No description available.

No description available.

The rapid digitalization of the healthcare domain in recent years highlighted the need for advanced predictive methods particularly based upon deep learning methods. Deep learning methods which are capable of dealing with time- series data have recently emerged in various fields such as natural language processing, machine translation, and the Intensive Care Unit (ICU). The recent applications of deep learning in ICU have increasingly received attention, and it has shown promising results for different clinical tasks; however, there is still a need for the benchmark models as far as a handful of public datasets are available in ICU. In this thesis, a novel benchmark model of four clinical tasks on a multi-center publicly available dataset is presented; we employed deep learning models to predict clinical studies. We believe this benchmark model can facilitate and accelerate the research in ICU by allowing other researchers to build on top of it. Moreover, we investigated the effectiveness of the proposed method to predict the risk of delirium in the varying observation and prediction windows, the variable ranking is provided to ease the implementation of a screening tool for helping caregivers at the bedside. Ultimately, an attention-based interpretable neural network is proposed to predict the outcome and rank the most influential variables in the model predictions’ outcome. Our experimental findings show the effectiveness of the proposed approaches in improving the application of deep learning models in daily ICU practice.

Explainability is a key component in building trust for computer calculated predictions when they are applied to areas with influence over individual people. This bachelor thesis project report focuses on the explanation regarding the decision making process of the machine learning method Logistic Regression when predicting mortality. The aim is to present theoretical information about the predictive model as well as an explainable interpretation when applied on the clinical MIMIC-III database. The project found that there was a significant difference between particular features considering the impact of each individual feature on the classification. The feature that showed the greatest impact was the Glasgow Coma Scale value, which could be proven through the fact that a good classifier could be constructed with only that and one other feature. An important conclusion from this study is that a great focus should be enforced early in the implementation process when the features are selected. In this specific case, when medical artificial intelligence is implemented, medical expertise is desired in order to make a good feature selection. / Förklarbarhet är en viktig komponent för att skapa förtroende för datorframtagna prognoser när de appliceras på områden som påverkar individuella personer. Denna kandidatexamensarbetesrapport fokuserar på förklarandet av beslutsprocessen hos maskininlärningsmetoden Logistic Regression när dödlighet ska förutsägas. Målet är att presentera information om den förutsägande modellen samt en förklarbar tolkning av resultaten när modellen appliceras på den kliniska databasen MIMIC-III. Projektet fann att det fanns signifikanta skillnader mellan särskilda egenskaper med hänsyn till den påverkan varje enskild egenskap har på klassificeringen. Den egenskapen som visade ha störst inverkan var Glascow Coma Scale värdet, vilket kunde visas via det faktum att en god klassificerare kunde konstrueras med endast den och en annan egenskap. En viktig slutsats av denna studie är att stort fokus bör läggas tidigt i implementationsprocessen då egenskaperna väljs. I detta specifika fall, då medicinsk artificiell intelligens implementeras, krävs medicinsk expertis för att göra ett gott egenskapsurval. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm

Machine learning has the potential of significantly improving daily operations in health care institutions but many persistent barriers are to be faced in order to ensure its wider acceptance. Among such obstacles are the accuracy and reliability. For a decision support system to be entrusted by the medical staff in clinical situations, it must perform with an accuracy comparable to or surpassing that of human medics, as well ashaving a universal applicability and not being subject to any bias. In this paper the MIMIC-IV Clinical Database will be utilized in order to: (1) Predict patient mortality and its associated risk factors in intensive care units (ICU) and: (2) Assess the reliability of utilizing the database as a basis for a clinical decision system. The cohort consisted of 523,740 hospitalizations, matched with each respective admitting diagnoses in ICD-9 format. The diagnoses were then converted from code to text-format, with the most frequently occurring factors (words) observed in deceased and surviving patients being analyzed with an Natural language Processing (NLP) algorithm. The results concluded that many of the observed risk factors were self-evident while others required further explanation, and that the performance was highly by selection of hyperparameters. Finally, the MIMIC-IV database can serve as a stable foundation for a clinical decision system but its reliability and universality shall also be taken into consideration. / Maskininlärninstekniker har en stor potential att gynna sjukvården men står inför ett flertal hinder för att fullständigt kunna tillämpas. Framförallt bör modellernas tolkningsbarhet och reproducerbarhet beaktas. För att att ett kliniskt beslutstodssystem skall vara fullständigt anförtrott av sjukvårdspersonal måste det kunna prestera med en jämförbar eller högre träffsäkerhet än sjukvårdspersonal, samt kunna tillämpas i åtskilliga sammanhang utan någon subjektivitet. Syftet med denna studie är att: (1) Förutspå patientdödsfall i intensivvårdsavdelningar och utreda dess riskfaktorer genom journalförd information från databasen MIMIC-IV och: 2) Bedöma databasens tillförlitlighet som underlag för ett kliniskt beslutstödssystem. Kohorten bestod av 523,740 insjuknanden som matchades med de diagnoser som ställdes vid deras sjukhusintag. Eftersom diagnoserna inskrevs i ICD-9-format omvandlades dessa till ord och de mest förekommande faktorerna (orden) för avlidna och överlevande patienter analyserades med en NLP-model (Natural Language Processing). Resultaten konkluderade att många av de förutspådda riskfaktorerna var uppenbara medan andra krävde ytterligare klargöranden. Dessutom kunde val av hyperparametrar stort påverka modellens kvalitet. MIMIC-IV-databasen kan utgöra ett gediget underlag för ett kliniskt beslutsystem men dess tillförlitlighet och relevans bör även tas i beaktande. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm

Accurate mortality prediction in intensive care units (ICUs) allows for the risk adjustment of study populations, aids in patient care and provides a method for benchmarking overall hospital and ICU performance. ICU risk-adjustment models are primarily comprised of an integer severity of illness score which increases with increasing patient risk of mortality. First published in the 1980s, the improvements to these scores primarily consisted of increasing the dimensionality of the model, and hence also increasing their complexity. This thesis aims to improve upon these models. First, the field is surveyed and the major models for risk-adjusting critically ill patient cohorts are identified including the acute physiology score (APS) and the simplified acute physiology score (SAPS). A key component of model performance is data preprocessing. The effect of preprocessing ICU data is quantified on a dataset of 8,000 ICU patients, and it is shown that after preprocessing to remove extreme values a logistic regression (LR) model performed competitively (AUROC of 0.8633) with the more complex machine learning model; a support vector machine (SVM) which had an AUROC of 0.8653. For validation, model development was repeated in a larger database containing over 80,000 patients admitted to 89 ICUs in the United States. Results were similar (AUROC of 0.8895 for the LR vs 0.8917 for the SVM) but showed the performance gain when using automated outlier rejection is less pronounced in well quality controlled datasets (0.8883 for LR without rejection). It is hypothesised from this that simpler models can perform competitively with more complicated models, while having a greatly reduced burden of data collection. A severity score is developed on the large multi-center database using a Genetic Algorithm and Particle Swarm Optimisation. The severity score, named the Oxford Acute Severity of Illness Score (OASIS), is shown to outperform the APS III (AUROC 0.837 vs 0.822) and perform competitively with APACHE IV when used as a covariate in a regression model (AUROC 0.868 vs 0.881). The severity score requires only 10 variables (58% as many as APS III), reducing the burden of quality control and data collection. These variables are routinely collected in critical care by continuous monitors and do not include comorbidities, diagnosis or laboratory measurements. The severity score is then externally evaluated in an American hospital and shown to discriminate well (AUROC 0.790 vs. 0.782 for the APS III) with excellent calibration. Finally, the severity score was evaluated in an English hospital and compared to other severity scores. OASIS again had excellent calibration and discrimination (AUROC 0.776 vs 0.750 for APS III) whilst requiring a much smaller number of variables. OASIS has many applications, including both simplifying data collection for studies and improving the risk assessment therein.

The objective of this thesis is to find patterns trends and assumptions for mortality vs. age prediction. Based on the analysis of trends in the already extinct cohorts, the most suitable models for estimating the future development of mortality among surviving cohorts are selected. This thesis compares real data extinct cohorts with balanced data Gompertz-Makehamovy function. The research and analysis is focused on the specifics of cohort mortality from the age of 90. The last part of this thesis illustrates comparison between real data of extinct cohorts with DeRaS model outputs. The selection of Kannisto and Thatcher as the optimal model is presented in the form of graphical outputs indicating the cohort life expectancy of men and women aged 90 years.

Indiana University-Purdue University Indianapolis (IUPUI) / With the increasing availability of Electronic Health Records (EHRs) and advances in deep learning techniques, developing deep predictive models that use EHR data to solve healthcare problems has gained momentum in recent years. The majority of clinical predictive models benefit from structured data in EHR (e.g., lab measurements and medications). Still, learning clinical outcomes from all possible information sources is one of the main challenges when building predictive models. This work focuses mainly on two sources of information that have been underused by researchers; unstructured data (e.g., clinical notes) and a patient network. We propose a novel hybrid deep learning model, DeepNote-GNN, that integrates clinical notes information and patient network topological structure to improve 30-day hospital readmission prediction. DeepNote-GNN is a robust deep learning framework consisting of two modules: DeepNote and patient network. DeepNote extracts deep representations of clinical notes using a feature aggregation unit on top of a state-of-the-art Natural Language Processing (NLP) technique - BERT. By exploiting these deep representations, a patient network is built, and Graph Neural Network (GNN) is used to train the network for hospital readmission predictions. Performance evaluation on the MIMIC-III dataset demonstrates that DeepNote-GNN achieves superior results compared to the state-of-the-art baselines on the 30-day hospital readmission task. We extensively analyze the DeepNote-GNN model to illustrate the effectiveness and contribution of each component of it. The model analysis shows that patient network has a significant contribution to the overall performance, and DeepNote-GNN is robust and can consistently perform well on the 30-day readmission prediction task. To evaluate the generalization of DeepNote and patient network modules on new prediction tasks, we create a multimodal model and train it on structured and unstructured data of MIMIC-III dataset to predict patient mortality and Length of Stay (LOS). Our proposed multimodal model consists of four components: DeepNote, patient network, DeepTemporal, and score aggregation. While DeepNote keeps its functionality and extracts representations of clinical notes, we build a DeepTemporal module using a fully connected layer stacked on top of a one-layer Gated Recurrent Unit (GRU) to extract the deep representations of temporal signals. Independent to DeepTemporal, we extract feature vectors of temporal signals and use them to build a patient network. Finally, the DeepNote, DeepTemporal, and patient network scores are linearly aggregated to fit the multimodal model on downstream prediction tasks. Our results are very competitive to the baseline model. The multimodal model analysis reveals that unstructured text data better help to estimate predictions than temporal signals. Moreover, there is no limitation in applying a patient network on structured data. In comparison to other modules, the patient network makes a more significant contribution to prediction tasks. We believe that our efforts in this work have opened up a new study area that can be used to enhance the performance of clinical predictive models.