More Like this

1. Long-term survival and second malignant tumor prediction in pediatric, adolescent, and young adult cancer survivors using Random Survival Forests: a SEER analysis

   https://doi.org/10.1038/s41598-023-29167-x  

   Zhang, Ivy Y.; Hart, Gregory R.; Qin, Bo; Deng, Jun (December 2023, Scientific Reports)

   Abstract Survival and second malignancy prediction models can aid clinical decision making. Most commonly, survival analysis studies are performed using traditional proportional hazards models, which require strong assumptions and can lead to biased estimates if violated. Therefore, this study aims to implement an alternative, machine learning (ML) model for survival analysis: Random Survival Forest (RSF). In this study, RSFs were built using the U.S. Surveillance Epidemiology and End Results to (1) predict 30-year survival in pediatric, adolescent, and young adult cancer survivors; and (2) predict risk and site of a second tumor within 30 years of the first tumor diagnosis in these age groups. The final RSF model for pediatric, adolescent, and young adult survival has an average Concordance index (C-index) of 92.9%, 94.2%, and 94.4% and average time-dependent area under the receiver operating characteristic curve (AUC) at 30-years since first diagnosis of 90.8%, 93.6%, 96.1% respectively. The final RSF model for pediatric, adolescent, and young adult second malignancy has an average C-index of 86.8%, 85.2%, and 88.6% and average time-dependent AUC at 30-years since first diagnosis of 76.5%, 88.1%, and 99.0% respectively. This study suggests the robustness and potential clinical value of ML models to alleviate physician burden by quickly identifying highest risk individuals. 

   more » « less
2. Optimal Lending Contracts with Retrospective and Prospective Bias

   https://doi.org/10.1257/pandp.20231115  

   Bohren, J Aislinn; Hauser, Daniel N (May 2023, AEA Papers and Proceedings)

   Model misspecification is a common approach to model belief formation distortions. Misspecified models can be decomposed into two classes of distortions: prospective and retrospective biases (Bohren and Hauser 2023). Prospective biases correspond to distortions in forecasting future beliefs, while retrospective biases correspond to distortions in interpreting information ex post. We disentangle the impact of these two distortions on optimal lending contracts in the context of an entrepreneur who borrows to invest in a project. The entrepreneur learns about project quality from a signal, which she interprets with a misspecified model. A lender leverages each form of bias in distinct ways. 

   more » « less
3. Machine Learning Applications in Solid Organ Transplantation and Related Complications

   https://doi.org/10.3389/fimmu.2021.739728  

   Balch, Jeremy A.; Delitto, Daniel; Tighe, Patrick J.; Zarrinpar, Ali; Efron, Philip A.; Rashidi, Parisa; Upchurch, Gilbert R.; Bihorac, Azra; Loftus, Tyler J. (September 2021, Frontiers in Immunology)

   The complexity of transplant medicine pushes the boundaries of innate, human reasoning. From networks of immune modulators to dynamic pharmacokinetics to variable postoperative graft survival to equitable allocation of scarce organs, machine learning promises to inform clinical decision making by deciphering prodigious amounts of available data. This paper reviews current research describing how algorithms have the potential to augment clinical practice in solid organ transplantation. We provide a general introduction to different machine learning techniques, describing their strengths, limitations, and barriers to clinical implementation. We summarize emerging evidence that recent advances that allow machine learning algorithms to predict acute post-surgical and long-term outcomes, classify biopsy and radiographic data, augment pharmacologic decision making, and accurately represent the complexity of host immune response. Yet, many of these applications exist in pre-clinical form only, supported primarily by evidence of single-center, retrospective studies. Prospective investigation of these technologies has the potential to unlock the potential of machine learning to augment solid organ transplantation clinical care and health care delivery systems. 

   more » « less
4. Contamination bias in the estimation of child maltreatment causal effects on adolescent internalizing and externalizing behavior problems

   https://doi.org/10.1111/jcpp.13990  

   Felt, John_M; Chimed‐Ochir, Ulziimaa; Shores, Kenneth_A; Olson, Anneke_E; Li, Yanling; Fisher, Zachary_F; Ram, Nilam; Shenk, Chad_E (April 2024, Journal of Child Psychology and Psychiatry)

   BackgroundWhen unaddressed, contamination in child maltreatment research, in which some proportion of children recruited for a nonmaltreated comparison group are exposed to maltreatment, downwardly biases the significance and magnitude of effect size estimates. This study extends previous contamination research by investigating how a dual‐measurement strategy of detecting and controlling contamination impacts causal effect size estimates of child behavior problems. MethodsThis study included 634 children from the LONGSCAN study with 63 cases of confirmed child maltreatment after age 8 and 571 cases without confirmed child maltreatment. Confirmed child maltreatment and internalizing and externalizing behaviors were recorded every 2 years between ages 4 and 16. Contamination in the nonmaltreated comparison group was identified and controlled by either a prospective self‐report assessment at ages 12, 14, and 16 or by a one‐time retrospective self‐report assessment at age 18. Synthetic control methods were used to establish causal effects and quantify the impact of contamination when it was not controlled, when it was controlled for by prospective self‐reports, and when it was controlled for by retrospective self‐reports. ResultsRates of contamination ranged from 62% to 67%. Without controlling for contamination, causal effect size estimates for internalizing behaviors were not statistically significant. Causal effects only became statistically significant after controlling contamination identified from either prospective or retrospective reports and effect sizes increased by between 17% and 54%. Controlling contamination had a smaller impact on effect size increases for externalizing behaviors but did produce a statistically significant overall effect, relative to the model ignoring contamination, when prospective methods were used. ConclusionsThe presence of contamination in a nonmaltreated comparison group can underestimate the magnitude and statistical significance of causal effect size estimates, especially when investigating internalizing behavior problems. Addressing contamination can facilitate the replication of results across studies. 

   more » « less
5. Planning to plan: a Bayesian model for optimizing the depth of decision tree search

   Kuperwajs, I.; Ma, W.J. (January 2021, Proceedings of the Annual Meeting of the Cognitive Science Society)

   Planning, the process of evaluating the future consequences of actions, is typically formalized as search over a decision tree. This procedure increases expected rewards but is computationally expensive. Past attempts to understand how people mitigate the costs of planning have been guided by heuristics or the accumulation of prior experience, both of which are intractable in novel, high-complexity tasks. In this work, we propose a normative framework for optimizing the depth of tree search. Specifically, we model a metacognitive process via Bayesian inference to compute optimal planning depth. We show that our model makes sensible predictions over a range of parameters without relying on retrospection and that integrating past experiences into our model produces results that are consistent with the transition from goal-directed to habitual behavior over time and the uncertainty associated with prospective and retrospective estimates. Finally, we derive an online variant of our model that replicates these results. 

   more » « less