Machine Learning Methods for Precision Dosing in Anticancer Drug Therapy: A Scoping Review.

INTRODUCTION: In the last decade, various Machine Learning techniques have been proposed aiming to individualise the dose of anticancer drugs mostly based on a presumed drug effect or measured effect biomarkers. The aim of this scoping review was to comprehensively summarise the research status on the use of Machine Learning for precision dosing in anticancer drug therapy. METHODS: This scoping review was conducted in accordance with the interim guidance by Cochrane and the Joanna Briggs Institute. We systematically searched the databases Medline (via PubMed), Embase and the Cochrane Library for research articles and reviews including results published after 2016. Results were reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) checklist. RESULTS: A total of 17 relevant studies was identified. In 12 of the included studies, Reinforcement Learning methods were used, including Classical, Deep, Double Deep and Conservative Q-Learning and Fuzzy Reinforcement Learning. Furthermore, classical Machine Learning methods were compared in terms of their performance and an artificial intelligence platform based on parabolic equations was used to guide dosing prospectively and retrospectively, albeit only in a limited number of patients. Due to the significantly different algorithm structures, a meaningful comparison between the various Machine Learning approaches was not possible. CONCLUSION: Overall, this review emphasises the clinical relevance of Machine Learning methods for anticancer drug dose optimisation, as many algorithms have shown promising results enabling model-free predictions with the potential to maximise efficacy and minimise toxicity when compared to standard protocols.

A dynamic ensemble model for short-term forecasting in pandemic situations.

During the COVID-19 pandemic, many hospitals reached their capacity limits and could no longer guarantee treatment of all patients. At the same time, governments endeavored to take sensible measures to stop the spread of the virus while at the same time trying to keep the economy afloat. Many models extrapolating confirmed cases and hospitalization rate over short periods of time have been proposed, including several ones coming from the field of machine learning. However, the highly dynamic nature of the pandemic with rapidly introduced interventions and new circulating variants imposed non-trivial challenges for the generalizability of such models. In the context of this paper, we propose the use of ensemble models, which are allowed to change in their composition or weighting of base models over time and could thus better adapt to highly dynamic pandemic or epidemic situations. In that regard, we also explored the use of secondary metadata-Google searches-to inform the ensemble model. We tested our approach using surveillance data from COVID-19, Influenza, and hospital syndromic surveillance of severe acute respiratory infections (SARI). In general, we found ensembles to be more robust than the individual models. Altogether we see our work as a contribution to enhance the preparedness for future pandemic situations.

Integrating machine learning with pharmacokinetic models: Benefits of scientific machine learning in adding neural networks components to existing PK models.

Recently, the use of machine-learning (ML) models for pharmacokinetic (PK) modeling has grown significantly. Although most of the current approaches use ML techniques as black boxes, there are only a few that have proposed interpretable architectures which integrate mechanistic knowledge. In this work, we use as the test case a one-compartment PK model using a scientific machine learning (SciML) framework and consider learning an unknown absorption using neural networks, while simultaneously estimating other parameters of drug distribution and elimination. We generate simulated data with different sampling strategies to show that our model can accurately predict concentrations in extrapolation tasks, including new dosing regimens with different sparsity levels, and produce reliable forecasts even for new patients. By using a scenario of fitting PK data with complex absorption, we demonstrate that including known physiological structure into an SciML model allows us to obtain highly accurate predictions while preserving the interpretability of classical compartmental models.

Development of an early alert model for pandemic situations in Germany.

The COVID-19 pandemic has pointed out the need for new technical approaches to increase the preparedness of healthcare systems. One important measure is to develop innovative early warning systems. Along those lines, we first compiled a corpus of relevant COVID-19 related symptoms with the help of a disease ontology, text mining and statistical analysis. Subsequently, we applied statistical and machine learning (ML) techniques to time series data of symptom related Google searches and tweets spanning the time period from March 2020 to June 2022. In conclusion, we found that a long-short-term memory (LSTM) jointly trained on COVID-19 symptoms related Google Trends and Twitter data was able to accurately forecast up-trends in classical surveillance data (confirmed cases and hospitalization rates) 14 days ahead. In both cases, F1 scores were above 98% and 97%, respectively, hence demonstrating the potential of using digital traces for building an early alert system for pandemics in Germany.

Smart pooling: AI-powered COVID-19 informative group testing.

Massive molecular testing for COVID-19 has been pointed out as fundamental to moderate the spread of the pandemic. Pooling methods can enhance testing efficiency, but they are viable only at low incidences of the disease. We propose Smart Pooling, a machine learning method that uses clinical and sociodemographic data from patients to increase the efficiency of informed Dorfman testing for COVID-19 by arranging samples into all-negative pools. To do this, we ran an automated method to train numerous machine learning models on a retrospective dataset from more than 8000 patients tested for SARS-CoV-2 from April to July 2020 in Bogotá, Colombia. We estimated the efficiency gains of using the predictor to support Dorfman testing by simulating the outcome of tests. We also computed the attainable efficiency gains of non-adaptive pooling schemes mathematically. Moreover, we measured the false-negative error rates in detecting the ORF1ab and N genes of the virus in RT-qPCR dilutions. Finally, we presented the efficiency gains of using our proposed pooling scheme on proof-of-concept pooled tests. We believe Smart Pooling will be efficient for optimizing massive testing of SARS-CoV-2.

The economics of shrimp disease.

Shrimp is not only one of the world's most valuable aquaculture species, but also a species that encounter high economic losses due to diseases. Diseases are sufficiently important to influence global supply and prices for longer periods. Profitability is the driving force behind shrimp farming and high profits associated with the absence of disease largely determines where shrimp production does take place; i.e. prevalence of disease leads to geographic relocation. In this paper, a basic economic model for the impact of the disease on a shrimp farm is provided and a Monte Carlo simulation is provided to illustrate the impact of disease on economic risk. Improved technologies, knowledge, and governance are important elements utilized in the mitigation of diseases in various shrimp producing countries. Economic aspects such as profitability in the absence and presence of diseases and cost of treatment determines the global production of shrimp along with shaping technologies and production systems.

The fishery performance indicators: a management tool for triple bottom line outcomes.

Pursuit of the triple bottom line of economic, community and ecological sustainability has increased the complexity of fishery management; fisheries assessments require new types of data and analysis to guide science-based policy in addition to traditional biological information and modeling. We introduce the Fishery Performance Indicators (FPIs), a broadly applicable and flexible tool for assessing performance in individual fisheries, and for establishing cross-sectional links between enabling conditions, management strategies and triple bottom line outcomes. Conceptually separating measures of performance, the FPIs use 68 individual outcome metrics--coded on a 1 to 5 scale based on expert assessment to facilitate application to data poor fisheries and sectors--that can be partitioned into sector-based or triple-bottom-line sustainability-based interpretative indicators. Variation among outcomes is explained with 54 similarly structured metrics of inputs, management approaches and enabling conditions. Using 61 initial fishery case studies drawn from industrial and developing countries around the world, we demonstrate the inferential importance of tracking economic and community outcomes, in addition to resource status.

Corioangioma placentario en el Hospital Victor Ríos Ruiz de Los Angeles: presentación de un caso / Placental chorioangioma at the Hospital Victor Ríos Ruiz of Los Angeles: presentation of a case

Chorioangioma is the most frequent placenta non trophoblastic tumor. It is a benign arteriovenous malformation, that can be unique, multiple or more rarely diffuse within the placenta. They can be diagnosed by ecography and they are observed as subchorionic compound injuries of hipoecogenic images around an ecogenic center. A case diagnosed during week 28 of pregnancy will be reviewed which was referred from primary care to the High Risk Fetus Unit with ecographic findings of placentary tumor. Its handling is described and later pathological diagnose compatible with placenta tumor: chorioangioma.

El corioangioma o hemangioma de la placenta es el tumor no trofoblástico más frecuente de la placenta. Es una malformación arterio-venosa benigna, que puede ser única, múltiple o más raramente difusa dentro de la placenta. Deben ser diagnosticados por ultrasonografía y se observan como lesiones subcoriónicas compuestas de imágenes hipoecoicas alrededor de un centro ecogénico. Se revisa un caso diagnosticado durante semana 28 de embarazo la cual fue referida desde su consultorio a la unidad de Feto de Alto Riesgo por hallazgo ultrasonográfico de masa placentaria. Se describe su manejo y posterior diagnóstico patológico de tumor placentario compatible con corioangioma.

High prevalence of hepatitis c virus infection in chronic hemodialysis patients

Hepatitis C virus (HCV) infection is very common among hemodialysis (HD) patients. Transmission of Infection in this setting has been related to the number of blood transfusions, the duration of hemodialysis and to nosocomial transmission of virus in the dialysis unit. We conducted a study of 74 HD patients to determine the frequency of HCV at a single point in time (cross-sectional analysis), and to evaluate the association between HCV infection and patients' demographic, clinical and biochemical features. Serum samples were tested for anti-HCV antibodies using a third-generation enzyme-linked immunosorbent assay (ELISA). In the case of a positive result, third-generation recombinant immunoblot and HCV RNA detection by polymerase chain reaction (PCR) tests were performed. Collected data included the patient's age, gender, time on HD, number of blood transfusions and serum alanine aminotransferase (ALT) activity. Twenty-nine patients (29/74.4 percent) were found to be HCV positive using a third generation ELISA assay. From these 29 patients, 27 were also positive by recombinant immunoblot assay and 2 patients had indederminate results. In the subgroup of anti-HCV ELISA positive, 20 (69 percent) of the 29 patients had detectable HCV RNA. The HCV RNA positive patients had received more blood transfusions (15ñ3 vs.5ñ1 units of packed red blood cells, p<0.0001) and had been on HD for a longer period of time than the HCV RNA negative patients (65ñ32 vs.32ñ29 months, p<0.0001). Mean serum ALT levels were significantly higher in the HCV RNA positive group (30ñ18 vs.15ñ9,p<0.0001). We were unable to determine the most likely mode of transmission in our unit, but these results emphasize the need for strict adherence to blood collecting and handing precautions, careful attention to hygiene in the dialysis units, and sterilization of dialysis machines in order to properly combat this frequent infection.