample data.

Ethereum smart contracts have recently drawn a considerable amount of attention from the media, the financial industry and academia. With the increase in popularity, malicious users found new opportunities to profit from deceiving newcomers. Consequently, attackers started luring other attackers into contracts that seem to have exploitable flaws, but that actually contain a complex hidden trap that in the end benefits the contract creator. This kind of contracts are known in the blockchain community as Honeypots. A recent study, proposed to investigate this phenomenon by focusing on the contract bytecode using symbolic analysis. In this paper, we present a data science approach based on the contract transaction behavior. We create a partition of all the possible cases of fund movement between the contract creator, the contract, the sender of the transaction and other participants. We calculate the frequency of every case per contract, and extract as well other contract features and transaction aggregated features. We use the collected information to train machine learning models that classify contracts as honeypot or non-honeypots, and also measure how well they perform when classifying unseen honeypot types. We compare our results with the bytecode analysis method using labels from a previous study, and discuss in which cases each solution has advantages over the other.

Machine learning is a branch of artificial intelligence that includes algorithms for automatically creating models from data. At a high level, there are four kinds of machine learning: supervised learning, unsupervised learning, reinforcement learning, and active machine learning. Since reinforcement learning and active machine learning are relatively new, they are sometimes omitted from lists of this kind. You could also add semi-supervised learning to the list, and not be wrong. Supervised learning starts with training data that are tagged with the correct answers (target values).

Scikit-learn defines a simple API for creating visualizations for machine learning. The key feature of this API is to allow for quick plotting and visual adjustments without recalculation. The returned svc_disp object allows us to continue using the already computed ROC curve for SVC in future plots. In this case, the svc_disp is a RocCurveDisplay that stores the computed values as attributes called roc_auc, fpr, and tpr. Next, we train a random forest classifier and plot the previously computed roc curve again by using the plot method of the Display object.

For this explanation let's suppose we were working on a binary classification problem to detect whether or not a transaction is fraudulent. Our model uses characteristics of the user and transaction and returns 1 if the transaction is predicted to be fraudulent and 0 if not. Given that machine learning models are rarely 100% accurate there is going to be a level of risk in deploying this model. If we incorrectly classify a non-fraudulent transaction as fraud then we may well lose that transaction, and possibly even the future customers business. On the other hand, if we incorrectly detect a fraudulent transaction as non-fraudulent then we might stand to lose the value of that transaction. The confusion matrix essentially places the resulting predictions into four groups.

In cellular systems, the user equipment (UE) can request a change in the frequency band when its rate drops below a threshold on the current band. The UE is then instructed by the base station (BS) to measure the quality of candidate bands, which requires a measurement gap in the data transmission, thus lowering the data rate. We propose a band switching approach based on machine learning that does not require any measurement gap. Our proposed classifier-based band switching policy instead exploits spatial and spectral correlation between radio frequency signals in different bands based on knowledge of the UE location. We focus on switching between a lower (e.g. 3.5 GHz) band and a millimeter wave band (e.g. 28 GHz), and design and evaluate two classification models that are trained on a ray-tracing dataset. A key insight is that measurement gaps are overkill, in that only the relative order of the bands is necessary for band selection, rather than a full channel estimate. Our proposed machine learning-based policies achieve roughly 30% improvement in mean effective rates over those of the industry standard policy, while achieving misclassification errors well below 0.5%.